Academic literature on the topic 'Habitat predictive model'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Habitat predictive model.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Habitat predictive model"
1
Reisinger, Ryan R., Ari S. Friedlaender, Alexandre N. Zerbini, Daniel M. Palacios, Virginia Andrews-Goff, Luciano Dalla Rosa, Mike Double, et al. "Combining Regional Habitat Selection Models for Large-Scale Prediction: Circumpolar Habitat Selection of Southern Ocean Humpback Whales." Remote Sensing 13, no. 11 (May 25, 2021): 2074. http://dx.doi.org/10.3390/rs13112074.
Full textAbstract:
Machine learning algorithms are often used to model and predict animal habitat selection—the relationships between animal occurrences and habitat characteristics. For broadly distributed species, habitat selection often varies among populations and regions; thus, it would seem preferable to fit region- or population-specific models of habitat selection for more accurate inference and prediction, rather than fitting large-scale models using pooled data. However, where the aim is to make range-wide predictions, including areas for which there are no existing data or models of habitat selection, how can regional models best be combined? We propose that ensemble approaches commonly used to combine different algorithms for a single region can be reframed, treating regional habitat selection models as the candidate models. By doing so, we can incorporate regional variation when fitting predictive models of animal habitat selection across large ranges. We test this approach using satellite telemetry data from 168 humpback whales across five geographic regions in the Southern Ocean. Using random forests, we fitted a large-scale model relating humpback whale locations, versus background locations, to 10 environmental covariates, and made a circumpolar prediction of humpback whale habitat selection. We also fitted five regional models, the predictions of which we used as input features for four ensemble approaches: an unweighted ensemble, an ensemble weighted by environmental similarity in each cell, stacked generalization, and a hybrid approach wherein the environmental covariates and regional predictions were used as input features in a new model. We tested the predictive performance of these approaches on an independent validation dataset of humpback whale sightings and whaling catches. These multiregional ensemble approaches resulted in models with higher predictive performance than the circumpolar naive model. These approaches can be used to incorporate regional variation in animal habitat selection when fitting range-wide predictive models using machine learning algorithms. This can yield more accurate predictions across regions or populations of animals that may show variation in habitat selection.
2
Meißner, Karin, and Alexander Darr. "Distribution of Magelona species (Polychaeta: Magelonidae) in the German Bight (North Sea): a modeling approach." Zoosymposia 2, no. 1 (August 31, 2009): 567–86. http://dx.doi.org/10.11646/zoosymposia.2.1.39.
Full textAbstract:
The aim of the present study was the development of species-habitat models for four Magelona species (Polychaeta: Magelonidae) found in the German Bight in the SE North Sea. Analyses were based on field data and data obtained from reexamination of material deposited in museum collections. In addition, data on environmental variables were retrieved from the sediment map by Figge (1981) and from long-term monitoring data sets. The statistical modeling technique applied was multivariate adaptive regression splines (MARS). Predictive accuracy measures were calculated for each model. The candidate model with highest discriminatory power was selected for predictive mapping. Models with excellent predictive performance were developed for Magelona johnstoni, M. filiformis and M. alleni based on the analyzed set of environmental predictors. In each of the developed habitat models the most important predictor was a sediment parameter, either median grain size diameter (M. johnstoni) or mud content (M. alleni, M. filiformis). Salinity and water depth were also of importance. Model predictions were aimed to allow evaluation of habitat suitability for the investigated species in the German Bight. According to our results suitable habitats for M. johnstoni are numerous and a wide distribution of this species could be expected. Habitat suitability for M. filiformis in the German Bight was suggested to be high in areas with mud contents below 10 % at water depths between 25 and 35 m. The M. alleni habitat model indicated the presence of suitable habitats where sands with elevated mud contents are present and where water depths exceed 30 m.
3
Enwright, Nicholas M., Lei Wang, Hongqing Wang, Michael J. Osland, Laura C. Feher, Sinéad M. Borchert, and Richard H. Day. "Modeling Barrier Island Habitats Using Landscape Position Information." Remote Sensing 11, no. 8 (April 24, 2019): 976. http://dx.doi.org/10.3390/rs11080976.
Full textAbstract:
Barrier islands are dynamic environments because of their position along the marine–estuarine interface. Geomorphology influences habitat distribution on barrier islands by regulating exposure to harsh abiotic conditions. Researchers have identified linkages between habitat and landscape position, such as elevation and distance from shore, yet these linkages have not been fully leveraged to develop predictive models. Our aim was to evaluate the performance of commonly used machine learning algorithms, including K-nearest neighbor, support vector machine, and random forest, for predicting barrier island habitats using landscape position for Dauphin Island, Alabama, USA. Landscape position predictors were extracted from topobathymetric data. Models were developed for three tidal zones: subtidal, intertidal, and supratidal/upland. We used a contemporary habitat map to identify landscape position linkages for habitats, such as beach, dune, woody vegetation, and marsh. Deterministic accuracy, fuzzy accuracy, and hindcasting were used for validation. The random forest algorithm performed best for intertidal and supratidal/upland habitats, while the K-nearest neighbor algorithm performed best for subtidal habitats. A posteriori application of expert rules based on theoretical understanding of barrier island habitats enhanced model results. For the contemporary model, deterministic overall accuracy was nearly 70%, and fuzzy overall accuracy was over 80%. For the hindcast model, deterministic overall accuracy was nearly 80%, and fuzzy overall accuracy was over 90%. We found machine learning algorithms were well-suited for predicting barrier island habitats using landscape position. Our model framework could be coupled with hydrodynamic geomorphologic models for forecasting habitats with accelerated sea-level rise, simulated storms, and restoration actions.
4
Rice, M. B., A. D. Apa, and L. A. Wiechman. "The importance of seasonal resource selection when managing a threatened species: targeting conservation actions within critical habitat designations for the Gunnison sage-grouse." Wildlife Research 44, no. 5 (2017): 407. http://dx.doi.org/10.1071/wr17027.
Full textAbstract:
Context The ability to identify priority habitat is critical for species of conservation concern. The designation of critical habitat under the US Endangered Species Act 1973 identifies areas occupied by the species that are important for conservation and may need special management or protection. However, relatively few species’ critical habitats designations incorporate habitat suitability models or seasonal specificity, even when that information exists. Gunnison sage-grouse (GUSG) have declined substantially from their historical range and were listed as threatened by the US Fish and Wildlife Service (USFWS) in November 2014. GUSG are distributed into eight isolated populations in Colorado and Utah, and one population, the Gunnison Basin (GB), has been the focus of much research. Aims To provide season-specific resource selection models to improve targeted conservation actions within the designated critical habitat in the GB. Methods We utilised radio-telemetry data from GUSG captured and monitored from 2004 to 2010. We were able to estimate resource selection models for the breeding (1 April–15 July) and summer (16 July–30 September) seasons in the GB using vegetation, topographical and anthropogenic variables. We compared the seasonal models with the existing critical habitat to investigate whether the more specific seasonal models helped identify priority habitat for GUSG. Key results The predictive surface for the breeding model indicated higher use of large areas of sagebrush, whereas the predictive surface for the summer model predicted use of more diverse habitats. The breeding and summer models (combined) matched the current critical habitat designation 68.5% of the time. We found that although the overall habitat was similar between the critical habitat designation and our combined models, the pattern and configuration of the habitat were very different. Conclusions These models highlight areas with favourable environmental variables and spatial juxtaposition to establish priority habitat within the critical habitat designated by USFWS. More seasonally specific resource selection models will assist in identifying specific areas within the critical habitat designation to concentrate habitat improvements, conservation and restoration within the GB. Implications This information can be used to provide insight into the patterns of seasonal habitat selection and can identify priority GUSG habitat to incorporate into critical habitat designation for targeted management actions.
5
Haxton, Tim J., C. Scott Findlay, and R. W. Threader. "Predictive Value of a Lake Sturgeon Habitat Suitability Model." North American Journal of Fisheries Management 28, no. 5 (October 2008): 1373–83. http://dx.doi.org/10.1577/m07-146.1.
Full text
6
Street, Garrett M., Lucas M. Vander Vennen, Tal Avgar, Anna Mosser, Morgan L. Anderson, Arthur R. Rodgers, and John M. Fryxell. "Habitat selection following recent disturbance: model transferability with implications for management and conservation of moose (Alces alces)." Canadian Journal of Zoology 93, no. 11 (November 2015): 813–21. http://dx.doi.org/10.1139/cjz-2015-0005.
Full textAbstract:
Site-specific variation in relative habitat abundance and disturbance regimes may produce differences in habitat preferences of associated populations. An evaluation of the predictive power of habitat selection models across space would benefit our understanding of the reliability of models of selection and space use in predicting animal occurrence. We used presence–absence data from winter surveys of moose (Alces alces (L., 1758)) to estimate resource selection functions (RSFs) across two study sites using Far North Land Cover updated with recent disturbance from fire and timber harvest. Moose selected foraging habitat (e.g., deciduous land cover) and for increasing deciduous foliage cover (ΔNDVI, i.e., the difference in the normalized difference vegetation index). Snow depth negatively influenced habitat selection, likely due to increased predation risk and reduced movement and foraging efficiency. Models lost little predictive power when applied to another site based on comparison of receiver operating characteristic (ROC) curves. Our results corroborated the current body of knowledge concerning moose habitat selection, i.e., moose preferentially use forest stands dominated by deciduous species, but suggested that moose strongly avoided very recently disturbed areas. Minimal site-specific variation and ROC comparison suggests that RSFs may be extended into novel systems, given adequate consideration for habitat quality and abundance, thereby simplifying management needs of this important species.
7
TAKEMURA, Shion, Yoshihisa AKAMATSU, and Mahito KAMADA. "Evaluation of vulnerability of mangrove habitats using predictive habitat distribution model in Palau Islands." Journal of Japan Society of Civil Engineers, Ser. G (Environmental Research) 68, no. 5 (2012): I_105—I_110. http://dx.doi.org/10.2208/jscejer.68.i_105.
Full text
8
Buechling, Arne, and Claudine Tobalske. "Predictive Habitat Modeling of Rare Plant Species in Pacific Northwest Forests." Western Journal of Applied Forestry 26, no. 2 (April 1, 2011): 71–81. http://dx.doi.org/10.1093/wjaf/26.2.71.
Full textAbstract:
Abstract Certification requirements associated with the Sustainable Forestry Initiative include efforts to identify and protect occurrences of endangered plant species. Habitat models were constructed in this study using maximum entropy and random forest algorithms to generate independent predictions for four selected rare plants, Castilleja chambersii, Erythronium elegans, Filipendula occidentalis, and Sidalcea nelsoniana, associated with divergent physical environments. Explanatory variables used to model rare plant occurrence included Landsat Enhanced Thematic Mapper Plus spectral imagery, spectral-based vegetation indices, climatic data, and several terrain variables derived from a digital elevation model. Models were trained with known occurrence records obtained from the Oregon Biodiversity Information Center. Subsequent field surveys were conducted to acquire randomly located test data for comparative model evaluation. A range of accuracy statistics was computed that indicated generally high prediction accuracy for both methods. Model performance was highest for species with narrow, well-defined ecological requirements at scales comparable to the resolution of the calibration data. Species with relatively broad ecological distributions or with extremely specific habitat requirements were less accurately predicted. Random forest-based models generally produced higher rates of prediction success than maximum entropy when model performance was limited by the ecology of a species. Field surveys identified 22 previously unknown populations of the target rare plants, suggesting the efficacy of habitat models for predicting rare species occurrence and their utility as a prescriptive tool for land management planning.
9
Alabia, Irene D., Sei-Ichi Saitoh, Hiromichi Igarashi, Yoichi Ishikawa, Norihisa Usui, Masafumi Kamachi, Toshiyuki Awaji, and Masaki Seito. "Ensemble squid habitat model using three-dimensional ocean data." ICES Journal of Marine Science 73, no. 7 (May 6, 2016): 1863–74. http://dx.doi.org/10.1093/icesjms/fsw075.
Full textAbstract:
Abstract Neon flying squid (Ommastrephes bartramii) is a large pelagic squid internationally harvested in the North Pacific. Here, we examined its potential habitat in the central North Pacific using an ensemble modelling approach. Initially, ten statistical models were constructed by combining the squid fishing points, selected vertical layers of the sea temperature and salinity, sea surface height (SSH), and SSH gradient from the multi-variate ocean variational estimation system for the western North Pacific from June to July 1999–2011. The variable selection analyses have captured the importance of vertical temperature and salinity layers at the upper 300 and 440 m, respectively, coinciding with the reported vertical ranges of diel migration for the squid's primary prey species in the North Pacific. The evaluation of the habitat predictions using the independent sets of the presence data from 2012 to 2014 showed significant variability in the predictive accuracy, which is likely reflective of the interannual differences in environmental conditions across the validation periods. Our findings from ensemble habitat model approach using three-dimensional oceanographic data were able to characterize the near- and subsurface habitats of the neon flying squid. Moreover, our results underpinned the possible link between interannual environmental variability and spatio-temporal patterns of potential squid habitats. As such, these further suggest that an ensemble model approach could present a promising tool for operational fishery application and squid resource management.
10
Socolar, Jacob B., and David S. Wilcove. "Forest-type specialization strongly predicts avian responses to tropical agriculture." Proceedings of the Royal Society B: Biological Sciences 286, no. 1913 (October 23, 2019): 20191724. http://dx.doi.org/10.1098/rspb.2019.1724.
Full textAbstract:
Species’ traits influence how populations respond to land-use change. However, even in well-characterized groups such as birds, widely studied traits explain only a modest proportion of the variance in response across species. Here, we show that associations with particular forest types strongly predict the sensitivity of forest-dwelling Amazonian birds to agriculture. Incorporating these fine-scale habitat associations into models of population response dramatically improves predictive performance and markedly outperforms the functional traits that commonly appear in similar analyses. Moreover, by identifying habitat features that support assemblages of unusually sensitive habitat-specialist species, our model furnishes straightforward conservation recommendations. In Amazonia, species that specialize on forests along a soil–nutrient gradient (i.e. both rich-soil specialists and poor-soil specialists) are exceptionally sensitive to agriculture, whereas species that specialize on floodplain forests are unusually insensitive. Thus, habitat specialization per se does not predict disturbance sensitivity, but particular habitat associations do. A focus on conserving specific habitats that harbour highly sensitive avifaunas (e.g. poor-soil forest) would protect a critically threatened component of regional biodiversity. We present a conceptual model to explain the divergent responses of habitat specialists in the different habitats, and we suggest that similar patterns and conservation opportunities probably exist for other taxa and regions.
Dissertations / Theses on the topic "Habitat predictive model"
1
Machemer, Ethan G. P. "A Predictive Habitat Model for Rainbow Parrotfish Scarus guacamaia." NSUWorks, 2010. http://nsuworks.nova.edu/occ_stuetd/212.
Full textAbstract:
The rainbow parrotfish Scarus guacamaia is a prominent herbivore in the coastal waters of southeastern Florida whose life history is strongly linked to a dependence on both mangrove and coral reef habitats. Rainbow parrotfish in turn serve in maintaining the health of coral reefs by keeping algal populations in check. This study used NOAA Fisheries data from the Mangrove Visual Census and the Reef Visual Census in Biscayne Bay and Upper Florida Bay. Observations of abiotic factors at individual sites were used to correlate and predict presence and absence of this species. This was done to visualize habitat presence and ontogenetic shifts present in this species between juvenile and adult stages through ArcGIS mapping. Logistic regression analysis was used to predict presence or absence using the environmental variables of temperature, dissolved oxygen, salinity, average depth, distance from channel openings, mangrove presence, temperature Δ, and salinity Δ. Average depth, distance from channel openings, temperature Δ and salinity Δ were significant in predicting the presence of this species, while salinity, temperature, dissolved oxygen, and mangrove presence were not. Conservation efforts for this species, listed as vulnerable under the IUCN, need to be given greater consideration. The health of this and other parrotfish may have a greater impact on coral reef ecosystems across the Caribbean Sea than currently acknowledged and management breadth and priorities should be adjusted to reflect this role.
2
Alizadeh, Shabani Afshin, and afshin alizadeh@rmit edu au. "Identifying bird species as biodiversity indicators for terrestrial ecosystem management." RMIT University. Mathematical and Geospatial Sciences, 2006. http://adt.lib.rmit.edu.au/adt/public/adt-VIT20061116.161912.
Full textAbstract:
It is widely known that the world is losing biodiversity and primarily it is thought to be caused by anthropogenic activities. Many of these activities have been identified. However, we still lack a clear understanding of the causal relationships between human activities and the pressures they place on the environment and biodiversity. We need to know how ecosystems and individual species respond to changes in human activities and therefore how best to moderate our actions and reduce the rate of loss of biodiversity. One of the ways to detect these changes is to use indicators of ecosystem conditions. Indicators are statistics following changes in a particular factor usually over time. These indicators are used to summarise a complex set of data, and are seen as being representative of the wider situation in that field. So it can be assumed that if that particular factor is declining or improving, then the situation in general is also declining or improving. They are used to check the status and trends of biodiversity by both the public and policy makers. Indicators are also used to assess national performance and can be used to identify the actions required at the policy level. In this manner, they provide an important link between policy-makers and scientists collecting the data. The current thesis investigates the possibility of using bird species as indicators of biodiversity for better management of natural terrestrial ecosystems, by identifying their habitats according to various environmental factors. The study is established by drawing upon three main scientific areas: ecology, geographical information system (GIS), and statistical modelling. The Mornington Peninsula and Western Port Biosphere Reserve (MPWPBR) (Victoria, Australia) was chosen for the study area because of the combination of suburban and natural environments that made it optimum for this type of study. Once the study area was defined, the necessary data for the research were obtained from various sources. Birds Australia provided data on recorded observation of 271 bird species within the study area. Based on the nature of this study, seven species were selected for the study. The criteria for this selection are discussed in Chapter 3. Most literature state that the primary determinant for bird abundance is vegetation and land cover. Because of this, Ecological Vegetation Class (EVC) layer was used to determine which type(s) of vegetation have the greatest impact on habitat selection. Each species showed a relationship to a number of v vegetation types. These EVCs were combined to produce vegetation patches, and were considered as potentially suitable habitats of corresponding bird species. For each of the species, these habitat patches were analysed for the different aspects of patch characteristics (such as the level of patchiness, connectivity, size, shape, weighted distance between patches, etc.) by using the Landscape Context Tool (a GIS add-on). This process assisted the understanding of the importance of patch quality in habitat selection among different bird species by analysing the location of bird observation sites relative to habitat patches. In this way, the association between bird presence and the conditions of a habitat patch was identified by performing a discriminant function analysis. To investigate the probability of a species presence according to different environmental factors, a model of species distribution was created. Binary logistic regression was used to indicate the level of effect of each variable. The model was then successfully validated in the field. To define the indicators of environmental factors, it was essential to separate bird species based on their dependency on one or more of the studied variables. For this purpose, One-Way ANOVA was used. This analysis showed that some bird species can be considered as indicators of urban areas, while others could be good indicators of wellpreserved large forests. Finally, it must be mentioned that the type and quality of the datasets are crucial to this type of study, because some species have a higher degree of sensitivity to certain types of vegetation or land cover. Therefore, the vegetation data must be produced as detailed as possible. At the same time, the species data needs to be collected based on the presence and absence (versus presence-only) of the birds.
3
Embling, Clare B. "Predictive models of cetacean distributions off the west coast of Scotland." Thesis, University of St Andrews, 2008. http://hdl.handle.net/10023/640.
Full textAbstract:
The main purpose of this study was to produce and test the reliability of predictive models of cetacean distributions off the west coast of Scotland. Passive acoustic and visual surveys were carried out from platforms of opportunity between 2003 and 2005. Acoustic identifications were made primarily of harbour porpoises (Phocoena phocoena), delphinids, and sperm whales (Physeter macrocephalus). Generalised Additive Models (GAMs) were used to relate species’ distributions to a range of environmental variables over a range of temporal and spatial scales. Predictive models of delphinid distributions showed both inter-annual and inter-month variations. Combining all data for all months and years resulted in a model that combined the environmental influences from each monthly and yearly model. Overall, delphinids were found to associate with the deep (> 400m) warm water (10.5°C-12.5°C), and in areas of deep thermocline. Relationships between sperm whales and environmental variables were consistent over changes in grain size (9 km or 18 km), but not between areas. Although sperm whales were distributed in deep water characterised by weak thermoclines and strong haloclines in the most northerly area (Faroe-Shetland Channel), they were found in deep productive areas with cold surface temperature in the more southerly waters (Rockall Trough). Within the southern Inner Hebrides, high use areas for harbour porpoises were consistently predicted over time (in years) and with differing survey techniques (acoustic versus visual), but not over space (southern Inner Hebrides versus whole of the Inner Hebrides). Harbour porpoises were mainly distributed in areas with low tidal currents and with higher detection rates during spring tides. The use of prey as a predictor variable within models of delphinid distribution shows some promise: there were correlations between delphinid and herring (Clupea harengus) in shelf-waters in 2005 but not in 2004. These models can be used in mitigating acoustic threats to cetaceans in predicted high use areas off the west coast of Scotland.
4
Morris, Charisa Maria. "Building a Predictive Model of Delmarva Fox Squirrel (Sciurus niger cinereus) Occurrence Using Infrared Photomonitors." Thesis, Virginia Tech, 2006. http://hdl.handle.net/10919/35356.
Full textAbstract:
Habitat modeling can assist in managing potentially widespread but poorly known biological resources such as the federally endangered Delmarva fox squirrel (DFS; Sciurus niger cinereus). The ability to predict or identify suitable habitat is a necessary component of this species' recovery. Habitat identification is also an important consideration when evaluating impacts of land development on this species distribution, which is limited to the Delmarva Peninsula. The goal of this study was to build a predictive model of DFS occurrence that can be used towards the effective management of this species.
I developed 5 a'priori global models to predict DFS occurrence based on literature review, past models, and professional experience. I used infrared photomonitors to document habitat use of Delmarva fox squirrels at 27 of 86 sites in the southern Maryland portion of the Delmarva Peninsula. All data were collected on the U.S. Fish and Wildlife Service Chesapeake Marshlands National Wildlife Refuge in Dorchester County, Maryland. Preliminary analyses of 27 DFS present (P) and 59 DFS absent (A) sites suggested that DFS use in my study area was significantly (Wilcoxon Mann-Whitney, P < 0.10) correlated with tree stems > 50 cm dbh/ha (Pmean = 16 + 3.8, Amean = 8+ 2.2), tree stems > 40 cm dbh/ha (Pmean = 49 + 8.1, Amean = 33 + 5.5), understory height (Pmean = 11 m + 0.8, Amean = 9 m + 0.5), overstory canopy height (Pmean = 31 m + 0.6, Amean = 28 m + 0.6), percent overstory cover (Pmean = 82 + 3.9, Amean = 73 + 3.1), shrub stems/ha (Pmean = 8068 + 3218, Amean = 11,119 + 2189), and distance from agricultural fields (Pmean = 964 m + 10, Amean = 1308 m + 103). Chi-square analysis indicated a correlation with shrub evenness (observed on 7% of DFS present sites and 21% of DFS absent sites). Using logistic regression and the Information Theoretic approach, I developed 7 model sets (5 a priori and 2 post hoc) to predict the probability of Delmarva fox squirrel habitat use as a function of micro- and macro-habitat characteristics.
Of over 200 total model arrays tested, the model that fit the statistical, biological, and pragmatic criteria postulated was a post hoc integrated model: DFS use = percent overstory cover + shrub evenness + overstory canopy height. This model was determined to be the best of its subset (wi = 0.54), had a high percent concordance (>75%), a significant likelihood ratio (P = 0.0015), and the lowest AICc value (98.3) observed. Employing this predictive model of Delmarva fox squirrel occurrence can benefit recovery and consultation processes by facilitating systematic rangewide survey efforts and simplifying site screenings.<br>Master of Science
5
Amey, Katherine Springer. "Hydrology And Predictive Model Of Headwater Streams And The Groundwater/Surface Water Interactions Supporting Brook Trout Habitat In Northeast Ohio." Kent State University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=kent1301618586.
Full text
6
González-Andrés, Cristina. "The role of marine offshore protected areas in protecting large pelagics. Practical case: Cocos Island National Park (Costa Rica)." Doctoral thesis, Universidad de Alicante, 2020. http://hdl.handle.net/10045/115291.
Full text
7
Wickert, Claudia. "Breeding white storks in former East Prussia : comparing predicted relative occurrences across scales and time using a stochastic gradient boosting method (TreeNet), GIS and public data." Master's thesis, Universität Potsdam, 2007. http://opus.kobv.de/ubp/volltexte/2007/1353/.
Full textAbstract:
In dieser Arbeit wurden verschiedene GIS-basierte Habitatmodelle für den Weißstorch (Ciconia ciconia) im Gebiet der ehemaligen deutschen Provinz Ostpreußen (ca. Gebiet der russischen Exklave Kaliningrad und der polnischen Woiwodschaft Ermland-Masuren) erstellt. Zur Charakterisierung der Beziehung zwischen dem Weißstorch und der Beschaffenheit seiner Umwelt wurden verschiedene historische Datensätze über den Bestand des Weißstorches in den 1930er Jahren sowie ausgewählte Variablen zur Habitat-Beschreibung genutzt. Die Aufbereitung und Modellierung der verwendeten Datensätze erfolgte mit Hilfe eines geographischen Informationssystems (ArcGIS) und einer statistisch-mathematischen Methode aus den Bereichen „Machine Learning“ und „Data-Mining“ (TreeNet, Salford Systems Ltd.).
Unter Verwendung der historischen Habitat-Parameter sowie der Daten zum Vorkommen des Weißstorches wurden quantitative Modelle auf zwei Maßstabs-Ebenen erstellt: (i) auf Punktskala unter Verwendung eines Rasters mit einer Zellgröße von 1 km und (ii) auf Verwaltungs-Kreisebene basierend auf der Gliederung der Provinz Ostpreußen in ihre Landkreise.
Die Auswertung der erstellten Modelle zeigt, dass das Vorkommen von Storchennestern im ehemaligen Ostpreußen, unter Berücksichtigung der hier verwendeten Variablen, maßgeblich durch die Variablen ‚forest’, ‚settlement area’, ‚pasture land’ und ‚coastline’ bestimmt wird. Folglich lässt sich davon ausgehen, dass eine gute Nahrungsverfügbarkeit, wie der Weißstorch sie auf Wiesen und Weiden findet, sowie die Nähe zu menschlichen Siedlungen ausschlaggebend für die Nistplatzwahl des Weißstorches in Ostpreußen sind. Geschlossene Waldgebiete zeigen sich in den Modellen als Standorte für Horste des Weißstorches ungeeignet. Der starke Einfluss der Variable ‚coastline’ lässt sich höchstwahrscheinlich durch die starke naturräumliche Gliederung Ostpreußens parallel zur Küstenlinie erklären.
In einem zweiten Schritt konnte unter Verwendung der in dieser Arbeit erstellten Modelle auf beiden Skalen Vorhersagen für den Zeitraum 1981-1993 getroffen werden. Dabei wurde auf dem Punktmaßstab eine Abnahme an potentiellem Bruthabitat vorhergesagt. Im Gegensatz dazu steigt die vorhergesagte Weißstorchdichte unter Verwendung des Modells auf Verwaltungs-Kreisebene. Der Unterschied zwischen beiden Vorhersagen beruht vermutlich auf der Verwendung unterschiedlicher Skalen und von zum Teil voneinander verschiedenen erklärenden Variablen. Weiterführende Untersuchungen sind notwendig, um diesen Sachverhalt zu klären.
Des Weiteren konnten die Modellvorhersagen für den Zeitraum 1981-1993 mit den vorliegenden Bestandserfassungen aus dieser Zeit deskriptiv verglichen werden. Es zeigt sich hierbei, dass die hier vorhergesagten Bestandszahlen höher sind als die in den Zählungen ermittelten. Die hier erstellten Modelle beschreiben somit vielmehr die Kapazität des Habitats. Andere Faktoren, die die Größe der Weißstorch-Population bestimmen, wie z.B. Bruterfolg oder Mortalität sollten in zukünftige Untersuchungen mit einbezogen werden.
Es wurde ein möglicher Ansatz aufgezeigt, wie man mit den hier vorgestellten Methoden und unter Verwendung historischer Daten wertvolle Habitatmodelle erstellen sowie die Auswirkung von Landnutzungsänderungen auf den Weißstorch beurteilen kann. Die hier erstellten Modelle sind als erste Grundlage zu sehen und lassen sich mit Hilfe weitere Daten hinsichtlich Habitatstruktur und mit exakteren räumlich expliziten Angaben zu Neststandorten des Weißstorches weiter verfeinern. In einem weiteren Schritt sollte außerdem ein Habitatmodell für die heutige Zeit erstellt werden. Dadurch wäre ein besserer Vergleich möglich hinsichtlich erdenklicher Auswirkungen von Änderungen der Landnutzung und relevanten Umweltbedingungen auf den Weißstorch im Gebiet des ehemaligen Ostpreußens sowie in seinem gesamten Verbreitungsgebiet.<br>Different habitat models were created for the White Stork (Ciconia ciconia) in the region of the former German province of East Prussia (equals app. the current Russian oblast Kaliningrad and the Polish voivodship Warmia-Masuria). Different historical data sets describing the occurrence of the White Stork in the 1930s, as well as selected variables for the description of landscape and habitat, were employed. The processing and modeling of the applied data sets was done with a geographical information system (ArcGIS) and a statistical modeling approach that comes from the disciplines of machine-learning and data mining (TreeNet by Salford Systems Ltd.).
Applying historical habitat descriptors, as well as data on the occurrence of the White Stork, models on two different scales were created: (i) a point scale model applying a raster with a cell size of 1 km2 and (ii) an administrative district scale model based on the organization of the former province of East Prussia.
The evaluation of the created models show that the occurrence of White Stork nesting grounds in the former East Prussia for most parts is defined by the variables ‘forest’, ‘settlement area’, ‘pasture land’ and ‘proximity to coastline’. From this set of variables it can be assumed that a good food supply and nesting opportunities are provided to the White Stork in pasture and meadows as well as in the proximity to human settlements. These could be seen as crucial factors for the choice of nesting White Stork in East Prussia. Dense forest areas appear to be unsuited as nesting grounds of White Storks. The high influence of the variable ‘coastline’ is most likely explained by the specific landscape composition of East Prussia parallel to the coastline and is to be seen as a proximal factor for explaining the distribution of breeding White Storks.
In a second step, predictions for the period of 1981 to 1993 could be made applying both scales of the models created in this study. In doing so, a decline of potential nesting habitat was predicted on the point scale. In contrast, the predicted White Stork occurrence increases when applying the model of the administrative district scale. The difference between both predictions is to be seen in the application of different scales (density versus suitability as breeding ground) and partly dissimilar explanatory variables. More studies are needed to investigate this phenomenon.
The model predictions for the period 1981 to 1993 could be compared to the available inventories of that period. It shows that the figures predicted here were higher than the figures established by the census. This means that the models created here show rather a capacity of the habitat (potential niche). Other factors affecting the population size e.g. breeding success or mortality have to be investigated further.
A feasible approach on how to generate possible habitat models was shown employing the methods presented here and applying historical data as well as assessing the effects of changes in land use on the White Stork. The models present the first of their kind, and could be improved by means of further data regarding the structure of the habitat and more exact spatially explicit information on the location of the nesting sites of the White Stork. In a further step, a habitat model of the present times should be created. This would allow for a more precise comparison regarding the findings from the changes of land use and relevant conditions of the environment on the White Stork in the region of former East Prussia, e.g. in the light of coming landscape changes brought by the European Union (EU).
8
Cross, Cheryl L. "Predictive Habitat Models for Four Cetaceans in the Mid-Atlantic Bight." NSUWorks, 2010. http://nsuworks.nova.edu/occ_stuetd/221.
Full textAbstract:
This study focuses on the habitats of cetaceans in the Mid-Atlantic Bight, a region characterized by bathymetric diversity and the presence of distinct water masses (i.e. the shelf water, slope water, and Gulf Stream). The combination of these features contributes to the hydrographic complexity of the area, which furthermore influences biological productivity and potential prey available for cetaceans. The collection of cetacean sighting data together with physical oceanographic data can be used to examine cetacean habitat associations. Cetacean habitat modeling is a mechanism for predicting cetacean distribution patterns based on environmental variables such as bathymetric and physical properties, and for exploring the potential ecological implications that contribute to cetacean spatial distributions. We can advance conservation efforts of cetacean populations by expanding our knowledge of their habitats and distribution.
Generalized additive models (GAMs) were developed to predict the spatial distribution patterns of sperm whales (Physeter macrocephalus), pilot whales (Globicephala spp.), bottlenose dolphins (Tursiops truncatus), and Atlantic spotted dolphins (Stenella frontalis) based on significant physical parameters along the continental shelf-break region in the Mid-Atlantic Bight. Data implemented in the GAMs were collected in the summer of 2006 aboard the NOAA R/V Gordon Gunter. These included visual cetacean survey data collected along with physical data at depth via expendable bathythermograph (XBT), and conductivity-temperature-depth (CTD) instrumentation. Additionally, continual surface data were collected via the ship’s flow through sensor system. Interpolations of physical data were created from collected point data using the inverse distant weighted method (IDW) to estimate the spatial distribution of physical data within the area of interest. Interpolated physical data, as well as bathymetric (bottom depth and slope) data were extracted to overlaid cetacean sightings, so that each sighting had an associated value for nine potentially significant physical habitat parameters.
A grid containing 5x5 km grid cells was created over the study area and cetacean sightings along with the values for each associated habitat parameter were summarized in each grid cell. Redundant parameters were reduced, resulting in a full model containing temperature at 50 m depth, mixed layer depth, bottom depth, slope, surface temperature, and surface salinity. GAMs were fit for each species based on these six potentially significant parameters. The resultant fit models for each species predicted the number of individuals per km2 based on a unique combination of environmental parameters. Spatial prediction grids were created based on the significant habitat parameters for each species to illustrate the GAM outputs and to indicate predicted regions of high density. Predictions were consistent with observed sightings. Sperm whale distribution was predicted by a combination of depth, sea surface temperature, and sea surface salinity. The model for pilot whales included bottom slope, and temperature at 50 m depth. It also indicated that mixed layer depth, bottom depth and surface salinity contributed to group size. Similarly, temperature at 50 m depth was significant for Atlantic spotted dolphins. Predicted bottlenose dolphin distribution was determined by a combination of bottom slope, surface salinity, and temperature at 50 m depth, with mixed layer depth contributing to group size.
Distribution is most likely a sign of prey availability and ecological implications can be drawn from the habitat parameters associated with each species. For example, regions of high slope can indicate zones of upwelling, enhanced vertical mixing and prey availability throughout the water column. Furthermore, surface temperature and salinity can be indicative of patchy zones of productivity where potential prey aggregations occur.
The benefits of these models is that collected point data can be used to expand our knowledge of potential cetacean “hotspots” based on associations with physical parameters. Data collection for abundance estimates, higher resolution studies, and future habitat surveys can be adjusted based on these model predictions. Furthermore, predictive habitat models can be used to establish Marine Protected Areas with boundaries that adapt to dynamic oceanographic features reflecting potential cetacean mobility. This can be valuable for the advancement of cetacean conservation efforts and to limit potential vessel and fisheries interactions with cetaceans, which may pose a threat to the sustainability of cetacean populations.
9
Wright, Amanda. "Predicting the distribution of Eurasian badger (Meles meles) setts." Thesis, Manchester Metropolitan University, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.364059.
Full text
10
Krause, Colin William. "Evaluation and Use of Stream Temperature Prediction Models for Instream Flow and Fish Habitat Management." Thesis, Virginia Tech, 2002. http://hdl.handle.net/10919/31229.
Full textAbstract:
The SNTEMP (U.S. Fish and Wildlife Service), QUAL2E (U.S. Environmental Protection Agency), and RQUAL (Tennessee Valley Authority) stream temperature prediction models were evaluated. All models had high predictive ability with the majority of predictions, >80% for Back Creek (Roanoke County, VA) and >90% for the Smith River tailwater (SRT) (Patrick County, VA), within 3°C of the measured water temperature. Sensitivity of model input parameters was found to differ between model, stream system, and season. The most sensitive of assessed parameters, dependent on model and stream, were lateral inflow, starting-water, air, and wet-bulb temperature. All three models predicted well, therefore, selecting a model to assess alternative water management scenarios was based on model capabilities. The RQUAL model, used to predict SRT temperatures under alternative hydropower release regimes, illustrated potential thermal habitat improvement for brown trout (Salmo trutta) compared to existing conditions. A 7-day/week morning 1 hr release was determined to best concurrently increase occurrence of brown trout optimal growth temperatures (+10.2% mean), decrease 21°C (state standard) exceedances (99% prevention), and decrease hourly changes in temperature (-1.6°C mean) compared to existing thermal conditions. The SNTEMP model was used to assess thermal habitat under flow, shade, and channel width changes occurring from future urbanization within the Back Creek watershed. Predictions reveal that additional urban development could limit thermal habitat for present fish species by elevating summer mean daily temperature up to 1°C and cause 31°C (state standard) exceedances compared to existing conditions. Temperature impacts were lessened by single rather than cumulative changes suggesting mitigation measures may maintain suitable thermal habitat.<br>Master of Science
Books on the topic "Habitat predictive model"
1
Canada. Natural Resources Canada. Canadian Forest Service. Great Lakes Forestry Centre. Predicting canopy closure for habitat modeling. Ottawa: Natural Resources Canada., 1995.
Find full text
2
Drew, C. Ashton. Predictive species and habitat modeling in landscape ecology: Concepts and applications. New York: Springer, 2011.
Find full text
3
Contor, Craig R. Assessment of COWFISH for predicting trout populations in grazed watersheds of the Intermountain West. Ogden, Utah: U.S. Dept. of Agriculture, Forest Service, Intermountain Research Station, 1991.
Find full text
4
Zorn, Troy G. Utility of species-specific, multiple linear regression models for prediction of fish assemblages in rivers of Michigan's lower peninsula. Lansing, MI: Michigan Dept. of Natural Resources, Fisheries Division, 2004.
Find full text
5
Evaluation of the Predictive Ecological Model for the Edwards Aquifer Habitat Conservation Plan. Washington, D.C.: National Academies Press, 2016. http://dx.doi.org/10.17226/23557.
Full text
6
Ltd, Dendron Resource Surveys, Great Lakes Forestry Centre, Canada-Ontario Subsidiary Agreement on Northern Ontario Development., and Northern Forestry Program (Canada), eds. Predicting canopy closure for habitat modeling. Sault Ste. Marie, Ont: Great Lakes Forestry Centre, 1995.
Find full text
7
Inc, Dendron Resource Surveys, and Great Lakes Forest Research Centre., eds. Predicting canopy closure for habitat modeling. Sault Ste. Marie, Ont: Great Lakes Forestry Centre, 1995.
Find full text
8
Railsback, Steven F., and Bret C. Harvey. Modeling Populations of Adaptive Individuals. Princeton University Press, 2020. http://dx.doi.org/10.23943/princeton/9780691195285.001.0001.
Full textAbstract:
Ecologists now recognize that the dynamics of populations, communities, and ecosystems are strongly affected by adaptive individual behaviors. Yet until now, we have lacked effective and flexible methods for modeling such dynamics. Traditional ecological models become impractical with the inclusion of behavior, and the optimization approaches of behavioral ecology cannot be used when future conditions are unpredictable due to feedbacks from the behavior of other individuals. This book provides a comprehensive introduction to state- and prediction-based theory, or SPT, a powerful new approach to modeling trade-off behaviors in contexts such as individual-based population models where feedbacks and variability make optimization impossible. This book features a wealth of examples that range from highly simplified behavior models to complex population models in which individuals make adaptive trade-off decisions about habitat and activity selection in highly heterogeneous environments. The book explains how SPT builds on key concepts from the state-based dynamic modeling theory of behavioral ecology, and how it combines explicit predictions of future conditions with approximations of a fitness measure to represent how individuals make good—not optimal—decisions that they revise as conditions change. The resulting models are realistic, testable, adaptable, and invaluable for answering fundamental questions in ecology and forecasting ecological outcomes of real-world scenarios.
9
Jappelli, Tullio, and Luigi Pistaferri. The Response of Consumption to Anticipated Changes in Income. Oxford University Press, 2017. http://dx.doi.org/10.1093/acprof:oso/9780199383146.003.0008.
Full textAbstract:
The intertemporal models studied so far postulate that people use savings in order to smooth income fluctuations, and that unless there are liquidity constraints, consumption responds little if at all to changes in income that were expected. When this major theoretical prediction is violated, researchers conclude that consumption is excessively sensitive to anticipated income changes. In this chapter we review some of the empirical approaches researchers have taken to estimate the response of consumption to anticipated income changes. We point out that empirically it is very hard to identify situations in which income changes in a predictable way. But even if the empirical difficulties can be surmounted, there are many plausible explanations for the rejection of the implications of the theoretical models, including liquidity constraints, non-separability between consumption and leisure, home production, the persistence of habits, aggregation bias, and the durability of goods.
10
1945-, Silander John August, Civco Daniel L, and United States. National Aeronautics and Space Administration., eds. Landscape dynamics of northeastern forests: First year annual report. [Washington, DC: National Aeronautics and Space Administration, 1994.
Find full textBook chapters on the topic "Habitat predictive model"
1
Huettmann, Falk, and Thomas Gottschalk. "Simplicity, Model Fit, Complexity and Uncertainty in Spatial Prediction Models Applied Over Time: We Are Quite Sure, Aren’t We?" In Predictive Species and Habitat Modeling in Landscape Ecology, 189–208. New York, NY: Springer New York, 2010. http://dx.doi.org/10.1007/978-1-4419-7390-0_10.
Full text
2
Drew, C. Ashton, and Ajith H. Perera. "Expert Knowledge as a Basis for Landscape Ecological Predictive Models." In Predictive Species and Habitat Modeling in Landscape Ecology, 229–48. New York, NY: Springer New York, 2010. http://dx.doi.org/10.1007/978-1-4419-7390-0_12.
Full text
3
Lawler, Josh J., Yolanda F. Wiersma, and Falk Huettmann. "Using Species Distribution Models for Conservation Planning and Ecological Forecasting." In Predictive Species and Habitat Modeling in Landscape Ecology, 271–90. New York, NY: Springer New York, 2010. http://dx.doi.org/10.1007/978-1-4419-7390-0_14.
Full text
4
Wiersma, Yolanda F. "Variation, Use, and Misuse of Statistical Models: A Review of the Effects on the Interpretation of Research Results." In Predictive Species and Habitat Modeling in Landscape Ecology, 209–27. New York, NY: Springer New York, 2010. http://dx.doi.org/10.1007/978-1-4419-7390-0_11.
Full text
5
Veech, Joseph A. "Post-analysis Procedures." In Habitat Ecology and Analysis, 175–92. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780198829287.003.0010.
Full textAbstract:
There are several additional statistical procedures that can be conducted after a habitat analysis. The statistical model produced by a habitat analysis can be assessed for fit to the data. Model fit describes how well the predictor variables explain the variance in the response variable, typically species presence–absence or abundance. When more than one statistical model has been produced by the habitat analysis, these can be compared by a formal procedure called model comparison. This usually involves identifying the model with the lowest Akaike information criterion (AIC) value. If the statistical model is considered a predictive tool then its predictive accuracy needs to be assessed. There are many metrics for assessing the predictive performance of a model and quantifying rates of correct and incorrect classification; the latter are error rates. Many of these metrics are based on the numbers of true positive, true negative, false positive, and false negative observations in an independent dataset. “True” and “false” refer to whether species presence–absence was correctly predicted or not. Predictive performance can also be assessed by constructing a receiver operating characteristic (ROC) curve and calculating area under the curve (AUC) values. High AUC values approaching 1 indicate good predictive performance, whereas a value near 0.5 indicates a poor model that predicts species presence–absence no better than a random guess.
6
"Fish Habitat: Essential Fish Habitat and Rehabilitation." In Fish Habitat: Essential Fish Habitat and Rehabilitation, edited by Peter J. Auster. American Fisheries Society, 1999. http://dx.doi.org/10.47886/9781888569124.ch13.
Full textAbstract:
<em>Abstract.—</em> The 1996 Magnuson–Stevens Fishery Conservation and Management Act mandates that regional fishery management councils must designate essential fish habitat (EFH) for each managed species, assess the effects of fishing on EFH, and develop conservation measures for EFH where needed. This synthesis of fishing effects on habitat was produced to aid the fishery management councils in assessing the impacts of fishing activities. A wide range of studies was reviewed that reported effects of fishing on habitat (i.e., structural habitat components, community structure, and ecosystem processes) for a diversity of habitats and fishing gear types. Commonalities of all studies included immediate effects on species composition and diversity and a reduction in habitat complexity. Studies of acute effects were found to be a good predictor of chronic effects. Recovery after fishing was more variable depending on habitat type, life history strategy of component species, and the natural disturbance regime. The ultimate goal of gear impact studies should not be to retrospectively analyze environmental impacts but ultimately to develop the ability to predict outcomes of particular management regimes. Synthesizing the results of these studies into predictive numerical models is not currently possible. However, conceptual models can coalesce the patterns found over the range of observations and can be used to predict effects of gear impacts within the framework of current ecological theory. Initially, it is useful to consider fishes’ use of habitats along a gradient of habitat complexity and environmental variability. Such considerations can be facilitated by a model of gear impacts on a range of seafloor types based on changes in structural habitat values. Disturbance theory provides the framework for predicting effects of habitat change based on spatial patterns of disturbance. Alternative community state models and type 1–type 2 disturbance patterns may be used to predict the general outcome of habitat management. Primary data are lacking on the spatial extent of fishing-induced disturbance, the effects of specific gear types along a gradient of fishing effort, and the linkages between habitat characteristics and the population dynamics of fishes. Adaptive and precautionary management practices will therefore be required until empirical data become available for validating model predictions.
7
"Fish Habitat: Essential Fish Habitat and Rehabilitation." In Fish Habitat: Essential Fish Habitat and Rehabilitation, edited by Peter J. Auster. American Fisheries Society, 1999. http://dx.doi.org/10.47886/9781888569124.ch13.
Full textAbstract:
<em>Abstract.—</em> The 1996 Magnuson–Stevens Fishery Conservation and Management Act mandates that regional fishery management councils must designate essential fish habitat (EFH) for each managed species, assess the effects of fishing on EFH, and develop conservation measures for EFH where needed. This synthesis of fishing effects on habitat was produced to aid the fishery management councils in assessing the impacts of fishing activities. A wide range of studies was reviewed that reported effects of fishing on habitat (i.e., structural habitat components, community structure, and ecosystem processes) for a diversity of habitats and fishing gear types. Commonalities of all studies included immediate effects on species composition and diversity and a reduction in habitat complexity. Studies of acute effects were found to be a good predictor of chronic effects. Recovery after fishing was more variable depending on habitat type, life history strategy of component species, and the natural disturbance regime. The ultimate goal of gear impact studies should not be to retrospectively analyze environmental impacts but ultimately to develop the ability to predict outcomes of particular management regimes. Synthesizing the results of these studies into predictive numerical models is not currently possible. However, conceptual models can coalesce the patterns found over the range of observations and can be used to predict effects of gear impacts within the framework of current ecological theory. Initially, it is useful to consider fishes’ use of habitats along a gradient of habitat complexity and environmental variability. Such considerations can be facilitated by a model of gear impacts on a range of seafloor types based on changes in structural habitat values. Disturbance theory provides the framework for predicting effects of habitat change based on spatial patterns of disturbance. Alternative community state models and type 1–type 2 disturbance patterns may be used to predict the general outcome of habitat management. Primary data are lacking on the spatial extent of fishing-induced disturbance, the effects of specific gear types along a gradient of fishing effort, and the linkages between habitat characteristics and the population dynamics of fishes. Adaptive and precautionary management practices will therefore be required until empirical data become available for validating model predictions.
8
"Landscape Influences on Stream Habitats and Biological Assemblages." In Landscape Influences on Stream Habitats and Biological Assemblages, edited by James E. McKenna, Richard P. McDonald, Chris Castiglione, Sandy S. Morrison, Kurt P. Kowalski, and Dora R. Passino-Reader. American Fisheries Society, 2006. http://dx.doi.org/10.47886/9781888569766.ch26.
Full textAbstract:
<em>Abstract.</em>—We describe a methodology for developing species–habitat models using available fish and stream habitat data from New York State, focusing on the Genesee basin. Electrofishing data from the New York Department of Environmental Conservation were standardized and used for model development and testing. Four types of predictive models (multiple linear regression, stepwise multiple linear regression, linear discriminant analysis, and neural network) were developed and compared for 11 fish species. Predictive models used as many as 25 habitat variables and explained 35–91% of observed species abundance variability. Omission rates were generally low, but commission rates varied widely. Neural network models performed best for all species, except for rainbow trout <em>Oncorhynchus mykiss</em>, gizzard shad <em>Dorosoma cepedianum</em>, and brown trout <em>Salmo trutta</em>. Linear discriminant functions generally performed poorly. The species–environment models we constructed performed well and have potential applications to management issues.
9
"Landscape Influences on Stream Habitats and Biological Assemblages." In Landscape Influences on Stream Habitats and Biological Assemblages, edited by Les W. Stanfield, Scott F. Gibson, and Jason A. Borwick. American Fisheries Society, 2006. http://dx.doi.org/10.47886/9781888569766.ch29.
Full textAbstract:
<em>Abstract.</em>—Effective management of salmonid populations in the Great Lakes basin requires understanding how their distribution and density vary spatially. We used a hierarchical approach to evaluate the predictive capabilities of landscape conditions, local habitat features, and potential effects from coinhabiting salmonids on the distribution and densities of rainbow trout <em>Oncorhynchus mykiss</em>, brook trout <em>Salvelinus fontinalis, </em>brown trout <em>Salmo trutta</em>, and coho salmon <em>O. kisutch </em>within the majority of the Canadian tributaries of Lake Ontario. We collected fish assemblage, instream habitat, and water temperature data from 416 wadeable stream sites. Landscape characteristics were obtained for each site’s catchment and summarized into six key attributes (drainage area, base flow index, percent impervious cover (PIC), reach slope, elevation, and location with respect to permanent fish barriers). Classification trees indicated that PIC in a catchment was a critical predictor of salmonid distribution, in that beyond a threshold of 6.6–9 PIC, all salmonids were predicted to be absent. Base flow index and barriers were also important predictors of the distribution of salmonids. Models generally provided higher classification success at predicting absence (86–98%) than predicting presence (63–87%). Landscape features were the best predictors of densities of rainbow and brook trout (adjusted <em>r</em><sup>2</sup> = 0.49 and 0.30 respectively), although the local habitat features were almost as effective for predicting brook trout (<em>r</em><sup>2</sup> = 0.23). Local habitat features (proportion of riffles and pools, substrate, cover, and stream temperature), and presence of other salmonids produced the best predictive model for brown trout. Coho salmon was only locally distributed in the basin, and the derived model was driven by spatial characteristics rather than ecological processes. Our models estimate 653,000 juvenile rainbow trout and 231,000 brook trout (all age-classes) in our study streams. Finally, we estimate that current brook trout distribution in our study area is only 21% of its historic range.
10
"Landscape Influences on Stream Habitats and Biological Assemblages." In Landscape Influences on Stream Habitats and Biological Assemblages, edited by Keith B. Gido, Jeffrey A. Falke, Robert M. Oakes, and Kristen J. Hase. American Fisheries Society, 2006. http://dx.doi.org/10.47886/9781888569766.ch12.
Full textAbstract:
<em>Abstract.</em>—Habitat data collected at three spatial scales (catchments, reaches, and sites) were used to predict individual fish species occurrences and assemblage structure at 150 sites in the Kansas River basin. Habitat measurements for the catchments and reaches of each sample site were derived from available geographic information system (GIS) data layers. Habitat measurements at the sample sites were collected at the time of fish sampling. Because habitat measurements are typically more difficult to collect as the spatial scale of sampling decreases (i.e., field measurement versus a GIS analysis), our objective was to quantify the relative increase in predictive ability as we added habitat measurements from increasingly finer spatial scales. Although the addition of site-scale habitat variables increased the predictive performance of models, the relative magnitude of these increases was small. This was largely due to the general association of species occurrences with measurements of catchment area and soil factors, both of which could be quantified with a GIS. Habitat measurements taken at different spatial scales were often correlated; however, a partial canonical correspondence analysis showed that catchment- scale habitat measurements accounted for a slightly higher percent of the variation in fish-assemblage structure across the 150 sample sites than reach- or site-scale habitat measurements. We concluded that field habitat measurements were less informative for predicting species occurrences within the Kansas River basin than catchment data. However, because of the hierarchical nature of the geomorphological processes that form stream habitats, a refined understanding of the relationship between catchment-, reach- and site-scale habitats provides a mechanistic understanding of fish–habitat relations across spatial scales.
Conference papers on the topic "Habitat predictive model"
1
Chen, Di, Yexiang Xue, Daniel Fink, Shuo Chen, and Carla P. Gomes. "Deep Multi-species Embedding." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/509.
Full textAbstract:
Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature space via a deep neural network. Applied to bird observational data from the citizen science project eBird, we demonstrate how the DMSE model discovers inter-species relationships to outperform single-species distribution models (random forests and SVMs) as well as competing multi-label models. Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. An important domain contribution of the DMSE model is the ability to discover and describe species interactions while simultaneously learning the shared habitat preferences among species. As an additional contribution, we provide a graphical embedding of hundreds of bird species in the Northeast US.
2
Ahsan, Nasir, Stefan B. Williams, Michael Jakuba, Oscar Pizarro, and Ben Radford. "Predictive habitat models from AUV-based multibeam and optical imagery." In 2010 OCEANS MTS/IEEE SEATTLE. IEEE, 2010. http://dx.doi.org/10.1109/oceans.2010.5663809.
Full text
3
KUMADA, Takayuki, Takaaki UDA, and Masumi SERIZAWA. "MODEL FOR PREDICTING THE EXTENSION OF HABITAT OF JAPANESE HARD CLAM MERETRIX LAMARCKII." In Proceedings of the 31st International Conference. World Scientific Publishing Company, 2009. http://dx.doi.org/10.1142/9789814277426_0378.
Full text
4
Garg, Priya, and Deepti Aggarwal. "Application of Swarm-Based Feature Selection and Extreme Learning Machines in Lung Cancer Risk Prediction." In Intelligent Computing and Technologies Conference. AIJR Publisher, 2021. http://dx.doi.org/10.21467/proceedings.115.1.
Full textAbstract:
Lung cancer risk prediction models help in identifying high-risk individuals for early CT screening tests. These predictive models can play a pivotal role in healthcare by decreasing lung cancer's mortality rate and saving many lives. Although many predictive models have been developed that use various features, no specific guidelines have been provided regarding the crucial features in lung cancer risk prediction. This study proposes novel risk prediction models using bio-inspired swarm-based techniques for feature selection and extreme learning machines for classification. The proposed models are applied on a public dataset consisting of 1000 patient records and 23 variables, including sociodemographic factors, smoking status, and lung cancer clinical symptoms. The models, validated using 10-fold cross-validation, achieve an AUC score in the range of 0.985 to 0.989, accuracy in the range of 0.986 to 0.99 and F-Measure in range of 0.98 to 0.985. The study also identifies smoking habits, exposure to air pollution, occupational hazards and some clinical symptoms as the most commonly selected lung cancer risk prediction features. The study concludes that the developed lung cancer risk prediction models can be successfully applied for early screening, diagnosis and treatment of high-risk individuals.
5
Uenaka, Takashi, Naohisa Sakamoto, and Koji Koyamada. "Visual Analysis of Habitat Suitability Index Model for Predicting the Locations of Fishing Grounds." In 2014 IEEE Pacific Visualization Symposium (PacificVis). IEEE, 2014. http://dx.doi.org/10.1109/pacificvis.2014.33.
Full text
6
Piacenza, Joseph, Salvador Mayoral, Bahaa Albarhami, and Sean Lin. "Understanding the Importance of Post Occupancy Usage Trends During Concept-Stage Sustainable Building Design." In ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2017. http://dx.doi.org/10.1115/detc2017-67461.
Full textAbstract:
As sustainable building mandates become more prevalent in new commercial and mixed use buildings, it is a challenge to create a broad, one-size-fits-all certification process. While designers can estimate energy usage with computational tools such as model based design, anticipating the post occupancy usage is more challenging. Understanding and predicting energy usage trends is especially complicated in unique mixed use building applications, such as university student housing buildings, where occupancy varies significantly as a function of enrollment, course scheduling, and student study habits. This research explores a computational modeling approach used to achieve LEED (Leadership in Energy and Environmental Design) Platinum certification for a student housing complex design. A case study is presented from the California State University, Fullerton (CSUF) campus, and examines the impact of post occupancy building usage trends, and diversity factor, defined as a building’s instantaneous energy usage normalized by the maximum allowable usage, on energy use estimates. The CSUF case model, which was originally created using EnergySoft’s EnergyPro 5 software, is examined. An annual predictive energy use comparison is performed in EnergyPro 5 using general building design mandates (i.e., ASHRAE 90.1, California Title 24), and CSUF case specific building usage details (e.g., student scheduling, diversity factor). In addition, the energy usage estimates of these two predictive models are compared to the actual usage data collected during the 2014 academic year. The results of this comparison show the benefits of considering post occupancy usage, and recommendations are presented for creating unique and application based computational models, early in the design process. This research has broad applications, and can extend to sustainable building design in other organizations, whose operational schedule falls outside of current prediction methods for sustainability mandates.
7
Long, Keyu, and Zaiyue Yang. "Model predictive control for household energy management based on individual habit." In 2013 25th Chinese Control and Decision Conference (CCDC). IEEE, 2013. http://dx.doi.org/10.1109/ccdc.2013.6561587.
Full text
8
Wang, Tianyi, Xiaohan Mei, J. Alex Thomasson, Xiongzhe Han, and Pappu Kumar Yadav. "<i>Volunteer Cotton Habitat Prediction Model and Detection with UAV Remote Sensing</i>." In 2020 ASABE Annual International Virtual Meeting, July 13-15, 2020. St. Joseph, MI: American Society of Agricultural and Biological Engineers, 2020. http://dx.doi.org/10.13031/aim.202000219.
Full text
9
Lazar, Alina, Alexandra Ballow, Ling Jin, C. Anna Spurlock, Alexander Sim, and Kesheng Wu. "Machine Learning for Prediction of Mid to Long Term Habitual Transportation Mode Use." In 2019 IEEE International Conference on Big Data (Big Data). IEEE, 2019. http://dx.doi.org/10.1109/bigdata47090.2019.9006411.
Full text
10
Jeon, Soonil, Jang-Moo Lee, and Yeong-Il Park. "Advanced Multi-Mode Control Strategy for a Parallel Hybrid Electric Vehicle Based on Driving Pattern Recognition." In ASME 2003 International Mechanical Engineering Congress and Exposition. ASMEDC, 2003. http://dx.doi.org/10.1115/imece2003-41857.
Full textAbstract:
The adaptive multi-mode control strategy (AMMCS) is defined as the control strategy that switches control parameters for the purpose of adjusting vehicles to diverse traffic conditions and driver’s habits. This strategy is composed of off-line and on-line procedures. In the off-line procedure, several sets of control parameters are optimized under representative driving patterns (RDP). In the on-line procedure, the control parameter switching or interpolation is periodically activated based on the driving pattern recognition (DPR) algorithm, assuming that the driving pattern during the future control horizon doesn’t change significantly compared to the past pattern. The AMMCS is conceptually similar to one of predictive control theories, namely the receding horizon control which is also known as model predictive control. The AMMCS is expected to be applied well to hybrid electric vehicle (HEV) system which is very sensitive to driving patterns. Furthermore, the AMMCS can be combined with the two conventional control strategies using global and local optimization techniques to improve performances further. The design goal of the AMMCS is to minimize fuel consumption and NOx for a pre-transmission single shaft parallel HEV.