Academic literature on the topic 'Electronic books. Earthquakes Earthquake prediction'

Fuzzy Expert System (FES) with application to earthquake prediction has been presented to reproduce the performance of a human expert in earthquake prediction using expert systems. This research aims to predict future earthquakes having a magnitude 5.5 or greater. Previous earthquake data from 2000 to 2019 have been collected for this purpose. Since the earthquake data for the specified region have been reported on different magnitude scales, suitable relationships were determined to obtain uniform data. The uniform data have been used to calculate seismicity indicators according to the guidelines provided by Gutenberg-Richter’s scale for quantitative determination of earthquake features. The relationships among these seismic indicators have been used by the human expert to set the rule base of Fuzzy expert system. These rules have been mathematically validated and tested on instrumentally recorded earthquake data. The results obtained from the proposed FES presented 47 % accuracy in predicting future earthquakes that may occur in the 100 km radial area from 34.708 ° N, 72.5478 ° E.

The influence of earthquake disasters on human social life is positively related to the magnitude and intensity of the earthquake, and effectively avoiding casualties and property losses can be attributed to the accurate prediction of earthquakes. In this study, an electromagnetic sensor is investigated to assess earthquakes in advance by collecting earthquake signals. At present, the mainstream earthquake magnitude prediction comprises two methods. On the one hand, most geophysicists or data analysis experts extract a series of basic features from earthquake precursor signals for seismic classification. On the other hand, the obtained data related to earth activities by seismograph or space satellite are directly used in classification networks. This article proposes a CNN and designs a 3D feature-map which can be used to solve the problem of earthquake magnitude classification by combining the advantages of shallow features and high-dimensional information. In addition, noise simulation technology and SMOTE oversampling technology are applied to overcome the problem of seismic data imbalance. The signals collected by electromagnetic sensors are used to evaluate the method proposed in this article. The results show that the method proposed in this paper can classify earthquake magnitudes well.

This article aims to discusses machine learning modelling using a dataset provided by the LANL (Los Alamos National Laboratory) earthquake prediction competition hosted by Kaggle. The data were obtained from a laboratory stick-slip friction experiment that mimics real earthquakes. Digitized acoustic signals were recorded against time to failure of a granular layer compressed between steel plates. In this work, machine learning was employed to develop models that could predict earthquakes. The aim is to highlight the importance and potential applicability of machine learning in seismology The XGBoost algorithm was used for modelling combined with 6-fold cross-validation and the mean absolute error (MAE) metric for model quality estimation. The backward feature elimination technique was used followed by the forward feature construction approach to find the best combination of features. The advantage of this feature engineering method is that it enables the best subset to be found from a relatively large set of features in a relatively short time. It was confirmed that the proper combination of statistical characteristics describing acoustic data can be used for effective prediction of time to failure. Additionally, statistical features based on the autocorrelation of acoustic data can also be used for further improvement of model quality. A total of 48 statistical features were considered. The best subset was determined as having 10 features. Its corresponding MAE was 1.913 s, which was stable to the third decimal point. The presented results can be used to develop artificial intelligence algorithms devoted to earthquake prediction.

Abstract A large amount of data about earthquake effects, supplied by citizens through a web-based questionnaire, enabled the analysis of the occurrence of many of the effects on humans and objects listed in macroseismic scales descriptions. Regarding the other diagnostic effects (rattling, moving, shifting, falling or overturning depending of the object type of doors, windows, china, glasses, small objects, pictures, vases, books, as well as frightened people and animal behaviour), data from more than 300,000 questionnaires about earthquakes felt in Italy from June 2007 to August 2017, were analysed by stacking them together as a function of hypocentral distance and magnitude. The comparison of the resulting percentages with the intensity prediction equation showed that almost all the chosen effects are good diagnostics for macroseismic intensity evaluation, as their percentages are well differentiated. We did not analyse the oscillations of hanging objects and liquids because the differences in effect attenuations, highlighted by the maps of the occurrence percentage, suggested to not consider them as diagnostic effect. This result allowed us to quantify the occurrence of each diagnostic effect for the intensity degrees from II to VI of the European macroseismic scale for the people who felt the earthquake. The application of the intensity assessment method to internet macroseismic data, based on the specifications herein proposed, should mitigate the problem of “not felt” undersampling in crowdsourced web data.

A complex system for zonal earthquake prediction, warning, and local assessment of seismic events has been designed, performed, implemented, and experimented/validated. The system was designed to ensure simultaneously: the reception of warning signals following earthquakes with the epicentre on a radius of 1000 km; acquisition of local precursor data for a possible prediction of seismic events with the epicentre in the perimeter of the targeted locality and/or improvement of the database in the field of Earth physics purchased and processed centrally at the national seismic dispatcher; acquisition of data on the intensity of local seismic movements, based on which, when a predetermined threshold considered dangerous is exceeded, a real-time action order is issued for the protection of high-risk equipment and installations in operation. The realized system is structured on the national seismic dispatcher DSN (with the role of seismic data acquisition from the territory) connected by a bidirectional communication system with a local dispatcher DL which is provided with a system for acquiring and storing local seismic data (vibration detector 3D and temperature transducer mounted in a 40 m deep drilled well, radon detector and associated parameters: temperature, pressure, and humidity of the air mounted at the mouth of the drilled well). The implemented system is able, through the specialized software implemented, to take over the warning signals received from the national seismic dispatcher, to process the locally acquired data, and after the local validation of the seismic event to issue real-time action command (when exceeding values of pre-established major risk threshold) of the protections of high-risk installations in operation in the targeted perimeter. The experimentation/validation of the system, of the interconnection networks, and of the specialized software of the implemented application was done both by continuously recording the local seismic parameters, verifying the communication between DSN and DL, and by taking two warnings regarding seismic events produced (on 30.10.2020  Mw = 7, Greece and on 22.10.2020, at 20:22 hours, ML = 4 R, Vrancea, RO). By processing the data recorded during these events, the speeds of seismic waves in the respective directions were calculated. Thus, for the event of 30.10.2020 Greece, a speed of seismic waves of 7,418 km/second was determined and for the event from 22.10.2020 Vrancea, at 20:22 hours, it was calculated that the secondary waves are moving with 12,686 km/second and the surface seismic waves with 5,063 km/second. Following the analysis/comparison of acceleration intensities with the pre-set threshold level recorded locally for potentially dangerous events, it was found that these events were felt in Râmnicu Vâlcea at a level below the pre-set danger threshold and consequently, the specialized software of the application did not generate a control signal for actuating the protection of high-risk equipment in operation.

In this paper the simplest and most widely used model of a rigid block undergoing harmonic forcing is analysed in detail. The block is shown to possess extremely complicated dynamics, with many different types of response being revealed. Symmetric single-impact subharmonic orbits of all orders are found and regions of parameter space in which they occur are given. In particular, period-doubling cascades of asymmetric orbits are found, which ultimately produce an apparently non-periodic or chaotic response. Sensitivity to initial conditions is illustrated, which leads to uncertainty in the prediction of the asymptotic dynamics. Nevertheless, the transient response may be the most important in connection with real earthquakes. To this end, the concept of the domain of maximum transients is introduced. In this light the response is shown to be quite ordered and predictable, despite the chaotic nature of the asymptotic domain of attraction. It is shown that safety issues cannot be satisfactorily resolved until an agreed set of initial conditions is established. It appears that blocks may survive under very high accelerations and topple at very low accelerations provided the initial conditions are correct. Consideration is also given to the use of actual earthquake recordings in attempting to reproduce responses in given structures. If the present conclusions carry over to general excitations, then small errors in recordings may produce large differences in response. The present methods include orbital stability techniques together with detailed numerical computations. These results are backed up by encouraging qualitative agreement from an electronic analogue circuit.

Thesis (Ph. D.)--University of Nevada, Reno, 2005.
"August 2005." Includes bibliographical references. Online version available on the World Wide Web. Library also has microfilm. Ann Arbor, Mich. : ProQuest Information and Learning Company, [2005]. 1 microfilm reel ; 35 mm.