| Popis: |
Introduction. During the operation of urban and rural geotechnical systems, the mechanical indicators of the stability of the soil base are significantly influenced by the regime and dynamics of the physicochemical properties of nearby water bodies, caused by the development of karst-suffusion processes. The results of information analysis of data on the dynamics of the river runoff level and water salinity make it possible to increase the accuracy of predictive estimates of the loss of stability of the geotechnical system due to the development of karst-suffusion processes. Goals and objectives. The aim of the work is to improve the safety of operation of geotechnical systems and increase the efficiency of modeling and forecasting systems for geodynamics by developing an algorithm for assessing changes in the risk of developing suffusion processes based on an analysis of the dynamics of the level of groundwater and surface waters. Methods. The paper analyzes the data on the number of karst sinkholes depending on the dynamics of the river water level, obtained on the basis of statistical sources and reports on regime observations, as well as a result of field research. In the course of data processing, a spline interpolation method was used, an algorithm and a neural network for predicting a failure using the Bayesian regularization method based on a network training function was developed, which updates the weight and bias of the value in accordance with the Levenberg-Marquardt optimization. Results and its discussion. Based on the results of practical use, the effectiveness of the developed algorithm was confirmed in identifying the dynamics of the formation of dips during information processing of data on changes in the water level in the Oka River and data on the appearance of new dips in the period from 2012 to 2019. Conclusion. The results obtained in the work make it possible to judge the presence of the expediency of using the developed algorithm for assessing the occurrence of karst sinkholes when monitoring the stability of geotechnical systems and assessing the safety of their operation in general. Prospects for further work are associated with expanding the set of training data and adapting the structure of the neural network to the individual characteristics of the territories by introducing additional geological, hydrological and climatic parameters into the processing. Key words: geotechnical system, stability, karst sinkhole, bifurcation parameters, information processing of data. |
