Machine Learning (ML) Methods in Assessing the Intensity of Damage Caused by High-Energy Mining Tremors in Traditional Development of LGOM Mining Area

The paper presents a comparative analysis of Machine Learning (ML) research methods allowing to assess the risk mining damage occurring in traditional masonry buildings located area Legnica-Głogów Copper District (LGOM) as result intense tremors. database reports on that occurred after tremors 20 February 2002, 16 May 2004 and 21 2006 formed basis for analysis.
 Based these data, classification models were created using Probabilistic Neural Network (PNN) Support Vector (SVM) method.
 results previous studies allowed include structural geometric features buildings,as well protective measures against model. probabilistic notation model makes it possible effectively probability large groups building structures paraseismic impacts. conducted analyses confirm thesis proposed methodology may allow estimate, with appropriate probability, financial outlays plant should secure repair expected development LGOM area.