Landslide susceptibility research method and system based on reinforcement learning-random forest

• Main Authors: LU YANBAO, XU WANQIANG, KONG QIUPING, WANG XU, FAN MEILING, NIE WEN, ZHENG TIANSHOU, ZHU TIANQIANG, CHEN XINQUAN, ZHENG WENMING
• Format: Patent
• Language: Chinese; English
• Published: 02.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a landslide susceptibility research method and system based on reinforcement learning-random forest, and belongs to the field of geological disaster prediction and evaluation. The method comprises the following steps: S1, carrying out drawing unit division on a research area to obtain a plurality of units; carrying out linear analysis on the landslide influence factors to obtain evaluation indexes; forming a data set by a plurality of units and evaluation indexes, and dividing the data set to obtain a training data set and a verification data set; s2, equivalently dividing the training data set according to a time sequence to obtain a first training data set, a second training data set and a third training data set; calculating a frequency ratio of the first training data set to obtain a first frequency ratio; s3, establishing an ILRF1 model based on the first frequency ratio; sequentially obtaining an ILRF2 model and an ILRF3 model based on the ILRF1 model, the second training data se