Landslide prediction method, device and equipment and storage medium

• Main Authors: TENG JIAYING, JIANG ZIJUN, SONG JIE, HU HUI, ZHENG ZENGRONG
• Format: Patent
• Language: Chinese; English
• Published: 08.01.2021
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The embodiment of the invention discloses a landslide prediction method and device, equipment and a storage medium. The method comprises steps of selecting a self-stepping classification learning model, determining a self-stepping factor of the self-stepping classification learning model according to the number of boxes and the number of iterations of historical non-landslide data, determining a downsampling proportion according to the self-stepping factor of each box and the self-stepping factors of all boxes, and obtaining a downsampling result. When the self-stepping factor and the down-sampling proportion are iteratively adjusted based on the historical landslide data and the historical non-landslide data, the down-sampling quantity in each sub-box is gradually and uniformly changed along with the increase of the number of iterations, and while the down-sampling proportion of each sub-box is uniformly changed, the down-sampling quantity in each sub-box is gradually and uniformly changed; it can also be gu