Power grid near-real-time rainfall estimation method, system and device and storage medium

• Main Authors: YANG WENMING, ZANG ZEZHOU, ZHU CHAO, CAO YONG, XU WEIGANG, CHEN HONGFEI, GAN QIANG, HAN XUECHUN, HE LUYA, WU XIJUAN
• Format: Patent
• Language: Chinese; English
• Published: 21.03.2023
• 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; MEASURING; METEOROLOGY; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING

The invention discloses a power grid near-real-time rainfall estimation method, system and device and a storage medium. The method comprises the steps that real-time spectral information of a stationary satellite is acquired and preprocessed to generate real-time feature data; inputting the real-time feature data into a pre-constructed rainfall estimation model to obtain an estimated value of near real-time rainfall; wherein the construction of the rainfall estimation model comprises the following steps: acquiring historical spectral information and historical meteorological data of a stationary satellite and each meteorological station at each moment in a preset time period; preprocessing the historical spectral information to generate historical feature data at each moment; performing space-time matching on the historical feature data and the historical meteorological data to obtain a data pair set; dividing the data pair set to generate a training set, a verification set and a test set; constructing a Ligh