Data-Driven Artificial Intelligence Model of Meteorological Elements Influence on Vegetation Coverage in North China

Based on remote sensing data of vegetation coverage, observation basic meteorological elements, and support vector machine (SVM) method, this study develops an analysis model elements influence coverage (MEVC). The variations for the changes are identified utilizing five (temperature, precipitation, relative humidity, sunshine hour, ground temperature) in SVM model. performance is also evaluated simulating anomaly change by comparing with statistical multiple linear regression (MLR) partial least squares (PLS)-based models. symbol agreement rates (SAR) simulations produced MLR, PLS, models 55%, 57%, 66%, respectively. shows obviously better than PLS MLR elements-related interannual variation North China. Therefore, introduction intelligent method term development has certain advantages studying internal impact regional coverage. It can be further applied to predict future change.