The prediction based on dynamic downscaling prediction technology of the climate extension of weather research and forecasting (CWRF) model to summer precipitation has a certain deviation, so it is difficult to achieve accurate prediction. This paper analyzed the correlated meteorological elements with summer precipitation based on the climatic characteristics of summer precipitation in the main land of China. And on this basis, the reforecasts of summer precipitation by CWRF model in China during 1996-2019 were corrected by using the combined method of dendritic network (DD) and artificial neural network (ANN). Finally, the correction effect was tested by mean square error (MSE), anomaly correlation coefficient (ACC) and temporal correlation coefficient (TCC), etc. The results show that the correction effect to summer precipitation based on the artificial dendritic neural network (ADNN) algorithm model was better than the historical reforecasts of CWRF model in China. The ACC and TCC both increased by about 0.10, MSE dropped by about 26%, and the overall trend anomaly test scores improved by 6.55, which indicated that the ADNN machine learning method could achieve correction to summer precipitation forecasts of CWRF model to a certain extent, thus it could improve the accuracy of precipitation forecasts of CWRF model.

Based on MODIS-NDVI (normalized difference vegetation index) datasets, the vegetation coverage was calculated in Liaoning Province from 2001 to 2019. Combined with land cover products of MODIS and air temperature and precipitation data at 61 meteorological observation stations in Liaoning Province, the spatio-temporal variation characteristics of vegetation coverage of five main types of vegetation were analyzed emphatically, and their responses to temperature and precipitation changes were discussed. The results are as follows: (1) The multi-year mean vegetation coverage was 0.48, and it was high in the east and low in the west of Liaoning Province from 2001 to 2019. The annual vegetation coverage increased in most areas of Liaoning Province in the past 19 years, and it presented an obvious increasing trend with the rate of 0.036 per 10-year as a whole. In additional, the vegetation coverage of five main vegetation types including crop, grassland, deciduous broadleaf forest, woody savanna and savanna increased significantly in Liaoning Province in the past 19 years, and the increasing rate of grassland vegetation coverage was the largest, while for crop vegetation coverage it was the smallest. (2) The vegetation coverage of crop was positively correlated with precipitation and negatively correlated with temperature in semi-arid areas of warm temperate zone in Liaoning Province, while it was positively correlated with precipitation and temperature in semi-humid areas of warm temperate zone. The response of grassland vegetation coverage to precipitation was stronger than temperature, while deciduous broadleaf forest, woody savanna and savanna were more sensitive to temperature. (3) The time lag responses of vegetation coverage with five main vegetation types to temperature and precipitation were different. The response of crop and grassland to precipitation in last month was sensitive during the growth season, while the responses of deciduous broadleaf forest, woody savanna and savanna to previous month’s temperature and precipitation were sensitive at the end stage of growth season.