Deep learning-based subseasonal to seasonal precipitation prediction in southwest China:Algorithm comparison and sensitivity to input features

The prediction of precipitation at subseasonal to seasonal(S2S)timescales remains an enormous challenge because of the gap between weather and climate predictions.This study compares three deep learning algorithms,namely,the long short-term memory recurrent(LSTM),gated recurrent unit(GRU),and recurrent neural network(RNN),and selects the optimal algorithm to establish an S2S precipitation prediction model.The models were evaluated in four subregions of the Sichuan Province:the Plateau,Valley,eastern Basin,and western Basin.The results showed that the RNN model had better performance than the LSTM and GRU models.This could be because the RNN model had an advantage over the LSTM model in the transformation of climate indices with positive and negative variations.In the validation of test datasets,the RNN model successfully predicted the precipitation trend in most years during the wet season(May-October).The RNN model had a lower prediction bias(within±10%),higher sign accuracy of the precipitation trend(~88.95%),and greater accuracy of the maximum precipitation month(>0.85).For the prediction of different lead times,the RNN model was able to provide a stable trend prediction for summer precipitation,and the time correlation coefficient score was higher than that of the National Climate Center of China.Furthermore,this study proposed a method to measure the sensitivity of the RNN model to different input features,which may provide unprecedented insights into the nonlinear relationship and complicated feedback process among climate systems.The results of the sensitivity distribution are as follows.First,the Niño 4 and Niño 3.4 indices were equally important for the prediction of wet season precipitation.Second,the sensitivity of the snow cover on the Tibetan Plateau was higher than that in the Northern Hemisphere.Third,an opposite sensitivity appeared in two different patterns of the Indian Ocean and sea ice concentrations in the Arctic and the Barents Sea.

The increasing predominance of extreme precipitation in Southwest China since the late 1970s

本文分析了中国西南20世纪70年代末以来极端降水事件的频率,强度及其对总降水的贡献.结果表明,该地区约60%的降水站点极端降水的频率和强度正在增加,而大多数站点总降水频率明显减少.同时极端降水总量对总降水量的贡献有显著增加的趋势,极端降水在日益干旱的中国西南地区变得更具主导性.研究结果提醒应更加重视极端降水及其可能引发的次生灾害,如洪水,山体滑坡等.

Main Detrainment Height of Deep Convection Systems over the Tibetan Plateau and Its Southern Slope

Deep convection systems (DCSs) can rapidly lift water vapor and other pollutants from the lower troposphere to the upper troposphere and lower stratosphere. The main detrainment height determines the level to which the air parcel is lifted. We analyzed the main detrainment height over the Tibetan Plateau and its southern slope based on the CloudSat Cloud Profiling Radar 2B_GEOPROF dataset and the Aura Microwave Limb Sounder Level 2 cloud ice product onboard the Atrain constellation of Earth-observing satellites. It was found that the DCSs over the Tibetan Plateau and its southern slope have a higher main detrainment height (about 10-16 km) than other regions in the same latitude. The mean main detrainment heights are 12.9 and 13.3 km over the Tibetan Plateau and its southern slope, respectively. The cloud ice water path decreases by 16.8% after excluding the influences of DCSs, and the height with the maximum increase in cloud ice water content is located at 178 hPa (about 13 km). The main detrainment height and outflow horizontal range are higher and larger over the central and eastern Tibetan Plateau, the west of the southern slope, and the southeastern edge of the Tibetan Plateau than that over the northwestern Tibetan Plateau. The main detrainment height and outflow horizontal range are lower and broader at nighttime than during daytime.

A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis

暴雨是我国最重要的自然灾害之一.大量的研究表明,暴雨的频率和强度在全球变暖的背景下正在逐年增强.但是如何成功的预测短期暴雨,特别是发生在复杂地形下的暴雨,仍然是一个巨大的挑战.本项研究采用BP神经网络和天气学诊断相结合的方法,探索了一种四川盆地西部复杂地形下的暴雨预报模型.该模型有效改善了喇叭口地形下,受低层偏东风影响的暴雨预报准确性.机器学习与天气学理论的结合,提升了模型的物理基础和预测成功率,同时该方法也为发展具有本地特征的暴雨预报客观工具,提供了一定的参考价值.