西安理工大学学报2023，Vol.39Issue(4)：529-535,7.DOI:10.19322/j.cnki.issn.1006-4710.2023.04.009
基于差分Causal LSTM模型的气象图像短时预测研究
Research on short-time prediction of meteorological images based on differential-Causal LSTM Model
摘要
Abstract
Due to the low accuracy of meteorological image sequences'short-term prediction,we propose a differential-Causal LSTM model by using Causal LSTM with cascaded memory units,which is an introduction to the image gradient difference penalty term into the training process to improve the prediction model's ability to capture the dynamics and abrupt changes of short-time sequences.We first establish the meteorological image short-time prediction model by the recur-rent neural network and then analyze the prediction effect by the ConvLSTM model on weather radar echogram and satellite cloud sequences.The results show that the improved model in this paper can effectively reduce the blurring and improve the accuracy of prediction results.The dif-ferential-Causal LSTM model improves the critical success index(CSI)by 0.019 in the HKO-7 dataset,CSI also improved by 0.078 in the meteorological cloud image dataset,and the blurring is reduced.关键词
ConvLSTM/Causal LSTM/端到端模型/图像梯度差分损失Key words
ConvLSTM/Causal LSTM/end-to-end module/gradient difference loss分类
天文与地球科学引用本文复制引用
张晓晖,白文奇,杨松楠,王晓娟..基于差分Causal LSTM模型的气象图像短时预测研究[J].西安理工大学学报,2023,39(4):529-535,7.基金项目
陕西省自然科学基础研究计划资助项目(2021JLM-58) （2021JLM-58）
