对比多种模型发现，卷积LSTM在印度四城降雨预测中并未持续领先。
Benchmarking ConvLSTM for One-Day-Ahead IMDAA Rainfall-Field Prediction across Four Indian Cities
- 用卷积递归结构处理每日再分析数据，比较十种不同模型的预测效果。
- 简单模型如持久性法在德里表现最佳，全连接LSTM在三城误差最低。
- 高降雨日预测仍依赖传统方法，且神经网络普遍低估雨量和漏报高峰。
卷积长短期记忆网络（ConvLSTM）广泛用于降水预报，但其性能证据多来自高频雷达数据。本研究检验了在小尺度每日再分析网格上，卷积递归是否提升一日提前量的降雨场预测能力。分析1998–2020年6–9月印度季风数据同化与分析（IMDAA）场中班加罗尔、德里、加尔各答和孟买四城市的降雨数据，对比了十种朴素、统计、树模型和神经网络方法，输入包括仅大气变量及大气+历史降雨量。评估涵盖完整场、区域平均降雨、空间异常及强降雨日。结果表明，ConvLSTM未始终优于简单模型：在班加罗尔、加尔各答和孟买，全连接LSTM（FC-LSTM）实现最低区域平均误差；德里则由持久性模型最优。仅在孟买，ConvLSTM在空间异常预测中表现最佳，因该地降雨场具有更强短时空间连续性，且历史降雨输入提升了所有神经架构性能。但ConvLSTM与FC-LSTM差距微小。所有神经模型均系统性低估降雨强度，并在高降雨日漏报过多阈值超限事件，而持久性模型在所有城市中检测性能最高。后验分析显示，各模型对最新输入日最敏感，其中孟买模型对近期多日输入也更敏感。结论表明，仅靠格点输入不足以证明采用ConvLSTM的合理性，模型选择应基于对平均、空间和极端降雨性能的全面基准测试。
原文摘要 · Abstract (English)
Convolutional long short-term memory networks (ConvLSTMs) are widely used for precipitation forecasting, but most evidence for their performance comes from dense, high-frequency radar sequences. This study tests whether convolutional recurrence improves one-day-ahead rainfall-field prediction on small daily reanalysis grids. Indian Monsoon Data Assimilation and Analysis (IMDAA) fields for June-September 1998-2020 were analysed for Bengaluru, Delhi, Kolkata and Mumbai. Ten naive, statistical, tree-based and neural approaches were compared using atmospheric-only and rainfall-history-plus-atmospheric inputs. Performance was assessed for complete fields, domain-mean rainfall, spatial anomalies and high-rainfall days. ConvLSTM did not consistently outperform simpler alternatives. FC-LSTM produced the numerically lowest domain-mean rainfall error in Bengaluru, Kolkata and Mumbai, whereas persistence performed best in Delhi. ConvLSTM produced the numerically lowest spatial-anomaly error only in Mumbai, where rainfall fields showed greater short-term spatial continuity and rainfall-history inputs improved all three neural architectures. The difference between ConvLSTM and FC-LSTM was nevertheless small. Neural models underestimated rainfall magnitude and predicted too few threshold exceedances on high-rainfall days, while persistence achieved the highest detection performance in every city. Post-hoc analyses showed that the selected models were most sensitive to the latest input day, with broader recent-lag sensitivity in Mumbai. These findings show that gridded inputs alone do not justify ConvLSTM and that architecture choice should follow strong benchmarking across average, spatial and high-rainfall performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。