新模型融合天气模式与异常检测，提升极端气温预测精度。
MMWSTM-ADRAN+: A Novel Hybrid Deep Learning Architecture for Enhanced Climate Time Series Forecasting and Extreme Event Prediction
- 双流架构：一捕天气系统变化，一增强对罕见异常信号的敏感度。
- 在3个气象数据集上，极端高温预测误差降低23%~31%，极低温预测提升显著。
- 适合气候风险预警、能源调度等需高精度短期气候预测的场景。
精准预测短期极端气温事件仍是气候风险管理中的核心挑战。本文提出多模态天气状态转移模型与异常驱动循环注意力网络+（MMWSTM-ADRAN+），一种双流深度学习架构，将感知天气系统演变的动力学模型与聚焦异常的注意力机制结合，用于预测日最高气温及其极端值。第一流MMWSTM融合双向长短期记忆单元（BiLSTM）与可学习的马尔可夫状态转移矩阵，捕捉大尺度天气系统变化。第二流ADRAN集成双向门控循环单元（BiGRU）、多头自注意力与新颖的异常放大层，增强对低概率信号的敏感性。轻量级注意力融合门自适应确定各流贡献。模型优化采用定制的ExtremeWeatherLoss函数，对温度分布上下5%的极端值误差进行加权；并使用时间序列数据增强套件（抖动、缩放、时间/幅度扭曲），使训练数据量有效翻倍。
原文摘要 · Abstract (English)
Accurate short-range prediction of extreme air temperature events remains a fundamental challenge in operational climate-risk management. We present Multi-Modal Weather State Transition Model with Anomaly-Driven Recurrent Attention Network Plus (MMWSTM-ADRAN+), a dual-stream deep learning architecture that couples a regime-aware dynamics model with an anomaly-focused attention mechanism to forecast daily maximum temperature and its extremes. The first stream, MMWSTM, combines bidirectional Long Short-Term Memory (BiLSTM) units with a learnable Markov state transition matrix to capture synoptic-scale weather regime changes. The second stream, ADRAN, integrates bidirectional Gated Recurrent Units (BiGRUs), multi-head self-attention, and a novel anomaly amplification layer to enhance sensitivity to low-probability signals. A lightweight attentive fusion gate adaptively determines the contribution of each stream to the final prediction. Model optimization employs a custom ExtremeWeatherLoss function that up-weights errors on the upper 5% and lower 5% of the temperature distribution, and a time-series data augmentation suite (jittering, scaling, time/magnitude warping) that effectively quadruples the training data
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。