MMWSTM-ADRAN+: A Novel Hybrid Deep Learning Architecture for Enhanced Climate Time Series Forecasting and Extreme Event Prediction

TL;DR

The paper introduces MMWSTM-ADRAN+, a hybrid deep learning model combining regime-aware dynamics and anomaly-focused attention to improve short-term extreme temperature event forecasting.

Contribution

It presents a novel dual-stream architecture with a custom loss and data augmentation for better climate extreme event prediction.

Findings

Enhanced accuracy in extreme temperature forecasting.

Effective detection of low-probability temperature anomalies.

Improved model robustness through data augmentation.

Abstract

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