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

• URL: http://arxiv.org/abs/2511.13419v1
• Date: Mon, 17 Nov 2025 14:31:54 GMT
• Title: MMWSTM-ADRAN+: A Novel Hybrid Deep Learning Architecture for Enhanced Climate Time Series Forecasting and Extreme Event Prediction
• Abstract summary: We present Multi-Modal Weather State Transition Model with Anomaly-Driven Recurrent Attention Network Plus (MMWSTM-ADRAN+)<n> MMWSTM combines bidirectional Long Short-Term Memory (BiLSTM) units with a learnable Markov state transition matrix to capture synoptic-scale weather regime changes.<n>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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• IMPA-Net: Meteorology-Aware Multi-Scale Attention and Dynamic Loss for Extreme Convective Radar Nowcasting [2.405586180193259]
  Short-range prediction of convective precipitation from weather radar observations is essential for severe weather warnings.<n>We propose IMPA-Net, a deterministic 0-2 hour nowcasting framework that addresses limitations through meteorologically-informed designs at the input, architecture, and loss function levels.
  arXiv  Detail & Related papers  (2026-04-27T09:30:07Z)
• Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting [52.53742727060265]
  Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets.<n>Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3Dwin UNet backbone of the pioneering model.<n>We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data.<n>Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T11:40:39Z)
• FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction [5.827179141989176]
  Traffic modeling requires complex temporal dynamics and long-range spatial forecasting over large sensor networks.<n>We propose FAST, a framework that combines attention-space modeling for unified state traffic forecasting.<n>FAST consistently outperforms strong baselines from Transformer-, GNN-, attention-, and Mamba-based families.
  arXiv  Detail & Related papers  (2026-04-15T04:05:10Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting [6.540270371082014]
  This study develops a deep learning-based ensemble framework for multi-step precipitation prediction.<n>The architecture employs a patch-based Swin Transformer backbone with periodic convolutions to handle longitudinal continuity.<n>Training minimizes a hybrid loss combining the Continuous Ranked Probability Score (CRPS) and weighted log1p mean squared error (log1pMSE)
  arXiv  Detail & Related papers  (2025-10-23T17:43:38Z)
• SEMPO: Lightweight Foundation Models for Time Series Forecasting [45.456949943052116]
  SEMPO is a lightweight foundation model that requires pretraining on relatively small-scale data, yet exhibits strong general time series forecasting.<n> SEMPO comprises two key modules: 1) energy-aware SpEctral decomposition module, that substantially improves the utilization of pre-training data.<n>Experiments on two large-scale benchmarks covering 16 datasets demonstrate the superior performance of SEMPO in both zero-shot and few-shot forecasting scenarios.
  arXiv  Detail & Related papers  (2025-10-22T15:58:44Z)
• MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction [44.09814361538848]
  We introduce MP-Bench, the first large-scale temporal multimodal dataset for severe weather events prediction.<n>On top of this dataset, we develop a multimodal large model (MMLM) that directly ingests 4D meteorological inputs.<n> MMLM performs exceptionally well across multiple tasks, highlighting its effectiveness in severe weather understanding.
  arXiv  Detail & Related papers  (2025-08-09T06:54:41Z)
• Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting [52.6508222408558]
  We introduce Elucidated Rolling Diffusion Models (ERDM)<n>ERDM is the first framework to unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM)<n>On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5circ resolution, ERDM consistently outperforms key diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-06-24T21:44:31Z)
• PFformer: A Position-Free Transformer Variant for Extreme-Adaptive Multivariate Time Series Forecasting [9.511600544581425]
  PFformer is a position-free Transformer-based model designed for single-target MTS forecasting.<n> PFformer integrates two novel embedding strategies: Enhanced Feature-based Embedding (EFE) and Auto-Encoder-based Embedding (AEE)
  arXiv  Detail & Related papers  (2025-02-27T22:21:27Z)
• Accurate Prediction of Temperature Indicators in Eastern China Using a Multi-Scale CNN-LSTM-Attention model [0.0]
  We propose a weather prediction model based on a multi-scale convolutional CNN-LSTM-Attention architecture.<n>The model integrates Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and attention mechanisms.<n> Experimental results show that the model performs excellently in predicting temperature trends with high accuracy.
  arXiv  Detail & Related papers  (2024-12-11T00:42:31Z)
• FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting [0.0]
  Climate stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns.<n> Accurate forecasting is critical for monitoring these phenomena and supporting mitigation strategies.<n>Recent data-driven models for time-series forecasting, including CNNs, RNNs, and attention-based transformers, have shown promise but struggle with dependencies and limited parallelization.<n>In this work, we present Modulated Attention Focal (FATE) for reliable time-series forecasting.
  arXiv  Detail & Related papers  (2024-08-21T04:40:18Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting [17.70984737213973]
  HiMTM is a hierarchical multi-scale masked time series modeling with self-distillation for long-term forecasting. HiMTM integrates four key components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales; (2) decoupled encoder-decoder (DED) that directs the encoder towards feature extraction while the decoder focuses on pretext tasks. Experiments on seven mainstream datasets show that HiMTM surpasses state-of-the-art self-supervised and end-to-end learning methods by a considerable margin of 3.16-68.54%.
  arXiv  Detail & Related papers  (2024-01-10T09:00:03Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning [63.83425382922157]
  Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
  arXiv  Detail & Related papers  (2022-03-26T20:37:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.