Learning Regional Monsoon Patterns with a Multimodal Attention U-Net

• URL: http://arxiv.org/abs/2509.23267v1
• Date: Sat, 27 Sep 2025 11:48:30 GMT
• Title: Learning Regional Monsoon Patterns with a Multimodal Attention U-Net
• Authors: Swaib Ilias Mazumder, Manish Kumar, Aparajita Khan,
• Abstract summary: We present a multimodal deep learning framework for high-resolution precipitation classification.<n>We curate a new 1 km resolution dataset for five Indian states.<n>Our framework consistently outperforms unimodal baselines and existing deep learning methods.
• Score: 3.134311415077079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate monsoon rainfall prediction is vital for India's agriculture, water management, and climate risk planning, yet remains challenging due to sparse ground observations and complex regional variability. We present a multimodal deep learning framework for high-resolution precipitation classification that leverages satellite and Earth observation data. Unlike previous rainfall prediction models based on coarse 5-50 km grids, we curate a new 1 km resolution dataset for five Indian states, integrating seven key geospatial modalities: land surface temperature, vegetation (NDVI), soil moisture, relative humidity, wind speed, elevation, and land use, covering the June-September 2024 monsoon season. Our approach uses an attention-guided U-Net architecture to capture spatial patterns and temporal dependencies across modalities, combined with focal and dice loss functions to handle rainfall class imbalance defined by the India Meteorological Department (IMD). Experiments demonstrate that our multimodal framework consistently outperforms unimodal baselines and existing deep learning methods, especially in extreme rainfall categories. This work contributes a scalable framework, benchmark dataset, and state-of-the-art results for regional monsoon forecasting, climate resilience, and geospatial AI applications in India.

Related papers

• A Spatio-Temporal Deep Learning Approach For High-Resolution Gridded Monsoon Prediction [0.0]
  Indian Monsoon Summer (ISM) is a critical climate phenomenon, impacting the agriculture, economy, and water security of over a billion people.<n>Traditional long-range forecasting has predominantly focused on predicting a single, spatially-averaged seasonal value, lacking spatial detail essential for regional-level management.<n>We introduce a novel learning framework that reframes monsoon prediction as a deep-temporal computer vision task.<n>Using 85 years of ERA5 reanalysis data for predictors and IMD rainfall data for targets, we employ a Convolutional Neural Network (CNN)-based architecture to learn the detail mapping from the complex pre-monsoon period
  arXiv  Detail & Related papers  (2026-01-05T14:02:04Z)
• IndiaWeatherBench: A Dataset and Benchmark for Data-Driven Regional Weather Forecasting over India [37.53463011903496]
  IndiaWeatherBench is a benchmark for data-driven regional weather forecasting focused on the Indian subcontinent.<n>We implement and evaluate a range of models across diverse architectures, including UNets, Transformers, and Graph-based networks.<n>We open-source all raw and preprocessed datasets, model implementations, and pipelines to promote accessibility and future development.
  arXiv  Detail & Related papers  (2025-08-31T01:25:49Z)
• ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method [61.76389719956301]
  We contribute a multi-modal climate benchmark, i.e., ClimateBench-M, which aligns time series climate data from ERA5, extreme weather events data from NOAA, and satellite image data from NASA.<n>Under each data modality, we also propose a simple but strong generative method that could produce competitive performance in weather forecasting, thunderstorm alerts, and crop segmentation tasks.
  arXiv  Detail & Related papers  (2025-04-10T02:22:23Z)
• OneForecast: A Universal Framework for Global and Regional Weather Forecasting [67.61381313555091]
  We propose a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks.<n>By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region.<n>We introduce an adaptive messaging mechanism, using dynamic gating units, to deeply integrate node and edge features for more accurate extreme event forecasting.
  arXiv  Detail & Related papers  (2025-02-01T06:49:16Z)
• Efficient Localized Adaptation of Neural Weather Forecasting: A Case Study in the MENA Region [62.09891513612252]
  We focus on limited-area modeling and train our model specifically for localized region-level downstream tasks. We consider the MENA region due to its unique climatic challenges, where accurate localized weather forecasting is crucial for managing water resources, agriculture and mitigating the impacts of extreme weather events. Our study aims to validate the effectiveness of integrating parameter-efficient fine-tuning (PEFT) methodologies, specifically Low-Rank Adaptation (LoRA) and its variants, to enhance forecast accuracy, as well as training speed, computational resource utilization, and memory efficiency in weather and climate modeling for specific regions.
  arXiv  Detail & Related papers  (2024-09-11T19:31:56Z)
• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• Enhanced Precision in Rainfall Forecasting for Mumbai: Utilizing Physics Informed ConvLSTM2D Models for Finer Spatial and Temporal Resolution [0.0]
  This study introduces deep learning spatial model aimed at enhancing rainfall prediction accuracy on a finer scale. To test this hypothesis, we introduce a physics informed ConvLSTM2D model to predict precipitation 6hr and 12hr ahead for Mumbai, India.
  arXiv  Detail & Related papers  (2024-04-01T13:56:12Z)
• Comparing skill of historical rainfall data based monsoon rainfall prediction in India with NWP forecasts [1.517355052203938]
  The Indian summer monsoon is a highly complex and critical weather system that directly affects over a billion people across the Indian subcontinent.<n> Accurate short-term forecasting remains a major scientific challenge due to the monsoon's intrinsic nonlinearity and its sensitivity to multi-scale drivers.<n>In this study, we address the problem of forecasting daily rainfall across India during the summer months, focusing on both one-day and three-day lead times.
  arXiv  Detail & Related papers  (2024-02-12T17:59:20Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Multi-scale Digital Twin: Developing a fast and physics-informed surrogate model for groundwater contamination with uncertain climate models [53.44486283038738]
  Climate change exacerbates the long-term soil management problem of groundwater contamination. We develop a physics-informed machine learning surrogate model using U-Net enhanced Fourier Neural Contaminated (PDENO) In parallel, we develop a convolutional autoencoder combined with climate data to reduce the dimensionality of climatic region similarities across the United States.
  arXiv  Detail & Related papers  (2022-11-20T06:46:35Z)
• A Deep and Wide Neural Network-based Model for Rajasthan Summer Monsoon Rainfall (RSMR) Prediction [0.0]
  We analyze and evaluate various deep learning approaches for prediction of summer monsoon rainfall in Indian state of Rajasthan. From IMD grided dataset, rainfall data of 484 coordinates are selected which lies within the geographical boundaries of Rajasthan. We have also collected rainfall data of 158 rain gauge station from water resources department.
  arXiv  Detail & Related papers  (2021-03-03T03:42:45Z)
• Prediction of Rainfall in Rajasthan, India using Deep and Wide Neural Network [0.5735035463793008]
  We propose a deep and wide rainfall prediction model (DWRPM) to predict rainfall in Indian state of Rajasthan. Information of geographical parameters (latitude and longitude) are included in a unique way. We compare our results with various deep-learning approaches like LSTM and CNN, which are observed to work well in sequence-based predictions.
  arXiv  Detail & Related papers  (2020-10-22T15:01:22Z)

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.