GLOFNet -- A Multimodal Dataset for GLOF Monitoring and Prediction

2025-10-12

AI Summary

To address the challenges of fragmented multi-source data, modality isolation, and absence of physics-aware visual annotations in glacial lake outburst flood (GLOF) prediction, this work introduces GLOFNet—the first spatiotemporally aligned, quality-controlled multimodal benchmark dataset for GLOF monitoring and forecasting, centered on the Hispar Glacier in the Karakoram. It innovatively integrates Sentinel-2 multispectral imagery, NASA glacier surface velocity, and MODIS land surface temperature data, employing cloud masking, quality filtering, temporal interpolation, cyclical time encoding, and cross-modal normalization for deep fusion. The dataset reveals pronounced seasonal velocity variations, a ~0.8 K/decade warming trend over the past two decades, and marked cryospheric spatial heterogeneity. GLOFNet establishes a scalable foundation for multimodal deep learning modeling of rare geohazards and is publicly released.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Glacial Lake Outburst Floods (GLOFs) are rare but destructive hazards in high mountain regions, yet predictive research is hindered by fragmented and unimodal data. Most prior efforts emphasize post-event mapping, whereas forecasting requires harmonized datasets that combine visual indicators with physical precursors. We present GLOFNet, a multimodal dataset for GLOF monitoring and prediction, focused on the Shisper Glacier in the Karakoram. It integrates three complementary sources: Sentinel-2 multispectral imagery for spatial monitoring, NASA ITS_LIVE velocity products for glacier kinematics, and MODIS Land Surface Temperature records spanning over two decades. Preprocessing included cloud masking, quality filtering, normalization, temporal interpolation, augmentation, and cyclical encoding, followed by harmonization across modalities. Exploratory analysis reveals seasonal glacier velocity cycles, long-term warming of ~0.8 K per decade, and spatial heterogeneity in cryospheric conditions. The resulting dataset, GLOFNet, is publicly available to support future research in glacial hazard prediction. By addressing challenges such as class imbalance, cloud contamination, and coarse resolution, GLOFNet provides a structured foundation for benchmarking multimodal deep learning approaches to rare hazard prediction.

Problem

• Addresses fragmented unimodal data for GLOF prediction
• Integrates satellite imagery and physical precursors for forecasting
• Provides structured multimodal dataset to benchmark deep learning

Innovation

• Integrates satellite imagery with glacier velocity data
• Combines temperature records with multispectral spatial monitoring
• Applies preprocessing techniques for multimodal data harmonization