Deep Learning-Driven Downscaling for Climate Risk Assessment of Projected Temperature Extremes in the Nordic Region

2025-11-05

AI Summary

High-resolution risk assessment of temperature extremes is urgently needed across Nordic Köppen–Geiger climate zones due to intensifying climate variability. Method: We propose the first deep learning downscaling framework integrating Vision Transformer, ConvLSTM, and a novel Geographic Spatiotemporal Attention Network (GeoStaNet), augmented with imbalance-aware learning and multi-model ensemble strategies. Bias correction and future temperature projections are performed on CMIP6 (NorESM2-LM) outputs via a DL-TOPSIS multi-criteria decision system. Contribution/Results: Validated across ten meteorological stations spanning diverse climate zones, the framework achieves an RMSE of 1.01°C (R² = 0.92). Projections indicate end-of-century warming of 4.8°C in Dfc and 3.9°C in Dfb regions, with diurnal temperature range expansion exceeding 1.5°C. Statistically significant warming signals emerge as early as 2032 in subarctic winter, demonstrating enhanced detection capability for emergent climate change impacts.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Rapid changes and increasing climatic variability across the widely varied Koppen-Geiger regions of northern Europe generate significant needs for adaptation. Regional planning needs high-resolution projected temperatures. This work presents an integrative downscaling framework that incorporates Vision Transformer (ViT), Convolutional Long Short-Term Memory (ConvLSTM), and Geospatial Spatiotemporal Transformer with Attention and Imbalance-Aware Network (GeoStaNet) models. The framework is evaluated with a multicriteria decision system, Deep Learning-TOPSIS (DL-TOPSIS), for ten strategically chosen meteorological stations encompassing the temperate oceanic (Cfb), subpolar oceanic (Cfc), warm-summer continental (Dfb), and subarctic (Dfc) climate regions. Norwegian Earth System Model (NorESM2-LM) Coupled Model Intercomparison Project Phase 6 (CMIP6) outputs were bias-corrected during the 1951-2014 period and subsequently validated against earlier observations of day-to-day temperature metrics and diurnal range statistics. The ViT showed improved performance (Root Mean Squared Error (RMSE): 1.01 degrees C; R^2: 0.92), allowing for production of credible downscaled projections. Under the SSP5-8.5 scenario, the Dfc and Dfb climate zones are projected to warm by 4.8 degrees C and 3.9 degrees C, respectively, by 2100, with expansion in the diurnal temperature range by more than 1.5 degrees C. The Time of Emergence signal first appears in subarctic winter seasons (Dfc: approximately 2032), signifying an urgent need for adaptation measures. The presented framework offers station-based, high-resolution estimates of uncertainties and extremes, with direct uses for adaptation policy over high-latitude regions with fast environmental change.

Problem

• Downscaling climate projections to assess temperature extremes in Nordic regions
• Providing high-resolution temperature data for regional adaptation planning
• Evaluating warming trends and diurnal range changes across diverse climate zones

Innovation

• Vision Transformer model for temperature downscaling
• ConvLSTM network processing spatiotemporal climate data
• Geospatial Transformer with attention mechanism