Daily Land Surface Temperature Reconstruction in Landsat Cross-Track Areas Using Deep Ensemble Learning With Uncertainty Quantification

2025-02-20

AI Summary

High-spatiotemporal-resolution land surface temperature (LST) reconstruction over complex urban surfaces is hindered by severe Landsat cloud contamination and its 16-day revisit cycle, leading to substantial data gaps. Method: This study proposes DELAG, a deep ensemble learning framework that innovatively integrates annual thermal cycle modeling, Gaussian process regression, and multi-source remote sensing data fusion to enable daily, 30-m-resolution urban LST reconstruction and associated uncertainty quantification. Leveraging cross-track and dual-satellite Landsat observations (enhanced to four scenes per 16-day period since 2021), DELAG significantly mitigates data scarcity. Results: Validation over New York, London, and Hong Kong demonstrates cloud-obscured LST reconstruction RMSEs of 0.84–1.62 K—surpassing state-of-the-art methods. Subsequent near-surface air temperature retrieval achieves RMSEs of 1.48–2.11 K, matching the accuracy attainable from clear-sky LST.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• 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: Applied ML and AI for Web-based mobile applications

Abstract

Many real-world applications rely on land surface temperature (LST) data at high spatiotemporal resolution. In complex urban areas, LST exhibits significant variations, fluctuating dramatically within and across city blocks. Landsat provides high spatial resolution data at 100 meters but is limited by long revisit time, with cloud cover further disrupting data collection. Here, we propose DELAG, a deep ensemble learning method that integrates annual temperature cycles and Gaussian processes, to reconstruct Landsat LST in complex urban areas. Leveraging the cross-track characteristics and dual-satellite operation of Landsat since 2021, we further enhance data availability to 4 scenes every 16 days. We select New York City, London and Hong Kong from three different continents as study areas. Experiments show that DELAG successfully reconstructed LST in the three cities under clear-sky (RMSE = 0.73-0.96 K) and heavily-cloudy (RMSE = 0.84-1.62 K) situations, superior to existing methods. Additionally, DELAG can quantify uncertainty that enhances LST reconstruction reliability. We further tested the reconstructed LST to estimate near-surface air temperature, achieving results (RMSE = 1.48-2.11 K) comparable to those derived from clear-sky LST (RMSE = 1.63-2.02 K). The results demonstrate the successful reconstruction through DELAG and highlight the broader applications of LST reconstruction for estimating accurate air temperature. Our study thus provides a novel and practical method for Landsat LST reconstruction, particularly suited for complex urban areas within Landsat cross-track areas, taking one step toward addressing complex climate events at high spatiotemporal resolution.

Problem

• Reconstructs Landsat LST in urban areas
• Improves data availability with dual-satellite operation
• Quantifies uncertainty in temperature reconstruction

Innovation

• Deep ensemble learning integrates temperature cycles
• Enhances data availability with dual-satellite operation
• Quantifies uncertainty to improve reconstruction reliability