Deep Learning for Clouds and Cloud Shadow Segmentation in Methane Satellite and Airborne Imaging Spectroscopy

2025-09-23

AI Summary

In hyperspectral remote sensing for methane monitoring (e.g., MethaneSAT/MethaneAIR), cloud cover and cloud shadows introduce significant biases in methane retrieval, severely degrading emission quantification accuracy. To address this, we propose a semantic segmentation method tailored to hyperspectral data for joint cloud and cloud-shadow detection. Our core innovation is the Spectral Channel Attention Network (SCAN), which explicitly models inter-channel spectral dependencies via a channel-wise attention mechanism, thereby enhancing fine-grained boundary delineation. Evaluated on real MethaneSAT imagery, SCAN outperforms established baselines—including U-Net, MLP-based classifiers, and iterative logistic regression—achieving substantial gains in detection accuracy (e.g., +8.2% mIoU over U-Net). To foster reproducibility and scalability, we publicly release both the source code and a curated, expert-annotated dataset. This work advances robust, physics-informed preprocessing for next-generation hyperspectral methane monitoring missions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Web data integration and cleaning
• Security and Privacy: Data transparency and provenance

Abstract

Effective cloud and cloud shadow detection is a critical prerequisite for accurate retrieval of concentrations of atmospheric methane or other trace gases in hyperspectral remote sensing. This challenge is especially pertinent for MethaneSAT and for its airborne companion mission, MethaneAIR. In this study, we use machine learning methods to address the cloud and cloud shadow detection problem for sensors with these high spatial resolutions instruments. Cloud and cloud shadows in remote sensing data need to be effectively screened out as they bias methane retrievals in remote sensing imagery and impact the quantification of emissions. We deploy and evaluate conventional techniques including Iterative Logistic Regression (ILR) and Multilayer Perceptron (MLP), with advanced deep learning architectures, namely UNet and a Spectral Channel Attention Network (SCAN) method. Our results show that conventional methods struggle with spatial coherence and boundary definition, affecting the detection of clouds and cloud shadows. Deep learning models substantially improve detection quality: UNet performs best in preserving spatial structure, while SCAN excels at capturing fine boundary details. Notably, SCAN surpasses UNet on MethaneSAT data, underscoring the benefits of incorporating spectral attention for satellite specific features. This in depth assessment of various disparate machine learning techniques demonstrates the strengths and effectiveness of advanced deep learning architectures in providing robust, scalable solutions for clouds and cloud shadow screening towards enhancing methane emission quantification capacity of existing and next generation hyperspectral missions. Our data and code is publicly available at https://doi.org/10.7910/DVN/IKLZOJ

Problem

• Detecting clouds and shadows in hyperspectral methane sensing imagery
• Improving methane retrieval accuracy by screening atmospheric obstructions
• Evaluating deep learning methods for spatial coherence in detection

Innovation

• Uses UNet for preserving spatial structure
• Employs SCAN with spectral attention mechanism
• Compares deep learning with conventional ML methods