Towards Large Scale Geostatistical Methane Monitoring with Part-based Object Detection

2025-07-24

AI Summary

Detecting sparsely distributed, extremely rare biogas digesters in remote sensing imagery—and quantifying their methane emissions—is challenging due to severe class imbalance and insufficient labeled training samples. Method: We propose a part-level object detection framework that leverages key structural components (e.g., gas-holding membranes, fermentation tanks) as weak supervision cues, integrates few-shot learning with spatially adaptive feature alignment to enhance detection sensitivity under extreme class imbalance, and couples detection outputs with a geostatistical model for interpretable, region-level methane emission estimation. Contribution/Results: Evaluated on multi-regional satellite imagery across France, our method establishes the first high-confidence national-scale digester spatial inventory and enables robust kilometer-resolution methane flux inversion—outperforming end-to-end detection baselines significantly. This work provides a transferable methodological paradigm for remote sensing-based census of rare infrastructure and greenhouse gas emission monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Object detection is one of the main applications of computer vision in remote sensing imagery. Despite its increasing availability, the sheer volume of remote sensing data poses a challenge when detecting rare objects across large geographic areas. Paradoxically, this common challenge is crucial to many applications, such as estimating environmental impact of certain human activities at scale. In this paper, we propose to address the problem by investigating the methane production and emissions of bio-digesters in France. We first introduce a novel dataset containing bio-digesters, with small training and validation sets, and a large test set with a high imbalance towards observations without objects since such sites are rare. We develop a part-based method that considers essential bio-digester sub-elements to boost initial detections. To this end, we apply our method to new, unseen regions to build an inventory of bio-digesters. We then compute geostatistical estimates of the quantity of methane produced that can be attributed to these infrastructures in a given area at a given time.

Problem

• Detecting rare bio-digesters in large-scale remote sensing data
• Estimating methane production from bio-digesters geostatistically
• Addressing data imbalance in object detection for environmental monitoring

Innovation

• Part-based object detection for rare objects
• Novel dataset with imbalanced test set
• Geostatistical methane production estimation