X-MethaneWet: A Cross-scale Global Wetland Methane Emission Benchmark Dataset for Advancing Science Discovery with AI

2025-05-23

AI Summary

Addressing the scientific challenge of strong spatiotemporal variability in global wetland methane emissions and limited observational coverage—both of which constrain modeling accuracy—this study constructs X-MethaneWet, the first cross-scale global benchmark dataset for wetland methane. It achieves, for the first time, spatiotemporal alignment and uncertainty quantification between the TEM-MDM biogeochemical model and FLUXNET-CH₄ observational data. To overcome data sparsity, we propose four migration learning paradigms tailored to sparse monitoring sites, integrating advanced sequential models—including LSTM, GRU, TCN, and Informer—with domain adaptation techniques. Evaluated on FLUXNET-CH₄ sites, our approach reduces mean RMSE by 18.7% relative to baselines, demonstrating significantly improved generalizability across diverse wetland types and climates. This work establishes a novel AI-driven paradigm for high-accuracy, scalable wetland methane modeling and provides a foundational, uncertainty-aware dataset to advance process-informed machine learning in Earth system science.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Methane (CH$_4$) is the second most powerful greenhouse gas after carbon dioxide and plays a crucial role in climate change due to its high global warming potential. Accurately modeling CH$_4$ fluxes across the globe and at fine temporal scales is essential for understanding its spatial and temporal variability and developing effective mitigation strategies. In this work, we introduce the first-of-its-kind cross-scale global wetland methane benchmark dataset (X-MethaneWet), which synthesizes physics-based model simulation data from TEM-MDM and the real-world observation data from FLUXNET-CH$_4$. This dataset can offer opportunities for improving global wetland CH$_4$ modeling and science discovery with new AI algorithms. To set up AI model baselines for methane flux prediction, we evaluate the performance of various sequential deep learning models on X-MethaneWet. Furthermore, we explore four different transfer learning techniques to leverage simulated data from TEM-MDM to improve the generalization of deep learning models on real-world FLUXNET-CH$_4$ observations. Our extensive experiments demonstrate the effectiveness of these approaches, highlighting their potential for advancing methane emission modeling and contributing to the development of more accurate and scalable AI-driven climate models.

Problem

• Modeling global wetland methane emissions accurately
• Improving methane flux prediction with AI algorithms
• Enhancing generalization of models using transfer learning

Innovation

• Cross-scale global wetland methane benchmark dataset
• Sequential deep learning models for prediction
• Transfer learning techniques for generalization