Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.00338 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914619595948032 |
|---|---|
| author | Dong, Rongchao Sun, Yiming Chen, Shuo Oh, Youmi Liu, Licheng Xie, Yiqun Jia, Xiaowei |
| author_facet | Dong, Rongchao Sun, Yiming Chen, Shuo Oh, Youmi Liu, Licheng Xie, Yiqun Jia, Xiaowei |
| contents | Methane is a potent greenhouse gas that significantly contributes to global warming. However, accurately estimating global methane emissions and consumption remains challenging due to the complex interactions among environmental drivers that may vary across spatial and temporal scales. Prior data-driven methods often overlook the inherent spatiotemporal heterogeneity of ecosystems, failing to explicitly capture site-specific characteristics and cross-year evolutionary dynamics. To address these issues, we propose the Contrastive Hierarchical Adaptive Meta-network (CHAM-net), a novel framework that explicitly learns from historical context to capture site-specific dynamics. CHAM-net employs a hierarchical encoder-decoder architecture, in which the encoder captures site-specific characteristics from historical data and then dynamically conditions the decoder to generate the final prediction. Experimental results demonstrate that CHAM-net consistently outperforms all baseline methods on both simulation and observational datasets for methane emission and consumption, achieving nRMSE values as low as 0.43 and 0.88 with corresponding R2 scores up to 0.97 and 0.68 for emission prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00338 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction Dong, Rongchao Sun, Yiming Chen, Shuo Oh, Youmi Liu, Licheng Xie, Yiqun Jia, Xiaowei Machine Learning Methane is a potent greenhouse gas that significantly contributes to global warming. However, accurately estimating global methane emissions and consumption remains challenging due to the complex interactions among environmental drivers that may vary across spatial and temporal scales. Prior data-driven methods often overlook the inherent spatiotemporal heterogeneity of ecosystems, failing to explicitly capture site-specific characteristics and cross-year evolutionary dynamics. To address these issues, we propose the Contrastive Hierarchical Adaptive Meta-network (CHAM-net), a novel framework that explicitly learns from historical context to capture site-specific dynamics. CHAM-net employs a hierarchical encoder-decoder architecture, in which the encoder captures site-specific characteristics from historical data and then dynamically conditions the decoder to generate the final prediction. Experimental results demonstrate that CHAM-net consistently outperforms all baseline methods on both simulation and observational datasets for methane emission and consumption, achieving nRMSE values as low as 0.43 and 0.88 with corresponding R2 scores up to 0.97 and 0.68 for emission prediction. |
| title | CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2606.00338 |