【學術亮點】Innovating Taiwan's greenhouse gas estimation: A case study of atmospheric methane using GeoAI-based ensemble mixed spatial prediction model
Ecological Agriculture: Assessment of Forest Carbon Sink and Ecological Economy under Climate Change【 Department of Forestry / Liu, Wan-Yu / Distinguished Professor 、Department of Geomatics, National Cheng Kung University / Wu, Chih-Da / Professor】
生態農業：氣候變遷下森林碳匯與生態經濟評估【森林學系/柳婉郁特聘教授、國立成功大學測量及空間資訊學系/吳治達教授】
| 論文篇名 | 英文：Innovating Taiwan's greenhouse gas estimation: A case study of atmospheric methane using GeoAI-based ensemble mixed spatial prediction model 中文：臺灣溫室氣體排放估算之創新：以基於地理人工智慧的集成混合空間預測模型為例的甲烷研究 |
| 期刊名稱 | Journal of Environmental Management |
| 發表年份,卷數,起迄頁數 | 2025, 380, no.125110 |
| 作者 | Chang, Hao-Ting; Chern, Yinq-Rong; Asri, Aji Kusumaning; Liu, Wan-Yu(柳婉郁); Hsu, Chin-Yu; Hsiao, Ta-Chih; Chi, Kai Hsien; Lung, Shih-Chun Candice; Wu, Chih-Da(吳治達)* |
| DOI | 10.1016/j.jenvman.2025.125110 |
| 中文摘要 | 本研究針對甲烷（CH₄）這一全球暖化潛勢高達二氧化碳 80 倍的溫室氣體，提出了以 GeoAI 為核心的集成混合空間預測模型，突破以往僅著重排放源與減量策略的研究框架，首度全面分析臺灣地區大氣 CH₄ 濃度的時空變異。透過整合多種機器學習演算法並納入多元因子，本研究揭示了影響 CH₄ 濃度的關鍵因素，包括水產養殖、畜牧業、交通用地、氣象條件、人口密度、宗教活動及主要污染物等，並發現春、冬兩季濃度較高，夏、秋較低。模型於訓練、測試、交叉驗證與外部驗證中皆展現出高度解釋力（R² 分別為 0.99、0.82、0.98、0.67），顯示其穩健性與廣泛適用性。此成果不僅為臺灣甲烷濃度估算提供了高精度工具，也為全球淨零碳排與氣候減緩策略提供新的決策依據，具有方法學創新與政策應用的雙重價值。 |
| 英文摘要 | This study addresses a gap in atmospheric greenhouse gas research, focusing on methane (CH4), a gas with a global warming potential 80 times greater than carbon dioxide (CO2). Unlike prior studies that focus on emission sources and reduction strategies, this research emphasizes the spatiotemporal variations in atmospheric CH4 concentrations, providing new perspectives on global climate mitigation efforts. A novel GeoAI-based ensemble mixed spatial prediction model was developed, integrating multiple machine learning algorithms and considering various factors to accurately estimate CH4 concentrations across Taiwan. In the context of global net-zero emissions, this study offers a robust approach to assess spatial variations in CH4 concentrations, providing valuable insights into the effectiveness of greenhouse gas reduction policies and climate strategies. Key factors influencing CH4 levels include aquaculture, livestock, transportation land use, wind speed, national CH4 emissions, net greenhouse gas emissions, population density, quarry sites, solar radiation, seasonal variations, residential areas, temples, CO2 removal levels, and primary pollutants (e.g., NO2, NOx, PM2.5, PM10, CO, CO2, SO2, and O3). Seasonal analysis revealed higher CH4 concentrations in spring and winter, and lower levels in summer and autumn. The model demonstrated high explanatory power with R2 values of 0.99, 0.82, 0.98, and 0.67 across training, testing, cross-validation, and external validation datasets. This study presents a model that enhances the understanding of the dynamic factors influencing methane concentration variations. The methodology developed in this research can serve as a reference for other regions and timeframes, potentially offering key insights for the formulation of effective global climate mitigation strategies. |
| 發表成果與本中心研究主題相關性 | 本研究成果對永續農業具有深遠助益。甲烷是由畜牧業與水產養殖等農業活動大量排放的重要溫室氣體，對氣候變遷影響顯著。透過本研究所發展的 GeoAI 集成混合空間預測模型，可高精度掌握不同時空條件下的大氣甲烷濃度變化，並辨識出與農業相關的關鍵因子，如畜牧業、水產養殖、季節性氣候條件與土地利用模式。這不僅有助於農業部門更有效地評估與管理甲烷排放，還能為低碳農法的設計、農場碳管理策略以及農業碳盤查提供科學依據。更重要的是，本研究揭示了甲烷濃度的動態特徵，能協助制定兼顧農業生產與減排需求的政策，推動畜牧與養殖產業的綠色轉型，進而實現農業在糧食安全、氣候韌性與永續發展之間的平衡。 |
