Abstract. Wetlands are the largest natural source of methane (CH₄) emissions globally. Northern wetlands (>45° N), accounting for 42 % of global wetland area, are increasingly vulnerable to carbon loss, especially as CH₄ emissions may accelerate under intensified high-latitude warming. However, the magnitude and spatial patterns of high-latitude CH₄ emissions remain relatively uncertain. Here we present estimates of daily CH₄ fluxes obtained using a new machine learning-based wetland CH₄ upscaling framework (WetCH₄) that applies the most complete database of eddy covariance (EC) observations available to date, and satellite remote sensing informed observations of environmental conditions at 10-km resolution. The most important predictor variables included near-surface soil temperatures (top 40 cm), vegetation reflectance, and soil moisture. Our results, modeled from 138 site-years across 26 sites, had relatively strong predictive skill with a mean R² of 0.46 and 0.62 and a mean absolute error (MAE) of 23 nmol m^-2 s^-1 and 21 nmol m^-2 s^-1 for daily and monthly fluxes, respectively. Based on the model results, we estimated an annual average of 20.8 ±2.1 Tg CH₄ yr^-1 for the northern wetland region (2016–2022) and total budgets ranged from 13.7–44.1 Tg CH₄ yr^-1, depending on wetland map extents. Although 86 % of the estimated CH₄ budget occurred during the May–October period, a considerable amount (1.4 ±0.2 Tg CH₄) occurred during winter. Regionally, the West Siberian wetlands accounted for a majority (51 %) of the interannual variation in domain CH₄ emissions. Significant issues with data coverage remain, with only 23 % of the sites observing year-round and most of the data from 11 wetland sites in Alaska and 10 bog/fen sites in Canada and Fennoscandia, and in general, Western Siberian Lowlands are underrepresented by EC CH₄ sites. Our results provide high spatiotemporal information on the wetland emissions in the high-latitude carbon cycle and possible responses to climate change. Continued, all-season tower observations and improved soil moisture products are needed for future improvement of CH₄ upscaling. The dataset can be found at https://doi.org/10.5281/zenodo.10802154 (Ying et al., 2024).

中文翻译：

---

WetCH4：基于机器学习的 2016-2022 年北部湿地甲烷通量升级

摘要。湿地是全球最大的甲烷 (CH ₄ ) 自然排放源。占全球湿地面积 42% 的北部湿地（>45°N）越来越容易受到碳损失的影响，特别是在高纬度变暖加剧的情况下， CH _{4排放可能会加速。然而，高纬度CH 4}排放的规模和空间格局仍然相对不确定。在这里，我们提出了使用基于机器学习的新湿地 CH ₄升级框架 (WetCH _{4 ) 获得的每日 CH 4}通量估计值，该框架应用了迄今为止最完整的涡流协方差 (EC) 观测数据库以及卫星遥感信息观测结果10公里分辨率的环境条件。最重要的预测变量包括近地表土壤温度（顶部 40 厘米）、植被反射率和土壤湿度。我们的结果是根据 26 个站点的 138 个站点年进行建模的，具有相对较强的预测能力，平均 R ²为 0.46 和 0.62，平均绝对误差 (MAE) 为 23 nmol m ^-2 s ^-1和 21 nmol m ^-2 s ^-1分别表示每日和每月的通量。根据模型结果，我们估计北部湿地地区（2016-2022）年平均为 20.8 ±2.1 Tg CH ₄ yr ^{-1 ，总预算范围为 13.7–44.1 Tg CH} ₄ yr ^-1，具体取决于湿地地图范围。尽管估计的 CH ₄预算的 86%发生在 5 月至 10 月期间，但相当大的量 (1.4 ±0.2 Tg CH ₄ ) 发生在冬季。从区域来看，西西伯利亚湿地占 CH ₄排放范围年际变化的大部分（51%）。数据覆盖范围仍然存在重大问题，只有 23% 的站点全年进行观测，大部分数据来自阿拉斯加的 11 个湿地站点以及加拿大和芬诺斯坎迪亚的 10 个沼泽/沼泽站点，总体而言，西西伯利亚低地的代表性不足EC CH ₄位点。我们的结果提供了高纬度碳循环中湿地排放的高时空信息以及对气候变化的可能反应。未来改进 CH ₄升级需要持续的全季节塔观测和改进的土壤湿度产品。该数据集可以在 https://doi.org/10.5281/zenodo.10802154 找到（Ying 等人，2024）。