Which Site, and When: A Free-Satellite-Data Test of Himalayan Glacial Lake Bursts, Landslides, and Ice Floods

地点与时机：基于免费卫星数据的喜马拉雅冰湖溃决、滑坡及冰洪测试

Abstract: Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress. A companion feasibility study found that deformation indicates which lake is destabilizing and weather indicates when it is at risk, but proposed no predictive model. To address this gap, we propose and evaluate models that predict which site is susceptible and when a trigger arrives.

摘要： 两类免费卫星信号为尼泊尔喜马拉雅地区的冰湖溃决风险提供了真实信息：雷达干涉测量可以观测到冰碛坝的缓慢下沉，而卫星气象数据则能标记出处于压力下的冰湖所经历的危险周数。一项配套的可行性研究发现，形变数据可以指示哪些冰湖正在失稳，而气象数据可以指示其何时处于风险之中，但该研究并未提出预测模型。为了填补这一空白，我们提出并评估了能够预测哪些地点易受影响以及触发因素何时到来的模型。

We test three related hazards on free data alone: large moraine- and ice-dammed bursts, rainfall-triggered landslides, and smaller floods from ponds on and around a glacier. Each hazard gets two questions, never blended. Using 589 dated outbursts from HMAGLOFDB and several thousand catalogued landslides, we match each event against similar but unfailed sites, and hold every model to a strong simple baseline under spatial cross-validation that withholds whole map tiles, so no model succeeds by recognising a trained-on neighbourhood.

我们仅利用免费数据测试了三种相关灾害：大型冰碛坝和冰坝溃决、降雨引发的滑坡，以及冰川上及其周围池塘引发的小型洪水。每种灾害都对应两个问题，且互不混淆。我们利用 HMAGLOFDB 数据库中 589 起有记录的溃决事件和数千起滑坡记录，将每起事件与相似但未发生灾害的地点进行匹配，并在空间交叉验证下将所有模型与一个强有力的简单基准进行对比。该验证过程剔除了完整的地图区块，确保模型不会通过识别训练区域的邻域而侥幸成功。

Antecedent weather times the trigger at ROC 0.73 for big bursts, 0.83 for landslides, and 0.82 for small floods. Terrain ranks susceptibility only in part: scored naively it appears near 0.9, largely because catalogued failures cluster in wetter ranges; matched against comparable nearby sites the honest figures are 0.76, 0.71, and 0.54 (no better than chance). The burst signal holds within single regions, reaching 0.89 in Nepal alone.

前期气象数据对触发时间的预测 ROC 值分别为：大型溃决 0.73，滑坡 0.83，小型洪水 0.82。地形因素仅能部分反映易感性：如果进行简单评分，其准确率接近 0.9，这主要是因为记录在案的灾害多集中在降水较多的区域；但若与附近可比地点进行匹配，其实际表现分别为 0.76、0.71 和 0.54（不优于随机猜测）。溃决信号在单一区域内表现稳健，在尼泊尔境内达到了 0.89。

Five deep-learning models do not decisively beat a simple gradient-boosted baseline. Three score marginally higher on landslides, a hint too small to confirm. For the lake hazards the baseline wins outright, reproduced by a three-rule decision tree on ruggedness and monsoon rainfall. We close with a ranked Nepal watchlist, a prioritisation aid, not a prediction, and note where free data reaches its limits.

五个深度学习模型并未能显著超越简单的梯度提升基准模型。其中三个模型在滑坡预测上得分略高，但差异微小，不足以证实其优越性。对于冰湖灾害，基准模型表现完胜，且可以通过基于地形崎岖度和季风降雨量的三规则决策树进行复现。最后，我们提供了一份尼泊尔灾害风险排名观察名单，这是一种优先级排序辅助工具而非预测，并指出了免费数据在应用中的局限性。