arXiv：cs.LG（机器学习，全量分类）· Emam Hossain, Md Osman Gani·· 15 小时前AI 评分31
格陵兰冰盖冰上湖结局可在融季结束前数月预判
Supraglacial Lake Fate Is Knowable Long Before the Season Ends
AI 导读
研究通过将卫星分类器输入截断在5月1日至12月31日的14个时间点并分别重训，测得格陵兰冰盖冰上湖四种结局的F1达标最早时点：快速排水7月15日、缓慢排水8月1日，分别比全季管线最早可算日期提前92天和75天，被掩埋与再冻结分别提前44天和30天。该顺序在另外五个学习器中基本保持，逐日特征仅读取当日及之前数据，代价最多1.3个百分点。
正文
Abstract:A supraglacial lake on the Greenland Ice Sheet ends its melt season in one of four ways: it drains rapidly through a hydrofracture, drains slowly across the surface, refreezes in place, or is buried by late-season snowfall. Which one occurs decides whether the meltwater reaches the ice bed. Satellite classifiers recover the outcome accurately but only after the season closes, and how much of a season each outcome actually requires has never been measured. We measure it directly: holding the representation and the classifier fixed, we truncate the input at 14 cutoffs from May 1 to December 31, retrain at each, and record the earliest cutoff at which each outcome's per-class F1 reaches a fixed target. The outcomes resolve in a consistent order, two of them months early: rapid drainage by July 15 and slow drainage by August 1, respectively 92 and 75 days ahead of the earliest date a full-season pipeline can be computed at all, with buried and refreeze following at 44 and 30 days. Five further learners, from a majority-class floor and 54 summary statistics to a trigger-based early classifier, leave the ordering largely intact: the three that produce a per-class trajectory reproduce it in five of six cases despite end-of-season accuracies differing by up to 18 percentage points, and it survives leave-one-basin-out evaluation, though not a move to machine-labeled lakes in an unseen season. Every feature we compute at day t reads only days up to t, at a cost of at most 1.3 percentage points. A monitoring system should therefore not have one release date: rapid drainage can be flagged on July 15, three months before a full-season pipeline can be computed at all.
| Comments: | Accepted at PolDS '26, the 2nd ACM SIGSPATIAL International Workshop on Polar Data Science. 14 pages, 6 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.30113 [cs.LG] |
| (or arXiv:2608.30113v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2608.30113 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3849740.3856203
DOI(s) linking to related resources |
Submission history
From: Emam Hossain [view email]
[v1]
Mon, 31 Aug 2026 00:58:47 UTC (348 KB)
[v2]
Thu, 1 Oct 2026 00:53:10 UTC (328 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org