arXiv cs.AI· Emam Hossain, Muhammad Hasan Ferdous, Devon Dunmire, Aneesh Subramanian, Md Osman Gani·· 10 小时前AI 评分18
RIC-TSC：面向分布偏移下格陵兰冰上湖演化的因果时间序列建模
Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift
AI 导读
研究者提出 RIC-TSC 框架，将滞后感知的因果发现嵌入序列建模，用于格陵兰冰上湖演化的时间序列分类。该框架利用 Sentinel-1、Sentinel-2、Landsat-8 与 CARRA 气象数据，通过 J-PCMCI+ 识别区域特定与不变预测因子，在 2018-2019 两个融化季共 1000 个手工标注湖泊的平衡基准上，分布外评估准确率比相关性基线最高提升 12.59%。
正文 · 原文
Abstract:Causal modeling offers a principled foundation for uncovering stable, invariant relationships in time-series data, thereby improving robustness and generalization under distribution shifts. Yet its potential is underutilized in spatiotemporal Earth observation, where models often depend on purely correlational features that fail to transfer across heterogeneous domains. We propose RIC-TSC, a regionally-informed causal time-series classification framework that embeds lag-aware causal discovery directly into sequence modeling, enabling both predictive accuracy and scientific interpretability. Using multi-modal satellite and reanalysis data-including Sentinel-1 microwave backscatter, Sentinel-2 and Landsat-8 optical reflectance, and CARRA meteorological variables-we leverage Joint PCMCI+ (J-PCMCI+) to identify region-specific and invariant predictors of supraglacial lake evolution in Greenland. Causal graphs are estimated globally and per basin, with validated predictors and their time lags supplied to lightweight classifiers. On a balanced benchmark of 1000 manually labeled lakes from two contrasting melt seasons (2018-2019), causal models achieve up to 12.59% higher accuracy than correlation-based baselines under out-of-distribution evaluation. These results show that causal discovery is not only a means of feature selection but also a pathway to generalizable and mechanistically grounded models of dynamic Earth surface processes.
| Comments: | Accepted as full paper in ICMLA 2025 (Special Session 1: Deep Learning and Applications) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.15265 [cs.LG] |
| (or arXiv:2510.15265v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.15265 arXiv-issued DOI via DataCite |
Submission history
From: Emam Hossain [view email]
[v1]
Fri, 17 Oct 2025 03:06:08 UTC (1,944 KB)
来源：arXiv cs.AI · arxiv.org