arXiv cs.AI· Saleh Sakib Ahmed, Rashed Uz Zzaman, Saifur Rahman Jony, Faizur Rahman Himel, Afroza Sharmin, A. H. M. Khalequr Rahman, M. Sohel Rahman, Sara Nowreen·· 11 小时前AI 评分34
教师-学生框架重建孟加拉国地下水：时空可泛化模型揭示水位与补给同步下降
Unraveling Groundwater Stress: A Model Generalizable Across Space and Time Reveals Co-Declining Water Tables and Recharge Across Bangladesh
AI 导读
研究团队提出 Teacher-Student 框架，Teacher 从稀疏年度原位最深（R2 = 0.86）与最浅（R2 = 0.96）水位观测中学习并生成密集空间模式，Student 再借助位置特征将 25-km GLDAS 地下水储量数据迁移为 2-km 深度图，2003-2022 年 R2 = 0.93，留一年与留一区泛化 R2 分别为 0.93 和 0.70。
正文 · 原文
Abstract:Is Bangladesh replenishing the groundwater it depends on? Answering this question remains difficult in Bangladesh and worldwide because sparse in-situ measurements limit observational capabilities, while existing machine-learning approaches struggle to generalize across time and space. To address this bottleneck, we develop a Teacher-Student framework in which a Teacher accurately learns from sparse annual in-situ minimum (R2 = 0.86) and maximum (R2 = 0.96) depth observations to generate dense spatial patterns, and a Student transfers these patterns from time-varying 25-km GLDAS groundwater storage to high-resolution (2-km) depth maps using location-specific features. The Student achieves R2 = 0.93 over 2003-2022 and generalizes across unseen years (Leave-One-Year-Out R2 = 0.93) and locations (Leave-One-District-Out R2 = 0.70), enabling reconstruction without contemporary in-situ measurements. The reconstruction reveals widespread water-table deepening and a national decline in groundwater recharge of 1.10 mm/yr (p < 0.001). Autocorrelation-corrected analysis identifies statistically significant recharge declines across 55.6% of Bangladesh, compared with significant increases across only 4.9%. This imbalance suggests that pumping-induced recharge enhancement, as proposed by the Bengal Water Machine hypothesis, remains localized rather than widespread across Bangladesh. Together, these findings reveal widespread weakening of groundwater replenishment and provide a scalable framework for monitoring groundwater dynamics in data-sparse aquifers globally.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2503.22771 [cs.LG] |
| (or arXiv:2503.22771v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2503.22771 arXiv-issued DOI via DataCite |
Submission history
From: M. Sohel Rahman [view email]
[v1]
Fri, 28 Mar 2025 04:56:01 UTC (72,695 KB)
[v2]
Wed, 4 Nov 2026 03:08:02 UTC (66,494 KB)
来源：arXiv cs.AI · arxiv.org