Deep learning time-series modeling for assessing land subsidence under reduced groundwater use

Abstract

Intensive groundwater extraction and a severe 2021 drought have worsened land subsidence in Taiwan’s Choshui Delta, highlighting the need for effective predictive modeling to guide mitigation. In this study, we develop a machine learning framework for subsidence analysis using electricity consumption data from pumping wells as a proxy for groundwater extraction. A long short-term memory (LSTM) neural network is trained to reconstruct missing subsidence records and forecast subsidence trends, while an artificial neural network links well electricity usage to groundwater level fluctuations. Using these tools, we identify groundwater-level decline from pumping as a key driver of subsidence. The LSTM model achieves high accuracy in reproducing historical subsidence and provides reliable predictions of subsidence behavior. Scenario simulations indicate that reducing groundwater pumping, simulated by lowering well electricity use, allows groundwater levels to recover and significantly slows the rate of land subsidence. To assess the effectiveness of pumping reduction strategies, two artificial scenarios were simulated. The average subsidence rate at the Xiutan Elementary School multi-layer compression monitoring well (MLCW) decreased from 2.23 cm/year (observed) to 1.94 cm/year in first scenario and 1.34 cm/year in second scenario, demonstrating the potential of groundwater control in mitigating land subsidence. These findings underscore the importance of integrating groundwater-use indicators into subsidence models and demonstrate that curtailing groundwater extraction can effectively mitigate land subsidence in vulnerable deltaic regions.

https://doi.org/10.1038/s41598-025-16454-y

國立臺灣海洋大學團隊以AI深度學習技術成功預測地層下陷

🌏 以AI預測地層下陷，開創地質防災新模式

台灣中部濁水溪沖積扇長期面臨地下水超抽與地層下陷問題。國立臺灣海洋大學研究團隊結合人工智慧與地質監測，開發出深度學習時間序列模型（Long Short-Term Memory, LSTM），能高精度預測地層下陷趨勢，並量化減少地下水使用對地層穩定的正面影響。
研究成果已發表於國際頂尖期刊 Scientific Reports（Nature出版集團），展現台灣在環境監測與AI應用領域的科研實力。

📊 核心研究成果

1. 以電力數據作為地下水抽取指標
   團隊首創將農業抽水的「電力使用量」作為地下水開採代理變數，透過人工神經網路（ANN）建立電力—地下水位之關聯，再輸入LSTM進行時間序列預測。分析結果顯示，電力用量與地層下陷速率相關性高達 0.91，有效揭示人為抽水行為對地質變形的影響。
2. AI模型補全缺漏資料，預測準確率高達99%
   模型能成功重建2012–2014年間缺失的監測紀錄，訓練階段決定係數達 R² = 0.99，測試階段仍維持 R² = 0.69。此結果顯示AI方法具有高度泛化能力，足以用於實際地層監測與長期預警系統。
3. 模擬減抽水政策顯示顯著改善效果
   1. 當抽水量減少 8%（相當於10%稻田改種玉米），下陷率由 2.23 公分/年降至 1.94 公分/年。
   1. 當抽水量減少 17% 時，下陷率再降至 1.34 公分/年。
      結果顯示：減抽水對地層回彈具明顯效果，為制定水資源管理政策的重要量化依據。

💧 政策應用與社會影響

研究顯示地層下陷與地下水位下降呈現強烈非線性關係，當地下水位下降超過6公尺即可能引發不可逆壓縮。
此AI模型可協助政府建立精準的地層下陷監測與預警系統，支援以下政策方向：

• 推動農業用水調度與作物轉型；
• 制定分區抽水管制與地下水補注計畫；
• 發展AI導向的智慧地質防災決策平台。

研究團隊指出：「AI不僅能預測下陷，更能幫助政府制定具量化依據的永續水資源政策。」

📚 研究出處

Chih-Yu Liu, Cheng-Yu Ku*, Chuen-Fa Ni (2025), ” Deep learning time-series modeling for assessing land subsidence under reduced groundwater use”, Nature, Scientific Reports, 15, Article number: 30901 (SCIE, IF 3.9, Q1, 25/135 (18.5% JIF) in MULTIDISCIPLINARY SCIENCES, JCR 2024)

https://doi.org/10.1038/s41598-025-16454-y