Explainable artificial intelligence for groundwater quality prediction and hydrochemical interpretation

作者
G. Shyamala,Prakhash Neelamegam,Belin Jude Alphonse,B. Hemalatha,Missgna Addisalem Berhe,K. Rajesh Kumar
出处
期刊:Scientific Reports [Nature Portfolio]
卷期号:16 (1) 被引量:2
标识
DOI:10.1038/s41598-026-62033-0
摘要

Over the past decades, groundwater quality has declined significantly due to rapid urbanization, excessive fertilizer usage, and climate-driven hydrogeochemical changes. Accurate prediction and interpretation of groundwater quality therefore require advanced data-driven approaches integrated with domain knowledge. This study proposes an interpretable hybrid artificial intelligence framework for groundwater quality prediction and analysis using explainable artificial intelligence (XAI) and advanced machine learning algorithms. A total of 135 groundwater samples were collected from Tamil Nadu, India and analysed for 16 physicochemical parameters. The dataset was pre-processed through data cleaning, feature scaling, and outlier detection. Several machine learning models, including XGBoost, Random Forest, LightGBM, and CatBoost, were optimized using Optuna-based hyperparameter tuning and integrated through a stacked ensemble framework. The meta-learner achieved the best predictive performance (R 2 = 0.938, RMSE = 0.237, MAE = 0.184). Water Quality Index analysis identified ammonia (NH₃), iron (Fe), and chromium (Cr) as dominant contaminants. Model interpretability using SHAP, LIME, and permutation importance revealed the buffering role of hydrochemical ions such as HCO₃⁻ and Ca 2 ⁺, while spatial AI mapping indicated localized industrial contamination. The proposed framework improves predictive reliability while providing interpretable insights to support sustainable groundwater management.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
Jun的应助被科研通管家采纳,获得10
1秒前
molihuakai的应助被科研通管家采纳,获得10
1秒前
酷波er的应助被科研通管家采纳,获得10
1秒前
传奇3的应助被科研通管家采纳,获得10
1秒前
syvshc的应助被科研通管家采纳,获得10
2秒前
烟花的应助被科研通管家采纳,获得10
2秒前
卜凡完成签到,获得积分10
2秒前
上官若男的应助被科研通管家采纳,获得10
2秒前
研友_VZG7GZ的应助被科研通管家采纳,获得30
2秒前
orixero的应助被科研通管家采纳,获得10
2秒前
2秒前
zhonglv7的应助被科研通管家采纳,获得10
2秒前
深情安青的应助被科研通管家采纳,获得10
3秒前
华仔的应助被洋洋洋采纳,获得10
3秒前
香蕉觅云的应助被科研通管家采纳,获得10
3秒前
3秒前
传奇3的应助被科研通管家采纳,获得10
3秒前
打打的应助被科研通管家采纳,获得10
3秒前
3秒前
3秒前
3秒前
李爱国的应助被科研通管家采纳,获得10
3秒前
李爱国的应助被科研通管家采纳,获得10
3秒前
4秒前
科研通AI6.3的应助被emm采纳,获得10
4秒前
CipherSage的应助被科研通管家采纳,获得10
4秒前
4秒前
zyw0532完成签到,获得积分10
4秒前
Alfred完成签到,获得积分10
4秒前
5秒前
Hello的应助被123456采纳,获得10
5秒前
ldxghh发布了新的文献求助10
5秒前
李同学完成签到,获得积分10
6秒前
洁净的石头完成签到 ,获得积分10
6秒前
6秒前
小梅超顺利完成签到 ,获得积分10
7秒前
bkagyin的应助被不爱胡椒采纳,获得10
7秒前
鲁啊鲁完成签到 ,获得积分10
7秒前
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8182014
求助须知:如何正确求助?哪些是违规求助? 9571728
关于积分的说明 21819478
捐赠科研通 7778441
什么是DOI,文献DOI怎么找? 3433580
关于科研通互助平台的介绍 2557781
邀请新用户注册赠送积分活动 2479640