Liang Yuanyi, Zhang Xingjun, Gan Lin, Chen Si, Zhao Shandao, Ding Jihui, Kang Wulue, Yang Han
Observation and Research Station of Ecological Restoration for Chongqing Typical Mining Areas, Ministry of Natural Resources (Chongqing Institute of Geology and Mineral Resources) Chongqing, 401120, China.
Chongqing Institute of Geological Environment Monitoring, Chongqing, 401122, China.
Heliyon. 2024 Mar 13;10(6):e27867. doi: 10.1016/j.heliyon.2024.e27867. eCollection 2024 Mar 30.
Groundwater resources is not only important essential water resources but also imperative connectors within the intricate framework of the ecological environment. High nitrate concentrations in groundwater can exerting adverse impacts on human health. It is imperative to accurately delineate the distribution characteristics of groundwater nitrate concentrations. Four different machine learning models (Gradient Boosting Regression (GB), Random Forest Regression (RF), Extreme Gradient Boosting Regression (XG) and Adaptive Boosting Regression (AD)) which combine spatial environmental data and different radius contributing area was developed to predict the distribution of nitrate concentration in groundwater. The models use 595 groundwater samples and included topography, remote sensing, hydrogeological and hydrological, climate, nitrate input, and socio-economic predictor. Gradient Boosting Regression model outperforms the other models (R2 = 0.627, MAE = 0.529, RMSE = 0.705, PICP = 0.924 for test dataset) under 500 m radius contributing area. A high-resolution (1 km) groundwater nitrate concentration distribution map reveal in the majority of the study area, groundwater nitrate concentrations are below 1 mg/L and high nitrate concentration (>10 mg/L) proportion in southeast, northeast and central main urban area karst valley regions is 1.89%, 0.91%, and 0.38% respectively. In study area, hydrogeological conditions, soil parameters, nitrogen input factors, and percentage of arable land are among the most influential explanatory factors. This work, serving as the inaugural application of utilizing effective spatial methods for predicting groundwater nitrate concentrations in Chongqing city, furnish decision-making support for the prevention and control of groundwater pollution, particularly in areas primarily dependent on groundwater for water supply and holds profound significance as a milestone achievement.
地下水资源不仅是重要的基本水资源，也是生态环境复杂框架中不可或缺的连接要素。地下水中的高硝酸盐浓度会对人类健康产生不利影响。准确描绘地下水中硝酸盐浓度的分布特征至关重要。开发了四种不同的机器学习模型（梯度提升回归（GB）、随机森林回归（RF）、极端梯度提升回归（XG）和自适应提升回归（AD）），这些模型结合了空间环境数据和不同半径的贡献面积，以预测地下水中硝酸盐浓度的分布。这些模型使用了595个地下水样本，并纳入了地形、遥感、水文地质和水文、气候、硝酸盐输入以及社会经济预测变量。在500米半径贡献面积下，梯度提升回归模型优于其他模型（测试数据集的R2 = 0.627，MAE = 0.529，RMSE = 0.705，PICP = 0.924）。一幅高分辨率（1公里）的地下水中硝酸盐浓度分布图显示，在研究区域的大部分地区，地下水中硝酸盐浓度低于1毫克/升，东南部、东北部和中部主要城市岩溶谷地区的高硝酸盐浓度（>10毫克/升）比例分别为1.89%、0.91%和0.38%。在研究区域，水文地质条件、土壤参数、氮输入因素和耕地比例是最具影响力的解释因素。这项工作作为利用有效空间方法预测重庆市地下水中硝酸盐浓度的首次应用，为地下水污染的预防和控制提供了决策支持，特别是在主要依赖地下水供水的地区，作为一项具有里程碑意义的成就具有深远意义。
