Novel machine learning algorithms to predict the groundwater vulnerability index to nitrate pollution at two levels of modeling

Integrated approach to understand the multiple natural and anthropogenic stresses on intensively irrigated coastal aquifer in the Mediterranean region

Understanding the major factors influencing groundwater chemistry and its evolution in irrigation areas is crucial for efficient irrigation management. Major ions and isotopes (δD-H2O together with δ18O-H2O) were used to identify the natural and anthropogenic factors contributing to groundwater salinization in the shallow aquifer of the Wadi Guenniche Plain (WGP) in the Mediterranean region of Tunisia. A comprehensive geochemical investigation of groundwater was conducted during both the low irrigation season (L-IR) and the high irrigation season (H-IR). The results show that the variation range and average concentrations of almost all the ions in both the L-IR and H-IR seasons are high. The groundwater in both seasons is characterized by high electrical conductivity and CaMgCl/SO4 and NaCl types. The dissolution of halite and gypsum, the precipitation of calcite and dolomite, and Na-Ca exchange are the main chemical reactions in the geochemical evolution of groundwater in the Wadi Guenniche Shallow Aquifer (WGSA). Stable isotopes of hydrogen and oxygen (δ18O-H2O and δD-H2O) indicate that groundwater in WGSA originated from local precipitation. In the H-IR season, the δ18O-H2O and δD-H2O values indicate that the groundwater experienced noticeable evaporation. The enriched isotopic signatures reveal that the WGSA's groundwater was influenced by irrigation return flow and seawater intrusion. The proportions of mixing with seawater were found to vary between 0.12% and 5.95%, and between 0.13% and 8.42% during the L-IR and H-IR seasons, respectively. Irrigation return flow and the associated evaporation increase the dissolved solids content in groundwater during the irrigation season. The long-term human activities (fertilization, irrigation, and septic waste infiltration) are the main drives of the high nitrate-N concentrations in groundwater. In coastal irrigation areas suffering from water scarcity, these results can help planners and policy makers understand the complexities of groundwater salinization to enable more sustainable management and development.

Interpretable machine learning for predicting the fate and transport of pentachlorophenol in groundwater

Pentachlorophenol (PCP) is a commonly found recalcitrant and toxic groundwater contaminant that resists degradation, bioaccumulates, and has a potential for long-range environmental transport. Taking proper actions to deal with the pollutant accounting for the life cycle consequences requires a better understanding of its behavior in the subsurface. We recognize the huge potential for enhancing decision-making at contaminated groundwater sites with the arrival of machine learning (ML) techniques in environmental applications. We used ML to enhance the understanding of the dynamics of PCP transport properties in the subsurface, and to determine key hydrochemical and hydrogeological drivers affecting its transport and fate. We demonstrate how this complementary knowledge, provided by data-driven methods, may enable a more targeted planning of monitoring and remediation at two highly contaminated Swedish groundwater sites, where the method was validated. We evaluated 6 interpretable ML methods, 3 linear regressors and 3 non-linear (i.e., tree-based) regressors, to predict PCP concentration in the groundwater. The modeling results indicate that simple linear ML models were found to be useful in the prediction of observations for datasets without any missing values, while tree-based regressors were more suitable for datasets containing missing values. Considering that missing values are common in datasets collected during contaminated site investigations, this could be of significant importance for contaminated site planners and managers, ultimately reducing site investigation and monitoring costs. Furthermore, we interpreted the proposed models using the SHAP (SHapley Additive exPlanations) approach to decipher the importance of different drivers in the prediction and simulation of critical hydrogeochemical variables. Among these, sum of chlorophenols is of highest significance in the analyses. Setting that aside from the model, tetra chlorophenols, dissolved organic carbon, and conductivity found to be of highest importance. Accordingly, ML methods could potentially be used to improve the understanding of groundwater contamination transport dynamics, filling gaps in knowledge that remain when using more sophisticated deterministic modeling approaches.

Innovative approach for predicting daily reference evapotranspiration using improved shallow and deep learning models in a coastal region: A comparative study

Accurate and reliable estimation of Reference Evapotranspiration (ETo) is crucial for water resources management, hydrological processes, and agricultural production. The FAO-56 Penman-Monteith (FAO-56PM) approach is recommended as the standard model for ETo estimation; nevertheless, the absence of comprehensive meteorological variables at many global locations frequently restricts its implementation. This study compares shallow learning (SL) and deep learning (DL) models for estimating daily ETo against the FAO-56PM approach based on various statistic metrics and graphic tool over a coastal Red Sea region, Sudan. A novel approach of the SL model, the Catboost Regressor (CBR) and three DL models: 1D-Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) were adopted and coupled with a semi-supervised pseudo-labeling (PL) technique. Six scenarios were developed regarding different input combinations of meteorological variables such as air temperature (Tmin, Tmax, and Tmean), wind speed (U2), relative humidity (RH), sunshine hours duration (SSH), net radiation (Rn), and saturation vapor pressure deficit (es-ea). The results showed that the PL technique reduced the systematic error of SL and DL models during training for all the scenarios. The input combination of Tmin, Tmax, Tmean, and RH reflected higher performance than other combinations for all employed models. The CBR-PL model demonstrated good generalization abilities to predict daily ETo and was the overall superior model in the testing phase according to prediction accuracy, stability analysis, and less computation cost compared to DL models. Thus, the relatively simple CBR-PL model is highly recommended as a promising tool for predicting daily ETo in coastal regions worldwide which have limited climate data.

An innovative approach for predicting groundwater TDS using optimized ensemble machine learning algorithms at two levels of modeling strategy

Groundwater salinization in coastal aquifers is a major socioeconomic challenge in Oman and many other regions worldwide due to several anthropogenic activities and natural drivers. Therefore, assessing the salinization of groundwater resources is crucial to ensure the protection of water resources and sustainable management. The aim of this study is to apply a novel approach using predictive optimized ensemble trees-based (ETB) machine learning models, namely Catboost regression (CBR), Extra trees regression (ETR), and Bagging regression (BA), at two levels of modeling strategy for predicting groundwater TDS as an indicator for seawater intrusion in a coastal aquifer, Oman. At level 1, ETR and CBR models were used as base models or inputs for BA in level 2. The results show that the models at level 1 (i.e., ETR and CBR) yielded satisfactory results using a limited number of inputs (Cl, K, and Sr) from a few sets of 40 groundwater wells. The BA model at level 2 improved the overall performance of the modeling by extracting more information from ETR and CBR models at level 1 models. At level 2, the BA model achieved a significant improvement in accuracy (MSE = 0.0002, RSR = 0.062, R2 = 0.995 and NSE = 0.996) compared to each individual model of ETR (MSE = 0.0007, RSR = 0.245, R2 = 0.98 and NSE = 0.94), and CBR (MSE = 0.0035, RSR = 0.258, R2 = 0.933 and NSE = 0.934) at level 1 models in the testing dataset. BA model at level 2 outperformed all models regarding predictive accuracy, best generalization of new data, and matching the locations of the polluted and unpolluted wells. Our approach predicts groundwater TDS with high accuracy and thus provides early warnings of water quality deterioration along coastal aquifers which will improve water resources sustainability.