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.

A critical review of environmental and public health impacts from the activities of evaporation ponds.

Evaporation ponds (EVPs) are among the most cost-effective, and simple wastewater treatment technologies used in many regions/countries with high solar radiation levels. However, its operational limitations, which include the overflow of wastewater, leakages via liners, and large surface area of the EVP that is exposed to atmosphere, creates a negative feedback to the environment. Therefore, the main aim of this review study of more than a hundred works published a little all over the continents is to provide a summary of various contaminations that are associated with EVPs activities through different environmental compartments. In addition, the impacts of EVP on fauna, human health including the current on-site sustainable mitigation strategies were also reviewed. The first conclusion from this study shows that the most commonly contaminants released into surface waters, groundwater, soil and sediments were heavy metals, pesticides, herbicides, selenium, including several major anions and cations. Non-methane hydrocarbons (NMHCs), volatile organic compounds (VOCs), and particulate matters (PMs) were the main air pollutants emitted from the surfaces of an EVP. Limited data is available about the emissions of atmospheric greenhouse gas (GHGs) especially carbon dioxide (CO2) and methane (CH4) from EVP surfaces. Migratory birds and aquatic organisms are the most vulnerable fauna as EVP wastewaters can cause obstruction of movements, affect diversity, and causes mortalities following the exposure to the toxic wastewater. The study revealed limited data about the potential health risk associated with occupational and environmental exposure to radiological hazards and contaminated drinking water from EVP activities. On-site EVP treatment strategies using bioremediation and electrochemical treatment technologies have shown to be a promising sustainable mitigation approach. Knowledge gaps in areas of GHGs monitoring/modeling, pollution exposure estimation and health risk assessments are urgently required to gain deeper understanding about the impact of EVP activities, and incorporate them into future EVP designs.

Optimal Location of Wells for Storage and Recovery of Surplus Desalinated Water in Coastal Aquifers.

Storage of water in aquifers using injection wells is an efficient way for utilizing excess desalinated water in arid regions. In this investigation we estimate the benefits of optimally recharging seasonal surplus desalinated water into a strategic coastal aquifer already benefitting from natural recharge of flash-floods water by a recharge dam. Since, usually the buyers of desalinated water commit to purchase surplus desalinated water under take-or-pay contracts, any attempt in utilizing the paid water is beneficial. Coastal cities are observing an increased urbanization leaving limited space for aquifer recharge infrastructure. In order to determine the optimal location of wells and maximize the use of surplus desalinated water available in winter period, a decision tool combining a numerical groundwater flow simulation model (MODFLOW) with an optimization model is developed. The results of this study show that increasing the number of wells from the existing 45 wells to 173 would allow storing 31.4 million cubic meter per year of excess desalinated water into the aquifer that can be used during later during summer months. The net benefit would reach US$55 million/year while the cost of drilling the new wells is US$5.11 million.

Estimating Groundwater Mounding in Sloping Aquifers for Managed Aquifer Recharge.

Design of managed aquifer recharge (MAR) for augmentation of groundwater resources often lacks detailed data, and simple diagnostic tools for evaluation of the water table in a broad range of parameters are needed. In many large-scale MAR projects, the effect of a regional aquifer base dip cannot be ignored due to the scale of recharge sources (e.g., wadis, streams, reservoirs). However, Hantush's (1967) solution for a horizontal aquifer base is commonly used. To address sloping aquifers, a new closed-form analytical solution for water table mound accounts for the geometry and orientation of recharge sources at the land surface with respect to the aquifer base dip. The solution, based on the Dupiuit-Forchheimer approximation, Green's function method, and coordinate transformations is convenient for computing. This solution reveals important MAR traits in variance with Hantush's solution: mounding is limited in time and space; elevation of the mound is strongly affected by the dip angle; and the peak of the mound moves over time. These findings have important practical implications for assessment of various MAR scenarios, including waterlogging potential and determining proper rates of recharge. Computations are illustrated for several characteristic MAR settings.