Hybrid WT-CNN-GRU-based model for the estimation of reservoir water quality variables considering spatio-temporal features.

Water quality indicators (WQIs), such as chlorophyll-a (Chl-a) and dissolved oxygen (DO), are crucial for understanding and assessing the health of aquatic ecosystems. Precise prediction of these indicators is fundamental for the efficient administration of rivers, lakes, and reservoirs. This research utilized two unique DL algorithms-namely, convolutional neural network (CNNs) and gated recurrent units (GRUs)-alongside their amalgamation, CNN-GRU, to precisely gauge the concentration of these indicators within a reservoir. Moreover, to optimize the outcomes of the developed hybrid model, we considered the impact of a decomposition technique, specifically the wavelet transform (WT). In addition to these efforts, we created two distinct machine learning (ML) algorithms-namely, random forest (RF) and support vector regression (SVR)-to demonstrate the superior performance of deep learning algorithms over individual ML ones. We initially gathered WQIs from diverse locations and varying depths within the reservoir using an AAQ-RINKO device in the study area to achieve this. It is important to highlight that, despite utilizing diverse data-driven models in water quality estimation, a significant gap persists in the existing literature regarding implementing a comprehensive hybrid algorithm. This algorithm integrates the wavelet transform, convolutional neural network (CNN), and gated recurrent unit (GRU) methodologies to estimate WQIs accurately within a spatiotemporal framework. Subsequently, the effectiveness of the models that were developed was assessed utilizing various statistical metrics, encompassing the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE) throughout both the training and testing phases. The findings demonstrated that the WT-CNN-GRU model exhibited better performance in comparison with the other algorithms by 13% (SVR), 13% (RF), 9% (CNN), and 8% (GRU) when R-squared and DO were considered as evaluation indices and WQIs, respectively.

Robust clustering-based hybrid technique enabling reliable reservoir water quality prediction with uncertainty quantification and spatial analysis.

Machine learning methodology has recently been considered a smart and reliable way to monitor water quality parameters in aquatic environments like reservoirs and lakes. This study employs both individual and hybrid-based techniques to boost the accuracy of dissolved oxygen (DO) and chlorophyll-a (Chl-a) predictions in the Wadi Dayqah Dam located in Oman. At first, an AAQ-RINKO device (CTD+ sensor) was used to collect water quality parameters from different locations and varying depths in the reservoir. Second, the dataset is segmented into homogeneous clusters based on DO and Chl-a parameters by leveraging an optimized K-means algorithm, facilitating precise estimations. Third, ten sophisticated variational-individual data-driven models, namely generalized regression neural network (GRNN), random forest (RF), gaussian process regression (GPR), decision tree (DT), least-squares boosting (LSB), bayesian ridge (BR), support vector regression (SVR), K-nearest neighbors (KNN), multilayer perceptron (MLP), and group method of data handling (GMDH) are employed to estimate DO and Chl-a concentrations. Fourth, to improve prediction accuracy, bayesian model averaging (BMA), entropy weighted (EW), and a new enhanced clustering-based hybrid technique called Entropy-ORNESS are employed to combine model outputs. The Entropy-ORNESS method incorporates a Genetic Algorithm (GA) to determine optimal weights and then combine them with EW weights. Finally, the inclusion of bootstrapping techniques introduces a stochastic assessment of model uncertainty, resulting in a robust estimator model. In the validation phase, the Entropy-ORNESS technique outperforms the independent models among the three fusion-based methods, yielding R2 values of 0.92 and 0.89 for DO and Chl-a clusters, respectively. The proposed hybrid-based methodology demonstrates reduced uncertainty compared to single data-driven models and two combination frameworks, with uncertainty levels of 0.24% and 1.16% for cluster 1 of DO and cluster 2 of Chl-a parameters. As a highlight point, the spatial analysis of DO and Chl-a concentrations exhibit similar pattern variations across varying depths of the dam according to the comparison of field measurements with the best hybrid technique, in which DO concentration values notably decrease during warmer seasons. These findings collectively underscore the potential of the upgraded weighted-based hybrid approach to provide more accurate estimations of DO and Chl-a concentrations in dynamic aquatic environments.

Design of a high-coverage ground-based CO2 monitoring layout using a novel information theory-based optimization model.

Over the past decade, monitoring of the carbon cycle has become a major concern accented by the severe impacts of global warming. Here, we develop an information theory-based optimization model using the NSGA-II algorithm that determines an optimum ground-based CO2 monitoring layout with the highest spatial coverage using a finite number of stations. The value of information (VOI) concept is used to assess the efficacy of the monitoring stations given their construction cost. In conjunction with VOI, the entropy theory-in terms of transinformation-is adopted to determine the redundant (overlapping) information rendered by the selected monitoring stations. The developed model is used to determine a ground-based CO2 monitoring layout for Iran, the eighth-ranked country emitting CO2 worldwide. An NSGA-II optimization model provides a tradeoff curve given the objectives of (1) minimizing the size of monitoring network; (2) maximizing VOI, i.e., spatial coverage; and (3) minimizing transinformation, i.e., overlapping information. Borda count method is then employed to select the most appropriate compromise monitoring layout from the Pareto-front solutions given regional priorities and concerns.

A downscaling-disaggregation approach for developing IDF curves in arid regions.

Over the past decades, urbanization in Arabian Gulf region expands in flood-prone areas at an unprecedented rate. Chronic water stress and potential changes in extreme rainfall attributed to climate change therefore pose unique challenges in planning and designing water management infrastructures. The objective of this study is to develop a framework to integrate climate change variations into intensity-duration-frequency (IDF) curves in Oman. A two-stage downscaling-disaggregation method was applied with rainfall at Tawi-Atair station in Dhofar region. Potential variations of extreme rainfall in future were examined by eight scenarios composed with two general circulation models (GCMs), two representative concentration pathways (RCPs), and two future periods (2040-2059 and 2080-2099). A stochastic weather generator model was used to downscale rainfall output from GCM grid scale to local scale. Downscaled daily data were then disaggregated to hourly and 5-min series by using K-nearest neighbor (K-NN) technique. Annual maximum rainfall extracted from eight future scenarios and also from present climate (baseline period) was used to develop rainfall intensity-frequency relationships for eight durations range from 5 min to 24 h. Results of the K-NN analysis indicate that the optimum window size of 57 days and 181 h is suitable for hourly and 5-min disaggregation models, respectively. Results also predict that the effects of climate change on the rainfall intensity will be more significant on storms with shorter durations and higher return periods. Moving towards the end of the twenty-first century, the return period of extreme rainfall events is likely to decrease due to intensified rainfall events.

Assessment of future variability in extreme precipitation and the potential effects on the wadi flow regime.

The objective of this study is to investigate how the magnitude and occurrence of extreme precipitation events are affected by climate change and to predict the subsequent impacts on the wadi flow regime in the Al-Khod catchment area, Muscat, Oman. The tank model, a lumped-parameter rainfall-runoff model, was used to simulate the wadi flow. Precipitation extremes and their potential future changes were predicted using six-member ensembles of general circulation models (GCMs) from the Coupled Model Intercomparison Project Phase 5 (CMIP5). Yearly maxima of the daily precipitation and wadi flow for varying return periods were compared for observed and projected data by fitting the generalized extreme value (GEV) distribution function. Flow duration curves (FDC) were developed and compared for the observed and projected wadi flows. The results indicate that extreme precipitation events consistently increase by the middle of the twenty-first century for all return periods (49-52%), but changes may become more profound by the end of the twenty-first century (81-101%). Consequently, the relative change in extreme wadi flow is greater than twofolds for all of the return periods in the late twenty-first century compared to the relative changes that occur in the mid-century period. Precipitation analysis further suggests that greater than 50% of the precipitation may be associated with extreme events in the future. The FDC analysis reveals that changes in low-to-moderate flows (Q60-Q90) may not be statistically significant, whereas increases in high flows (Q5) are statistically robust (20 and 25% for the mid- and late-century periods, respectively).

Mapping reservoir water quality from Sentinel-2 satellite data based on a new approach of weighted averaging: Application of Bayesian maximum entropy.

In regions like Oman, which are characterized by aridity, enhancing the water quality discharged from reservoirs poses considerable challenges. This predicament is notably pronounced at Wadi Dayqah Dam (WDD), where meeting the demand for ample, superior water downstream proves to be a formidable task. Thus, accurately estimating and mapping water quality indicators (WQIs) is paramount for sustainable planning of inland in the study area. Since traditional procedures to collect water quality data are time-consuming, labor-intensive, and costly, water resources management has shifted from gathering field measurement data to utilizing remote sensing (RS) data. WDD has been threatened by various driving forces in recent years, such as contamination from different sources, sedimentation, nutrient runoff, salinity intrusion, temperature fluctuations, and microbial contamination. Therefore, this study aimed to retrieve and map WQIs, namely dissolved oxygen (DO) and chlorophyll-a (Chl-a) of the Wadi Dayqah Dam (WDD) reservoir from Sentinel-2 (S2) satellite data using a new procedure of weighted averaging, namely Bayesian Maximum Entropy-based Fusion (BMEF). To do so, the outputs of four Machine Learning (ML) algorithms, namely Multilayer Regression (MLR), Random Forest Regression (RFR), Support Vector Regression (SVRs), and XGBoost, were combined using this approach together, considering uncertainty. Water samples from 254 systematic plots were obtained for temperature (T), electrical conductivity (EC), chlorophyll-a (Chl-a), pH, oxidation-reduction potential (ORP), and dissolved oxygen (DO) in WDD. The findings indicated that, throughout both the training and testing phases, the BMEF model outperformed individual machine learning models. Considering Chl-a, as WQI, and R-squared, as evaluation indices, BMEF outperformed MLR, SVR, RFR, and XGBoost by 6%, 9%, 2%, and 7%, respectively. Furthermore, the results were significantly enhanced when the best combination of various spectral bands was considered to estimate specific WQIs instead of using all S2 bands as input variables of the ML algorithms.

Entropy-based air quality monitoring network optimization using NINP and Bayesian maximum entropy.

Effectual air quality monitoring network (AQMN) design plays a prominent role in environmental engineering. An optimal AQMN design should consider stations' mutual information and system uncertainties for effectiveness. This study develops a novel optimization model using a non-dominated sorting genetic algorithm II (NSGA-II). The Bayesian maximum entropy (BME) method generates potential stations as the input of a framework based on the transinformation entropy (TE) method to maximize the coverage and minimize the probability of selecting stations. Also, the fuzzy degree of membership and the nonlinear interval number programming (NINP) approaches are used to survey the uncertainty of the joint information. To obtain the best Pareto optimal solution of the AQMN characterization, a robust ranking technique, called Preference Ranking Organization METHod for Enrichment Evaluation (PROMETHEE) approach, is utilized to select the most appropriate AQMN properties. This methodology is applied to Los Angeles, Long Beach, and Anaheim in California, USA. Results suggest using 4, 4, and 5 stations to monitor CO, NO2, and ozone, respectively; however, implementing this recommendation reduces coverage by 3.75, 3.75, and 3 times for CO, NO2, and ozone, respectively. On the positive side, this substantially decreases TE for CO, NO2, and ozone concentrations by 8.25, 5.86, and 4.75 times, respectively.

Progressive improvement of DRASTICA and SI models for groundwater vulnerability assessment based on evolutionary algorithms.

Groundwater management is essential in water and environmental engineering from both quantity and quality aspects due to the growing urban population. Groundwater vulnerability evaluation models play a prominent role in groundwater resource management, such as the DRASTIC model that has been used successfully in numerous areas. Several studies have focused on improving this model by changing the initial parameters or the rates and weights. The presented study investigated results produced by the DRASTIC model by simultaneously exerting both modifications. For this purpose, two land use-based DRASTIC-derived models, DRASTICA and susceptibility index (SI), were implemented in the Shiraz plain, Iran, a semi-arid region and the primary resource of groundwater currently struggling with groundwater pollution. To develop the novel proposed framework for the progressive improvement of the mentioned rating-based techniques, three main calculation steps for rates and weights are presented: (1) original rates and weights; (2) modified rates by Wilcoxon tests and original weights; and (3) adjusted rates and optimized weights using the genetic algorithm (GA) and particle swarm optimization (PSO) algorithms. To validate the results of this framework applied to the case study, the concentrations of three contamination pollutants, NO3, SO4, and toxic metals, were considered. The results indicated that the DRASTICA model yielded more accurate contamination concentrations for vulnerability evaluations than the SI model. Moreover, both models initially displayed well-matched results for the SO4 concentrations, specifically 0.7 for DRASTICA and 0.58 for SI, respectively. Comparatively, the DRASTICA model showed a higher correlation with NO3 concentrations (0.8) than the SI model (0.6) through improved steps. Furthermore, although both original models demonstrated less correlation with toxic metal concentrations (0.05) compared to SO4 and NO3 concentrations, the DRASTICA and SI models with modified rates and optimized weights exhibited enhanced correlation with toxic metals of about 0.7 and 0.2, respectively.