Search

Abstract Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches—multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012–2018) were used as a training set, and 3 years (2019–2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3–10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

Evapotranspiration is one of agricultural water management's most significant and impactful hydrologic processes. A new multi-decomposition deep learning-based technique is proposed in this study to forecast weekly reference evapotranspiration (ETo) in western coastal regions of Australia (Redcliffe and Gold Coast). The time-varying filter-based empirical mode decomposition (TVF-EMD) technique was used to first break down the original meteorological variables/signals into intrinsic mode decomposition functions (IMFs), which included maximum and minimum temperature, relative humidity, wind speed, and solar radiation. Using a partial autocorrelation function (PACF), the significant lagged values were then calculated from the decomposed sub-sequences (i.e., IMFs). A novel Extra Tree- Boruta feature selection algorithm was used to extract important features from the decomposed IMFs. Four machine learning approaches, including bidirectional recurrent neural network (Bi-RNN), multi-layer perceptron neural network (MLP), random forest (RF), and extreme gradient boosting (XGBoost), were used to forecast weekly evapotranspiration using the TVF-EMD-based decomposed meteorological data. Different statistical metrics were applied to evaluate the model performances. The results showed that the decomposition of the input data by TVF-EMD significantly improved the accuracy compared with the non-decomposed inputs (single models without decomposition). The findings indicate that the TVF-BiRNN model, as presented, achieved the highest level of accuracy in simulating weekly ET0 at both the Redcliffe and Gold Coast stations (Redcliffe: R=0.9281, RMSE=3.8793 mm/week, MAPE = 9.2010%; Gold Coast: R=0.8717, RMSE=4.1169 mm/week, MAPE = 11.5408%). The novel hybrid modeling technique can potentially improve agricultural water management through its ability to generate more accurate ETo estimates weekly. The proposed methodology exhibits potential applicability to various other environmental and hydrological modeling issues.

Reference evapotranspiration (ETo) is a vital climate parameter affecting plants' water use. ETo can generate large deficits in soil moisture and runoff in different regions and seasons, leading to uncertainties in drought warning systems. A novel multivariate variational mode decomposition integrated with a boosted regression tree (i.e., MVMD-BRT) is constructed to forecast daily ETo. Firstly, the correlation matrix based on cross-correlation was computed to investigate the significant input predictor lags of daily ETo. Secondly, the MVMD technique decomposes the significant input lags into signals called intrinsic mode functions (IMFs). Thirdly, the IMFs were then employed in the BRT to build the MVMD-BRT model for daily ETo forecasting. A comparative assessment of MVMD against multivariate empirical mode decomposition (MEMD) was also performed on the same lines to develop the MEMD-BRT model. The MVMD-BRT model is compared against the random forest (RF) and hybrid MVMD-RF, MEMD-RF, extreme learning machine (ELM), and hybrid MVMD-ELM, MEMD-ELM, and cascaded feedforward neural network (CFNN) along with its hybrid MVMD-CFNN models for two stations in Queensland, Australia using a set of goodness-of-fit metrics. The results prove that the MVMD-BRT provide accurate daily ETo forecasting against the benchmark models. The MVMD-BRT model yielded the highest accuracy in terms of (WIE = 0.9070, NSE = 0.8421, LME = 0.6529, KGE = 0.8792) and (WIE = 0.8966, NSE = 0.8396, LME = 0.6521, KGE = 0.8803) for Brisbane and Gympie stations against the comparing models.

Power production through combustion of fuels plays a vital role in the progress of a nation. In liquid fuels, biodiesel has emerged as a potential replacement of fossil fuel. In this regard, the improvement of fuel properties or adjustment of the operating parameters can improve the efficiency and lower the emission for a biodiesel run diesel engine. In this regard, the current study focuses on the use of novel nano blended biodiesel, prepared by blending titanium dioxide nano particles along Eichhornia Crassipes biodiesel. Three different biodiesel blends are prepared having composition of titanium dioxide by 50 ppm, 100 ppm and 150 ppm which is tested in a four stroke, single cylinder, naturally aspirated water cooled diesel engine of 3.5 kW rated power for different loading conditions for performance, emission, and combustion evaluation. Further, at the same engine conditions, the biodiesel blend having 150 ppm of titanium dioxide is tested at fuel injection pressure of 220 bar. The findings suggests that the brake thermal efficiency improves and emissions lowers with the addition of nano particles at high fuel injection pressure. The maximum improvement of brake thermal efficiency of 1.01% in comparison to diesel mode has been found for nano blended biodiesel composition of 150 ppm of titanium dioxide at fuel injection pressure of 220 bar under full loading condition. For the same fuel injection pressure of 220 bar and same nano blended biodiesel composition, the hydrocarbon and carbon monoxide emission were found to minimum at 60% load.

In the present study, two innovative techniques namely, Deep Learning (DL) and Gradient boosting Machine (GBM) models are developed based on a maximum air temperature ‘univariate modeling scheme’ for modeling the monthly pan evaporation (Epan) process. Monthly air temperature and pan evaporation are used to build the predictive models. These models are used for evaluating the evaporation prediction for the Kiashahr meteorological station located in the north of Iran and Ranichauri station positioned in Uttarakhand State of India. Findings indicated that the deep learning model was found best at Kiashahr station for testing datasets MAE (0.5691, mm/month), RMSE (0.7111, mm/month), NSE (0.7496), and IOA (0.9413). It can be concluded that in the semi-arid climate of Iran both of the used methods had the good capability in modeling of monthly Epan. However, DL predicted monthly Epan better than GBM. Moreover, the highest accuracy of the deep learning model was also observed for the Ranichauri station in terms of MAE = 0.3693 mm/month, RMSE = 0.4357 mm/month, NSE = 0.8344, & IOA = 0.9507 in testing stage. Overall, results expose the superior performance of DL-based models for both study stations and can also be utilized for various other environmental modeling.

Extreme climate is one of the important variables which determine the capability of tropical peatland to act as either carbon sink and/or carbon source. The purpose of this study is to reveal the spatio-temporal trend in the long-term time series of extreme rainfall and temperature in Sarawak peatland cause by climate change. Gridded-based Princeton datasets were used for trend analysis spanning 68-year (1948–2016) based on Modified Mann-Kendall (m-MK) test which has the capability of distinguishing unidirectional trend with multi-scale variability. The m-MK test was also used to confirm the increasing or decreasing trend produce by Mann-Kendall (MK), and to discriminate the exaggeration in trend caused by serial auto-correlation due to the high effect of large scale climate events regulating the climate in the region. By using R-based program, RClimDex for extreme climate indices output, extreme climate under Northeast (NE) and Southwest (SW) monsoon showed lower grid point with significant changes under m-MK test compared to MK test at 95% significance level. Here, the exaggeration of trend by MK test has been reduced by using m-MK test which can accommodate the scaling effect in the time series due to inherent natural climate variability. Diurnal temperature range (DTR) was expected to decrease for both monsoons in the central-coastal region as minimum temperature (TN) increased more than maximum temperature (TX). Significant increase in extreme rainfall (R10, R20, Rnn) was spatially observed more during SW monsoon compared to NE monsoon, although with high spatial variability. Significant increase of TN indices of TNn and TN90p might cause increased rainfall intensity in the south and central-coastal region, while high TX indices of TXn might cause increased rainfall intensity in the north. Due to the imminent threat of climate change, this study gives scientists an essential view on the behavior of different extreme climate variables and its potential impact on the peatland area which is susceptible to flood and risk of fire during the NE and SW monsoon, respectively.

In the current study, three machine learning (ML) models, i.e. Gaussian process regression (GPR), generalized regression neural network (GRNN), and multigene genetic programming (MGGP), were developed for predicting the discharge coefficient (Cd) of a radial gate under two different flow conditions, i.e. free and submerged. The modeling development of the flow and geometry input variables for the Cd was determined based on statistical correlations. We also performed a sensitivity analysis of the input variables for the Cd. The modeling results indicated that the developed ML models attained acceptable predictable performance; however, the prediction accuracy of the models was better under the free flow condition. In quantitative terms, the minimum root mean square error (RMSE) value was 0.010 using the GPR model and 0.019 using the MGGP model for the submerged and free flow conditions, respectively. The sensitivity analysis evidenced that the ratio of the gate opening height to the depth of water in the upstream (W:Yo) was the influential variable for the Cd under the free flow condition, whereas the ratio of the depth of water in the upstream to the depth of water in downstream (Yo:YT) was the influential variable for the Cd under the submerged flow condition.

Forecasting of solar radiation (Radn) can provide an insight vision for the amount of green and friendly energy sources. Owing to the non-linearity and non-stationarity challenges caused by meteorological variables in forecasting Radn, a variational mode decomposition method is integrated with simulated annealing and random forest (VMD-SA-RF) for resolving this problem. Firstly, the input parameters are separated into training and testing phases​ after generating a one-day ahead significant lags at (t – 1). Secondly, the variational mode decomposition is set to factorize multivariate meteorological data of train and test sets, independently, into their band-limited signals. Thirdly, the simulate annealing based feature selection system is engaged to select the best band-limited signals. Finally, using the pertinent band-limited signals, the daily Radn is forecasted via random forest (RF) model. The outcomes are benchmarked with other comparative models. The hybrid fusion VMD-SA-RF model is tested geographically in Australia, generates reliable performance to forecast Radn. The hybrid VMD-SA-RF system combining the pertinent meteorological features, as the model predictors have substantial implications for renewable and sustainable energy resource management.

Quantification of the soil physicochemical properties is one of the essential process in the field of soil geo-science. In the current research, three types of machine learning (ML) models including support vector machine (SVM), random forest (RF), and gradient boosted decision tree (GBDT) were developed for Total Dissolved Salt (TDS) prediction over several locations in Iraq region. Various physicochemical soil properties were used as predictors for the TDS prediction. Four modeling scenarios are constructed based on the types of the associated soil input variables properties. The applied ML models were analyzed and discussed based on several statistical measures and graphical presentations. Based on the correlation analysis; Gypsum concentration, Sulfur trioxide ( $SO_{3}$ ), Chloride (Cl), and organic matter (OR) were the essential soil properties for the TDS concentration influence. The prediction results indicated that incorporating all the types of input variables including chemical, soil consistency limits, and soil sieve analysis attained the best prediction process. In quantitative terms, the SVM model attained the maximum coefficient of determination ( $R^{2}=0.849$ ) and minimum root mean square error (RMSE=3.882). Overall, the development of the ML models for the TDS of soil prediction provided a robust and reliable methodology that contributes to the soil geoscience field.

An accurate prediction of water quality (WQ) related parameters is considered as pivotal decisive tool in sustainable water resources management. In this study, five different ensemble machine learning (ML) models including Quantile regression forest (QRF), Random Forest (RF), radial support vector machine (SVM), Stochastic Gradient Boosting (GBM) and Gradient Boosting Machines (GBM_H2O) were developed to predict the monthly biochemical oxygen demand (BOD) values of the Euphrates River, Iraq. For this aim, monthly average data of water temperature (T), Turbidity, pH, Electrical Conductivity (EC), Alkalinity (Alk), Calcium (Ca), chemical oxygen demand (COD), Sulfate (SO4), total dissolved solids (TDS), total suspended solids (TSS), and BOD measured for ten years period were used in this study. The performances of these standalone models were compared with integrative models developed by coupling the applied ML models with two different feature extraction algorithms i.e., Genetic Algorithm (GA) and Principal Components Analysis (PCA). The reliability of the applied models was evaluated based on the statistical performance criteria of determination coefficient (R2), root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe model efficiency coefficient (NSE), Willmott index (d), and percent bias (PBIAS). Results showed that among the developed models, QRF model attained the superior performance. The performance of the evaluated models presented in this study proved that the developed integrative PCA-QRF model presented much better performance compared with the standalone ones and with those integrated with GA. The statistical criteria of R2, RMSE, MAE, NSE, d, and PBIAS of PCA-QRF were 0.94, 0.12, 0.05, 0.93, 0.98, and 0.3, respectively.

River sedimentation is an important indicator for ecological and geomorphological assessments of soil erosion within any watershed region. Sediment transport in a river basin is therefore a multifaceted field yet being a dynamic task in nature. It is characterized by high stochasticity, non-linearity, non-stationarity, and feature redundancy. Various artificial intelligence (AI) modeling frameworks have been introduced to solve river sediment problems. The present survey is designed to provide an updated account of the latest and most relevant AI-based applications for modeling the sediment transport in river basin systems. The review is established to capture the subsequent developments in the advanced AI models applied for river sediment transport prediction. Also, several hydrological and environmental aspects are identified and analyzed according to the results produced in those studies. The merits and constraints of the well-established AI models are further discussed in much detail, particularly considering state-of-the art, modeling frameworks and their application-specific appraisal, and some of the key proposed future research directions. Together with the synthesis of such information to drive a new understanding of models and methodologies related to suspended river sediment prediction, this review provides a future research vision for hydrologists, water scientists, water resource engineers, oceanography and environmental planners.

Among several indicators for river engineering sustainability, the longitudinal dispersion coefficient ( $ K_x $ ) is the main parameter that defines the transport of pollutants in natural streams. Accurate estimation of $ K_x $ has been challenging for hydrologists due to the high stochasticity and non-linearity of this hydraulic-environmental parameter. This study presents a new hybrid machine learning (ML) model integrating a Gaussian Process Regression (GPR) and an evolutionary feature selection (FS) approach (i.e. Covariance Matrix Adaptation Evolution Strategy (CMAES)) to estimate $ K_x $ in natural streams. The dataset consists of geometric and hydraulic river system parameters from 29 streams in the United States. The modeling results showed that the proposed model outperformed other models in the literature, producing more stable and accurate estimations. The FS approach evidenced the significance of the cross-sectional average flow velocity (U), channel width (B), and channel sinuosity σ to estimate the dispersion coefficient. In quantitative terms, the integrated GPR model with feature selection approach attained the minimum root mean square error ( $ {\rm RMSE} = 48.67 $ ) and maximum coefficient of determination ( $ R^2 = 0.95 $ ). The proposed hybrid evolutionary ML model arises as robust, flexible and reliable alternative computer aid technology for predicting the longitudinal dispersion coefficient in natural streams.

The potential of the soil to hold plant nutrients is governed by the cation-exchange capacity (CEC) of any soil. Estimating soil CEC aids in conventional soil management practices to replenish the soil solution that supports plant growth. In this study, a multiple model integration scheme supervised with a hybrid genetic algorithm-neural network (MM-GANN) was developed and employed to predict the accuracy of soil CEC in Tabriz plain, an arid region of Iran. The standalone models (i.e., artificial neural network (ANN) and extreme learning machine (ELM)) were implemented for incorporation into the MM-GANN. In addition, it was tested to enhance the prediction accuracy of the standalone models. The soil parameters such as clay, silt, pH, carbonate calcium equivalent (CCE), and soil organic matter (OM) were used as model inputs to predict soil CEC. With the use of several evaluation criteria, the results showed that the MM-GANN model involving the predictions of ELM and ANN models calibrated by considering all the soil parameters (e.g., Clay, OM, pH, silt, and CCE) as inputs provided superior soil CEC estimates with a Nash Sutcliffe Efficiency (NSE) = 0.87, Root Mean Square Error (RMSE) = 2.885, Mean Absolute Error (MAE) = 2.249, Mean Absolute Percentage Error (MAPE) = 12.072, and coefficient of determination (R2) = 0.884. The proposed MM-GANN model is a reliable intelligence-based approach for the assessment of soil quality parameters intended for sustainability and management prospects.

Water scarcity is a major constraint for food production, particularly in arid and semi-arid environments. In this regard, selecting the best irrigation technique is crucial to overcome water scarcity and enhance water productivity (WP) with no significant yield loss. This study aimed to assess the impact of irrigation techniques of every furrow irrigation (EFI), alternate furrow irrigation (AFI), and drip irrigation (DI), as well as the flow rate, on irrigation system performance parameters, yield, water productivity of cauliflower crop and soil salinity during the two successive growing seasons of 2017/2018 and 2018/2019 under field conditions. The treatments comprised three different irrigation inflow rates: Q1 = 0.47 L/s, Q2 = 0.95 L/s, and Q3 = 1.43 L/s. For both investigated seasons, the AFI + Q3 treatment produced the best water distribution uniformity (DU) and water application efficiency (AE) of 85.10% and 72.73%, respectively, of the surface irrigation, and DI methods across the two growing seasons produced the highest DU of 95%. DI produced the highest cauliflower curd yield (18.12 Mg/fed), followed by EFI + Q3 (12.285 Mg/fed) and AFI + Q3 (11.905 Mg/fed). The maximum mean WP value of 10.6 kg/m3 was recorded with DI, followed by AFI + Q3 (6.24 kg/m3), across the two growing seasons. DI, AFI + Q3, AFI + Q2, AFI + Q1, EFI + Q3, and EFI + Q2 saved irrigation water by 32.63, 28.71, 21.22, 18.04, 10.48, and 3.18%, respectively, compared with EFI + Q1 across the two growing seasons. During both seasons, the average value using the drip irrigation system was 3.60 dS/m. Considering the annual leaching requirements of soil, climate change conditions, and fixed costs, we recommend the use of a drip irrigation system in clayey soil to produce cauliflower, followed by the use of the alternative furrow irrigation method to enable the aeration of the same soil for a lower cost.

Climate change impacts on temperatures, precipitations, streamflows, and recharges were studied across eastern, central, and western Prince Edward Island (PEI) between climate normals in 1991–2020, 2021–2050, and 2051–2080 using observed and projected data, and SWAT modeling. Average annual temperature can significantly rise from the existing 5.90–6.86 °C to 8.26–11.09 °C in different parts during the next 30–60 years under different RCP scenarios. Average annual precipitations would not significantly change except in western PEI where a 17% likely increase would offset further warming impact; therefore, current streamflows (~650 mm/year) and recharges (~320 mm/year) would not be much affected there. However, warming and increased pumping together in its Wilmot River watershed could reduce streamflows up to 9%, and 13% during 2021–2050, and 2051–2080, respectively. In the eastern forest-dominated Bear River watershed, no significant reductions in current streamflows (~692 mm/year) or recharges (~597 mm/year) are expected. Nevertheless, near constant precipitation and warming could cumulatively reduce streamflows/recharges up to 8% there, as pumping will be negligible. In the central zone, precipitation could insignificantly increase up to 5%, but current streamflows (~737 mm/year) and recharges (~446 mm/year) would not be significantly affected, except for RCP8.5 under which streamflows could reduce by ~16% during 2051–2080. Overall, more attenuated streamflows and recharges are likely with higher quantities in late winter and early spring, and somewhat lesser ones in summer, which could reduce water supplies during the growing season. Besides, precipitation uncertainty of ~300 mm/year between dry and wet years continues to be a major water management challenge. Adapting policies and regulations to the changing environment would ensure sustainable water management in PEI.

Egypt has limited agricultural land, associated with the scarcity of irrigation water and rapid population growth. Hydroponic farming, seawater desalination and magnetic treatment are among the practical solutions for sustaining rapid population growth. In this regard, the main objective of the present research study was to design and construct a hierarchical engineering unit as a hydroponic farming system (soilless) to produce an iceberg lettuce crop using magnetically treated saline water. The treatments included four types of irrigation water: common irrigation water (IW1) with an electrical conductivity (EC) of 0.96 dS/m as a control treatment, magnetically treated common irrigation water (IW2) with an EC of 0.96 dS/m, saline water (IW3) with an EC of 4.56 dS/m and magnetically treated saline water (IW4) with an EC of 4.56 dS/m; three depletion ratios (DR) of field capacity (DR0 = 50%, DR1 = 60% and DR2 = 70%) and three slopes of hydroponic pipes (S1 = 0.0%, S2 = 0.025% and S3 = 0.075%). The results revealed that seawater contributed 7.15% to produce iceberg lettuce in the hydroponic system. The geometric parameter, the slope of the pipes, influenced the obtained luminous intensity by an average increase of 21% and 71% for S2 and S3, respectively, compared with the zero slope (horizontal pipes). Magnetization of irrigation water increased the total soluble solids (TSS) and enhanced the fresh weight and water productivity of both iceberg lettuce varieties used. The maximum percentages of TSS were 5.20% and 5.10% for lemur and iceberg 077, respectively, for the combination IW4DR2S2. The highest values of fresh weight and water productivity of 3.10 kg/m and 39.15 kg/m3 were recorded with the combinations IW3DR2S3 and IW4DR1S3, respectively, for lemur and iceberg lettuce. The percentages of these increases were 109.46% and 97.78%, respectively, when compared with the combination IW1DR0S1. The highest values of iceberg lettuce 077 fresh weight and water productivity were 2.93 kg/m and 36.15 kg/m3, respectively, which were recorded with the combination IW4DR1S3. The percentages of these increases were 112.32% and 120.56%, respectively, when compared with IW1DR0S1 (the control treatment).

Assessment of possible changes in crops water stress due to climate alteration is essential for agricultural planning, particularly in arid regions where water supply is the major challenge for agricultural development. This study aims to project climatic water availability (CWA) and crop water demand (CWD) to outline the possible future agricultural water stress of Iraq for different radiative concentration pathways (RCPs). The ensemble means of downscaled precipitation and temperature projections of the selected global climate models (GCMs) were used in a simple water balance model for this purpose. The modified Mann–Kendall (mMK) trend test was employed to estimate the tendency in CWA and the Wilcoxon rank test to evaluate CWD alteration in three future time horizons compared to the base period (1971–2000). The results revealed a decrease in CWA at a rate of up to −34/year during 2010–2099 for RCP8.5. The largest declination would be in summer (−29/year) and an insignificant decrease in winter (−1.3/year). The study also showed an increase in CWD of all major crops for all scenarios. The highest increase in CWD would be for summer crops, approximately 320 mm, and the lowest for winter crops, nearly 32 mm for RCP8.5 in the far future (2070–2099). The decrease in CWA and increase in CWD would cause a sharp rise in crop water stress in Iraq. This study indicates that the increase in temperature is the main reason for a large increase in CWD and increased agricultural water stress in Iraq.