Dissolved oxygen prediction using a new ensemble method

Leveraging Bayesian deep learning and ensemble methods for uncertainty quantification in image classification: A ranking-based approach

Bayesian deep learning (BDL) has emerged as a powerful technique for quantifying uncertainty in classification tasks, surpassing the effectiveness of traditional models by aligning with the probabilistic nature of real-world data. This alignment allows for informed decision-making by not only identifying the most likely outcome but also quantifying the surrounding uncertainty. Such capabilities hold great significance in fields like medical diagnoses and autonomous driving, where the consequences of misclassification are substantial. To further improve uncertainty quantification, the research community has introduced Bayesian model ensembles, which combines multiple Bayesian models to enhance predictive accuracy and uncertainty quantification. These ensembles have exhibited superior performance compared to individual Bayesian models and even non-Bayesian counterparts. In this study, we propose a novel approach that leverages the power of Bayesian ensembles for enhanced uncertainty quantification. The proposed method exploits the disparity between predicted positive and negative classes and employes it as a ranking metric for model selection. For each instance or sample, the ensemble's output for each class is determined by selecting the top 'k' models based on this ranking. Experimental results on different medical image classifications demonstrate that the proposed method consistently outperforms or achieves comparable performance to conventional Bayesian ensemble. This investigation highlights the practical application of Bayesian ensemble techniques in refining predictive performance and enhancing uncertainty evaluation in image classification tasks.

Development of a robust daily soil temperature estimation in semi-arid continental climate using meteorological predictors based on computational intelligent paradigms

Changes in soil temperature (ST) play an important role in the main mechanisms within the soil, including biological and chemical activities. For instance, they affect the microbial community composition, the speed at which soil organic matter breaks down and becomes minerals. Moreover, the growth and physiological activity of plants are directly influenced by the ST. Additionally, ST indirectly affects plant growth by influencing the accessibility of nutrients in the soil. Therefore, designing an efficient tool for ST estimating at different depths is useful for soil studies by considering meteorological parameters as input parameters, maximal air temperature, minimal air temperature, maximal air relative humidity, minimal air relative humidity, precipitation, and wind speed. This investigation employed various statistical metrics to evaluate the efficacy of the implemented models. These metrics encompassed the correlation coefficient (r), root mean square error (RMSE), Nash-Sutcliffe (NS) efficiency, and mean absolute error (MAE). Hence, this study presented several artificial intelligence-based models, MLPANN, SVR, RFR, and GPR for building robust predictive tools for daily scale ST estimation at 05, 10, 20, 30, 50, and 100cm soil depths. The suggested models are evaluated at two meteorological stations (i.e., Sulaimani and Dukan) located in Kurdistan region, Iraq. Based on assessment of outcomes of this study, the suggested models exhibited exceptional predictive capabilities and comparison of the results showed that among the proposed frameworks, GPR yielded the best results for 05, 10, 20, and 100cm soil depths, with RMSE values of 1.814°C, 1.652°C, 1.773°C, and 2.891°C, respectively. Also, for 50cm soil depth, MLPANN performed the best with an RMSE of 2.289°C at Sulaimani station using the RMSE during the validation phase. Furthermore, GPR produced the most superior outcomes for 10cm, 30cm, and 50cm soil depths, with RMSE values of 1.753°C, 2.270°C, and 2.631°C, respectively. In addition, for 05cm soil depth, SVR achieved the highest level of performance with an RMSE of 1.950°C at Dukan station. The results obtained in this research confirmed that the suggested models have the potential to be effectively used as daily predictive tools at different stations and various depths.

Predicting water quality through daily concentration of dissolved oxygen using improved artificial intelligence

As an important hydrological parameter, dissolved oxygen (DO) concentration is a well-accepted indicator of water quality. This study deals with introducing and evaluating four novel integrative methods for the prediction of DO. To this end, teaching-learning-based optimization (TLBO), sine cosine algorithm, water cycle algorithm (WCA), and electromagnetic field optimization (EFO) are appointed to train a commonly-used predictive system, namely multi-layer perceptron neural network (MLPNN). The records of a USGS station called Klamath River (Klamath County, Oregon) are used. First, the networks are fed by the data between October 01, 2014, and September 30, 2018. Later, their competency is assessed using the data belonging to the subsequent year (i.e., from October 01, 2018 to September 30, 2019). The reliability of all four models, as well as the superiority of the WCA-MLPNN, was revealed by mean absolute errors (MAEs of 0.9800, 1.1113, 0.9624, and 0.9783) in the training phase. The calculated Pearson correlation coefficients (RPs of 0.8785, 0.8587, 0.8762, and 0.8815) plus root mean square errors (RMSEs of 1.2980, 1.4493, 1.3096, and 1.2903) showed that the EFO-MLPNN and TLBO-MLPNN perform slightly better than WCA-MLPNN in the testing phase. Besides, analyzing the complexity and the optimization time pointed out the EFO-MLPNN as the most efficient tool for predicting the DO. In the end, a comparison with relevant previous literature indicated that the suggested models of this study provide accuracy improvement in machine learning-based DO modeling.

Applying Machine Learning to investigate metal isotope variations at the watershed scale: A case study with lithium isotopes across the Yukon River Basin

Constraining the multiple climatic, lithological, topographic, and geochemical variables controlling isotope variations in large rivers is often challenging with standard statistical methods. Machine learning (ML) is an efficient method for analyzing multidimensional datasets, resolving correlated processes, and exploring relationships between variables simultaneously. We tested four ML algorithms to elucidate the controls of riverine δ7Li variations across the Yukon River Basin (YRB). We compiled (n = 102) and analyzed new samples (n = 21), producing a dataset of 123 river water samples collected across the basin during the summer including δ7Li and extracted environmental, climatological, and geological characteristics of the drainage area for each sample from open-access geospatial databases. The ML models were trained, tuned, and tested under multiple scenarios to avoid issues such as overfitting. Random Forests (RF) performed best at predicting δ7Li across the basin, with the median model explaining 62 % of the variance. The most important variables controlling δ7Li across the basin are elevation, lithology, and past glacial coverage, which ultimately influence weathering congruence. Riverine δ7Li has a negative dependence on elevation. This reflects congruent weathering in kinetically-limited mountain zones with short residence times. The consistent ranking of lithology, specifically igneous and metamorphic rock cover, as a top feature controlling riverine δ7Li modeled by the RFs is unexpected. Further study is required to validate this finding. Rivers draining areas that were extensively covered during the last glacial maximum tend to have lower δ7Li due to immature weathering profiles resulting in short residence times, less secondary mineral formation and therefore more congruent weathering. We demonstrate that ML provides a fast, simple, visualizable, and interpretable approach for disentangling key controls of isotope variations in river water. We assert that ML should become a routine tool, and present a framework for applying ML to analyze spatial metal isotope data at the catchment scale.

Modeling dissolved oxygen concentration using machine learning techniques with dimensionality reduction approach

Oxygen is crucial to keep the life cycle balance in any aspect. Aquatic life is highly influenced by the levels of dissolved oxygen (DO). This calls for not just constant monitoring of the DO in aquatic systems, but to generate an accurate prediction model for future levels of the DO. This study aims to propose an accurate prediction model for DO concentrations. The performance of the Random Forest (RF) and multilayer perceptron (MLP) algorithms was evaluated in generating the regression models. Moreover, the effect of dimensionality reduction of the data by the wrapper feature Selection method on the performance of the models was evaluated. The results showed that the RF regressor excelled MLP in performance with both the dataset of all variables and the dataset of reduced variables with the best performance achieved by the RF regressor by considering Pearson correlation coefficient (0.8052), Mean absolute error (0.8911), and root mean square error (1.2805) when trained by the dataset of reduced variables. As for the accuracy of the models, the estimation error deviation of both models declined significantly when trained by the reduced variables. When the accuracy of the prediction was increased by 0.95% by the RF regressor, the accuracy of the MLP was incremented by 5.7% when trained by the dataset of reduced variables. The results demonstrated the positive impact of the dimensionality reduction on the accuracy of both models. However, RF can be considered a robust regressor in predicting DO concentrations.

The potential of novel hybrid SBO-based long short-term memory network for prediction of dissolved oxygen concentration in successive points of the Savannah River, USA

The accurate estimation of dissolved oxygen (DO) as an important water quality indicator can provide a basis for ensuring the preservation of the riverine ecosystem and designing proper water quality development plans. Therefore, this study aimed to propose a novel hybrid model based on long short-term memory (LSTM) networks with Satin Bowerbird optimizer (SBO) algorithm for the estimation of the DO concentration based on multiple water quality parameters. Furthermore, to compare the supreme performance of proposed hybrid model, standalone LSTM, support vector machine (SVM) and Gaussian process regression (GPR) were employed. The models were prepared using the datasets collected from three successive gauging stations along the Savannah River, USA, for the period 2015-2021. The modeling process was performed through local and cross-station scenarios to assess the interrelations between the DO values of upstream/downstream stations. The comparison of estimation accuracies of different employed models revealed that the proposed SBO-LSTM yields a correlation coefficient (R) of 0.981, Nash-Sutcliffe efficiency (NSE) of 0.957, and root mean square error (RMSE) of 0.034 for a test series of dissolved oxygen series which was the most accurate model through both local and cross-station scenarios. Also, the proposed SBO-LSTM model showed better performance by 0.52% and 1.26% than employed SVM and GPR models, respectively. The obtained results showed the essential role of the water temperature parameter in the DO modeling of all three studied stations.

An Analytical Framework on Utilizing Various Integrated Multi-Trophic Scenarios for Basil Production

Here, we aim to improve the overall sustainability of aquaponic basil (Ocimum basilicum L.)-sturgeon (Acipenser baerii) integrated recirculating systems. We implement new AI methods for operational management together with innovative solutions for plant growth bed, consisting of Rapana venosa shells (R), considered wastes in the food processing industry. To this end, the ARIMA-supervised learning method was used to develop solutions for forecasting the growth of both fish and plant biomass, while multi-linear regression (MLR), generalized additive models (GAM), and XGBoost were used for developing black-box virtual sensors for water quality. The efficiency of the new R substrate was evaluated and compared to the consecrated light expended clay aggregate-LECA aquaponics substrate (H). Considering two different technological scenarios (A-high feed input, B-low feed input, respectively), nutrient reduction rates, plant biomass growth performance and additionally plant quality are analysed. The resulting prediction models reveal a good accuracy, with the best metrics for predicting N-NO₃ concentration in technological water. Furthermore, PCA analysis reveals a high correlation between water dissolved oxygen and pH. The use of innovative R growth substrate assured better basil growth performance. Indeed, this was in terms of both average fresh weight per basil plant, with 22.59% more at AR compared to AH, 16.45% more at BR compared to BH, respectively, as well as for average leaf area (LA) with 8.36% more at AR compared to AH, 9.49% more at BR compared to BH. However, the use of R substrate revealed a lower N-NH₄ and N-NO₃ reduction rate in technological water, compared to H-based variants (19.58% at AR and 18.95% at BR, compared to 20.75% at AH and 26.53% at BH for N-NH₄; 2.02% at AR and 4.1% at BR, compared to 3.16% at AH and 5.24% at BH for N-NO₃). The concentration of Ca, K, Mg and NO₃ in the basil leaf area registered the following relationship between the experimental variants: AR > AH > BR > BH. In the root area however, the NO₃ were higher in H variants with low feed input. The total phenolic and flavonoid contents in basil roots and aerial parts and the antioxidant activity of the methanolic extracts of experimental variants revealed that the highest total phenolic and flavonoid contents were found in the BH variant (0.348% and 0.169%, respectively in the roots, 0.512% and 0.019%, respectively in the aerial parts), while the methanolic extract obtained from the roots of the same variant showed the most potent antioxidant activity (89.15%). The results revealed that an analytical framework based on supervised learning can be successfully employed in various technological scenarios to optimize operational management in an aquaponic basil (Ocimum basilicum L.)-sturgeon (Acipenser baerii) integrated recirculating systems. Also, the R substrate represents a suitable alternative for replacing conventional aquaponic grow beds. This is because it offers better plant growth performance and plant quality, together with a comparable nitrogen compound reduction rate. Future studies should investigate the long-term efficiency of innovative R aquaponic growth bed. Thus, focusing on the application of the developed prediction and forecasting models developed here, on a wider range of technological scenarios.

Multi-input multi-output temporal convolutional network for predicting the long-term water quality of ocean ranches

The prediction of water quality parameters is of great significance to the control of marine environments and provides a scientific decision-making basis for maintaining the stability of water environments and ensuring the normal survival and growth of marine aquatic products. However, the water quality in ocean ranches is affected by the complex, dynamic, and changeable environments of open water, which have complex nonlinear relationships, poor accuracy, high time complexity, and poor long-term predictability. Therefore, in this paper, a multi-input multi-output end-to-end prediction model based on a temporal convolutional network (MIMO-TCN) is proposed to predict water quality. A ConvNeXt module and TCN module were used as the model encoder and decoder, respectively. ConvNeXt was used to extract the features of the input data, and the TCN used the extracted feature data to achieve improved prediction accuracy. The model adds skip connections between its modules to solve the gradient disappearance problem as the number of network layers increases. To prove the effectiveness of the proposed method, a model robustness and prediction ability evaluation was conducted in this paper based on the dissolved oxygen in multiple ocean pasture validation samples. Compared with other learning models, the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) of the MIMO-TCN prediction results were reduced by 60.77%, 30.88%, and 52.45% on average, respectively, and the R² improved by 6.07% on average over those of other models. The experimental results show that the proposed method has higher forecasting accuracy than competing approaches.

The development of dissolved oxygen forecast model using hybrid machine learning algorithm with hydro-meteorological variables

Dissolved oxygen (DO) forecasting is essential for aquatic managers responsible for maintaining ecosystem health and the management of water bodies affected by water quality parameters. This paper aims to forecast dissolved oxygen (DO) concentration using a multivariate adaptive regression spline (MARS) hybrid model coupled with maximum overlap discrete wavelet transformation (MODWT) as a feature decomposition approach for Surma River water using a set of water quality hydro-meteorological variables. The proposed hybrid model is compared with numerous machine learning methods, namely Bayesian ridge regression (BNR), k-nearest neighbourhood (KNN), kernel ridge regression (KRR), random forest (RF), and support vector regression (SVR). The investigational results show that the proposed model of MODWT-MARS has a better prediction than the comparing benchmark models and individual standalone counter parts. The result shows that the hybrid algorithms (i.e. MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47%, and MAE = 0.089). This hybrid method may serve to forecast water quality variables with fewer predictor variables.

A Review on Machine Learning, Artificial Intelligence, and Smart Technology in Water Treatment and Monitoring

Artificial-intelligence methods and machine-learning models have demonstrated their ability to optimize, model, and automate critical water- and wastewater-treatment applications, natural-systems monitoring and management, and water-based agriculture such as hydroponics and aquaponics. In addition to providing computer-assisted aid to complex issues surrounding water chemistry and physical/biological processes, artificial intelligence and machine-learning (AI/ML) applications are anticipated to further optimize water-based applications and decrease capital expenses. This review offers a cross-section of peer reviewed, critical water-based applications that have been coupled with AI or ML, including chlorination, adsorption, membrane filtration, water-quality-index monitoring, water-quality-parameter modeling, river-level monitoring, and aquaponics/hydroponics automation/monitoring. Although success in control, optimization, and modeling has been achieved with the AI methods, ML models, and smart technologies (including the Internet of Things (IoT), sensors, and systems based on these technologies) that are reviewed herein, key challenges and limitations were common and pervasive throughout. Poor data management, low explainability, poor model reproducibility and standardization, as well as a lack of academic transparency are all important hurdles to overcome in order to successfully implement these intelligent applications. Recommendations to aid explainability, data management, reproducibility, and model causality are offered in order to overcome these hurdles and continue the successful implementation of these powerful tools.

Machine learning algorithm as a sustainable tool for dissolved oxygen prediction: a case study of Feitsui Reservoir, Taiwan

Water quality status in terms of one crucial parameter such as dissolved oxygen (D.O.) has been an important concern in the Fei-Tsui reservoir for decades since it's the primary water source for Taipei City. Therefore, this study aims to develop a reliable prediction model to predict D.O. in the Fei-Tsui reservoir for better water quality monitoring. The proposed model is an artificial neural network (ANN) with one hidden layer. Twenty-nine years of water quality data have been used to validate the accuracy of the proposed model. A different number of neurons have been investigated to optimize the model's accuracy. Statistical indices have been used to examine the reliability of the model. In addition to that, sensitivity analysis has been carried out to investigate the model's sensitivity to the input parameters. The results revealed the proposed model capable of capturing the dissolved oxygen's nonlinearity with an acceptable level of accuracy where the R-squared value was equal to 0.98. The optimum number of neurons was found to be equal to 15-neuron. Sensitivity analysis shows that the model can predict D.O. where four input parameters have been included as input where the d-factor value was equal to 0.010. This main achievement and finding will significantly impact the water quality status in reservoirs. Having such a simple and accurate model embedded in IoT devices to monitor and predict water quality parameters in real-time would ease the decision-makers and managers to control the pollution risk and support their decisions to improve water quality in reservoirs.

A hybrid XGBoost-ISSA-LSTM model for accurate short-term and long-term dissolved oxygen prediction in ponds

Dissolved oxygen (DO) is one of the most critical factors to measure the water quality in ponds, which greatly impacts on healthy growth of aquatic organisms. To improve the prediction accuracy of DO and grasp its changing trends, a novel hybrid DO prediction model based on the long short-term memory network (LSTM) optimized by an improved sparrow search algorithm (ISSA) is proposed. Firstly, to discard redundant information and improve the calculation speed of the model, the key factors that have a greater correlation with DO are selected as the input parameters by extreme gradient boosting (XGBoost). Secondly, towards expanding the searching range of sparrows and balancing the global and local search, we introduce an adaptive factor exponential declining strategy for producers, and an arcsine decreasing strategy for scouters, which nonlinearly decreases with the increase of iterations. Besides, we also improve the position updating of scouters, making the sparrows gradually move to the best position. Finally, LSTM is optimized by ISSA to get the best initial weights and thresholds to construct an XGBoost-ISSA-LSTM DO prediction model. Specifically, we first analyze the method for water quality prediction, which can make short-term prediction (including about 1 h, 2 h) and long-term prediction (including about 12 h, 24 h) of DO. In 1-h prediction, the root mean square error (RMSE) of the model is 0.5571, the mean absolute error (MAE) is 0.2572, and the R² is 0.9276. In 24 h prediction, RMSE of the model is 0.6310, MAE is 0.4562, and R² is 0.9082. The experimental results show that the proposed model has better generalization performance and higher prediction accuracy compared with other common models. Therefore, the presented model based on XGBoost-ISSA-LSTM is more effective and could meet the actual demand of accurate prediction of DO.

Groundwater quality modeling using a novel hybrid data-intelligence model based on gray wolf optimization algorithm and multi-layer perceptron artificial neural network: a case study in Asadabad Plain, Hamedan, Iran

Monitoring and assessment of groundwater quality (GWQ) as an important freshwater source for drinking purposes in urban and rural regions of developing countries due to rapidly increasing contamination is one of the concerns of water managers. Therefore, developing an efficient intelligent model for analyzing GWQ could help hydro-environmental engineers for sustainable water supply. The current research investigated the applicability of a novel nature-inspired optimization algorithm hybridized with multi-layer perceptron artificial neural network based on gray wolf optimization (GWO) for estimating dissolved oxygen (DO) total dissolved solid (TDS) and turbidity parameters at Asadabad Plain, Iran, and results are compared with the stand-alone multi-layer perceptron artificial neural network (MLPANN), generalized regression neural network (GRNN), and multiple linear regression (MLR) approaches. Evaluation of performance of models is carried out using various statistical indices like relative root mean square error, Nash-Sutcliffe efficiency, and correlation coefficient. Based on the results obtained, it is found that the hybrid GWO-MLPANN is a beneficial GWQ forecasting tool in accordance to high performance accuracy. Also, the study found that the superiority of the applied meta-heuristic algorithm (GWO) in improving the performance accuracy of the stand-alone artificial intelligence techniques in modeling the GWQ parameters.

An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model

Dissolved oxygen (DO) concentration in water is one of the key parameters for assessing river water quality. Artificial intelligence (AI) methods have previously proved to be accurate tools for DO concentration prediction. This study presents the implementation of a deep learning approach applied to a recurrent neural network (RNN) algorithm. The proposed deep recurrent neural network (DRNN) model is compared with support vector machine (SVM) and artificial neural network (ANN) models, formerly shown to be robust AI algorithms. The Fanno Creek in Oregon (USA) is selected as a case study and daily values of water temperature, specific conductance, streamflow discharge, pH, and DO concentration are used as input variables to predict DO concentration for three different lead times ("t + 1," "t + 3," and "t + 7"). Based on Pearson's correlation coefficient, several input variable combinations are formed and used for prediction. The model prediction performance is evaluated using various indices such as correlation coefficient, Nash-Sutcliffe efficiency, root mean square error, and mean absolute error. The results identify the DRNN model ([Formula: see text]) as the most accurate among the three models considered, highlighting the potential of deep learning approaches for water quality parameter prediction.

Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks

Predicting the level of dissolved oxygen (DO) is an important issue ensuring the sustainability of the inhabitants of a river. A prediction model can predict the DO level using a historical dataset with regard to water temperature, pH, and specific conductance for a given river. The model can be built using sophisticated computational procedures such as multi-layer perceptron-based artificial neural networks. Different types of networks can be constructed for this purpose. In this study, the authors constructed three networks, namely, multi-verse optimizer (MVO), black hole algorithm (BHA), and shuffled complex evolution (SCE). The networks were trained using the datasets collected from the Klamath River Station, Oregon, USA, for the period 2015–2018. We found that the trained networks could predict the DO level of 2019. We also found that both BHA- and SCE-based networks could predict the level of DO using a relatively simple configuration compared to that of MVO. From the viewpoints of absolute errors and Pearson’s correlation coefficient, MVO- and SCE-based networks performed better than BHA-based networks. In synopsis, the authors recommend MVO- and MLP-based artificial neural networks for predicting the DO level of a river.

Simulating Diurnal Variations of Water Temperature and Dissolved Oxygen in Shallow Minnesota Lakes

In shallow lakes, water quality is mostly affected by weather conditions and some ecological processes which vary throughout the day. To understand and model diurnal-nocturnal variations, a deterministic, one-dimensional hourly lake water quality model MINLAKE2018 was modified from daily MINLAKE2012, and applied to five shallow lakes in Minnesota to simulate water temperature and dissolved oxygen (DO) over multiple years. A maximum diurnal water temperature variation of 11.40 °C and DO variation of 5.63 mg/L were simulated. The root-mean-square errors (RMSEs) of simulated hourly surface temperatures in five lakes range from 1.19 to 1.95 °C when compared with hourly data over 4–8 years. The RMSEs of temperature and DO simulations from MINLAKE2018 decreased by 17.3% and 18.2%, respectively, and Nash-Sutcliffe efficiency increased by 10.3% and 66.7%, respectively; indicating the hourly model performs better in comparison to daily MINLAKE2012. The hourly model uses variable hourly wind speeds to determine the turbulent diffusion coefficient in the epilimnion and produces more hours of temperature and DO stratification including stratification that lasted several hours on some of the days. The hourly model includes direct solar radiation heating to the bottom sediment that decreases magnitude of heat flux from or to the sediment.

AI-HydSu: An advanced hybrid approach using support vector regression and particle swarm optimization for dissolved oxygen forecasting

Since the variations in the dissolved oxygen concentration are affected by many factors, the corresponding uncertainty is nonlinear and fuzzy. Therefore, the accurate prediction of dissolved oxygen concentrations has been a difficult problem in the fishing industry. To address this problem, a hybrid dissolved oxygen concentration prediction model (AI-HydSu) is proposed in this paper. First, to ensure the accuracy of the experimental results, the data are preprocessed by wavelet threshold denoising, and the advantages of the particle swarm optimization (PSO) algorithm are used to search the solution space and select the best parameters for the support vector regression (SVR) model. Second, the prediction model optimizes the invariant learning factors in the standard PSO algorithm by using nonlinear adaptive learning factors, thus effectively preventing the algorithm from falling to local optimal solutions and accelerating the algorithm's optimization search process. Third, the velocities and positions of the particles are updated by constantly updating the learning factors to finally obtain the optimal combination of SVR parameters. The algorithm not only performs searches for the penalty factor, kernel function parameters, and error parameters in SVR but also balances its global and local search abilities. A dissolved oxygen concentration prediction experiment demonstrates that the proposed model achieves high accuracy and a fast convergence rate.

Bayesian Model Averaging: A Unique Model Enhancing Forecasting Accuracy for Daily Streamflow Based on Different Antecedent Time Series

Streamflow forecasting is a vital task for hydrology and water resources engineering, and the different artificial intelligence (AI) approaches have been employed for this purposes until now. Additionally, the forecasting accuracy and uncertainty estimation are the meaningful assignments that need to be recognized. The addressed research investigates the potential of novel ensemble approach, Bayesian model averaging (BMA), in streamflow forecasting using daily time series data from two stations (i.e., Hongcheon and Jucheon), South Korea. Six categories (i.e., M1–M6) of input combination using different antecedent times were employed for streamflow forecasting. The outcomes of BMA model were compared with those of multivariate adaptive regression spline (MARS), M5 model tree (M5Tree), and Kernel extreme learning machines (KELM) models considering four assessment indexes, root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), and mean absolute error (MAE). The results revealed the superior accuracy of BMA model over three machine learning models in daily streamflow forecasting. Considering RMSE values among the best models during testing phase, the best BMA model (i.e., BMA2) enhanced the forecasting accuracy of MARS1, M5Tree4, and KELM3 models by 5.2%, 5.8%, and 3.4% in Hongcheon station. Additionally, the best BMA model (i.e., BMA1) improved the forecasting accuracy of MARS1, M5Tree1, and KELM1 models by 6.7%, 9.5%, and 3.7% in Jucheon station. In addition, the best BMA models in both stations allowed the uncertainty estimation, and produced higher uncertainty of peak flows compared to that of low flows. As one of the most robust and effective tools, therefore, the BMA model can be successfully employed for streamflow forecasting with different antecedent times.

Estimation of daily dissolved oxygen concentration for river water quality using conventional regression analysis, multivariate adaptive regression splines, and TreeNet techniques

The aim of this study was to model the surface water quality of the Broad River Basin, South Carolina. The most suitable two monitoring stations numbered as USGS 02156500 (Near Carlisle) and USGS 02160991 (Near Jenkinsville) were selected for the reason that the river water temperature (WT), pH, and specific conductance (SC), as well as dissolved oxygen (DO) concentration, were simultaneously monitored and recorded at these sites. The monitoring period from September 2016 to August 2017 was taken into account for the modeling studies. The electrical conductivity (EC) values corresponding to the river SC values were calculated. First, the conventional regression analysis (CRA) was applied to three regression forms, i.e., linear, power, and exponential functions, to estimate the river DO concentration. Then, the multivariate adaptive regression splines (MARS) and TreeNet gradient boosting machine (TreeNet) techniques were employed. Three performance statistics, i.e., root means square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe coefficient of efficiency (NS), were used to compare the estimation capabilities of these techniques. The TreeNet technique, which was used for the first time in the modeling of DO concentration, had higher estimation success with the RMSE, MAE, and NS values of 0.182 mg/L, 0.123 mg/L, and 0.990, respectively, for the Carlisle station and 0.313 mg/L, 0.233 mg/L, and 0.965, respectively, for the Jenkinsville station in the training phase. The MARS technique, which had limited availability of its application in the modeling of DO concentration, had higher estimation success with the RMSE, MAE, and NS values of 0.240 mg/L, 0.195 mg/L, and 0.981, respectively, for the Carlisle station and 0.527 mg/L, 0.432 mg/L, and 0.980, respectively, for the Jenkinsville station in the testing phase. Considering the RMSE and MAE values being lower, as well as NS values being higher for the model having an input combination of WT, pH, and EC, the Carlisle station came into prominence. It was concluded that international researchers, who have engaged in the river water quality modeling studies, can favor the MARS and TreeNET techniques without any hesitation and estimate the river DO concentration successfully. The models developed for the Carlisle station were tested with the data sets for the monitoring period from September 2017 to August 2018 at the same station. Similarly, the models developed for the Jenkinsville station were tested with the data sets for the monitoring period from September 2017 to August 2018 at the same station. It was concluded that the models could estimate the river DO concentrations very close to in situ measurements at the same site but for the different monitoring periods, too. Furthermore, the models developed for the Carlisle station were tested with the data sets from the Jenkinsville station for the same monitoring period. Similarly, the models developed for the Jenkinsville station were tested with the data sets from the Carlisle station for the same monitoring period. It was also concluded that the developed models could estimate the river DO concentrations very close to in situ measurements at different monitoring sites but for the same monitoring period on the same river, too. It can be asserted that the models developed for any monitoring site on a river can be employed for another monitoring site on the same river, too, as in the case of the Broad River, South Carolina.

Kernel Extreme Learning Machine: An Efficient Model for Estimating Daily Dew Point Temperature Using Weather Data

Accurate estimation of dew point temperature (Tdew) has a crucial role in sustainable water resource management. This study investigates kernel extreme learning machine (KELM), boosted regression tree (BRT), radial basis function neural network (RBFNN), multilayer perceptron neural network (MLPNN), and multivariate adaptive regression spline (MARS) models for daily dew point temperature estimation at Durham and UC Riverside stations in the United States. Daily time scale measured hydrometeorological data, including wind speed (WS), maximum air temperature (TMAX), minimum air temperature (TMIN), maximum relative humidity (RHMAX), minimum relative humidity (RHMIN), vapor pressure (VP), soil temperature (ST), solar radiation (SR), and dew point temperature (Tdew) were utilized to investigate the applied predictive models. Results of the KELM model were compared with other models using eight different input combinations with respect to root mean square error (RMSE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE) statistical indices. Results showed that the KELM models, using three input parameters, VP, TMAX, and RHMIN, with RMSE = 0.419 °C, NSE = 0.995, and R2 = 0.995 at Durham station, and seven input parameters, VP, ST, RHMAX, TMIN, RHMIN, TMAX, and WS, with RMSE = 0.485 °C, NSE = 0.994, and R2 = 0.994 at UC Riverside station, exhibited better performance in the modeling of daily Tdew. Finally, it was concluded from a comparison of the results that out of the five models applied, the KELM model was found to be the most robust by improving the performance of BRT, RBFNN, MLPNN, and MARS models in the testing phase at both stations.

Advanced machine learning model for better prediction accuracy of soil temperature at different depths

Soil temperature has a vital importance in biological, physical and chemical processes of terrestrial ecosystem and its modeling at different depths is very important for land-atmosphere interactions. The study compares four machine learning techniques, extreme learning machine (ELM), artificial neural networks (ANN), classification and regression trees (CART) and group method of data handling (GMDH) in estimating monthly soil temperatures at four different depths. Various combinations of climatic variables are utilized as input to the developed models. The models’ outcomes are also compared with multi-linear regression based on Nash-Sutcliffe efficiency, root mean square error, and coefficient of determination statistics. ELM is found to be generally performs better than the other four alternatives in estimating soil temperatures. A decrease in performance of the models is observed by an increase in soil depth. It is found that soil temperatures at three depths (5, 10 and 50 cm) could be mapped utilizing only air temperature data as input while solar radiation and wind speed information are also required for estimating soil temperature at the depth of 100 cm.

Spatial Forecasting of Dissolved Oxygen Concentration in the Eastern Black Sea Basin, Turkey

The aim of this study was to model, as well as monitor and assess the surface water quality in the Eastern Black Sea (EBS) Basin stream, Turkey. The water-quality indicators monitored monthly for the seven streams were water temperature (WT), pH, total dissolved solids (TDS), and electrical conductivity (EC), as well as luminescent dissolved oxygen (LDO) concentration and saturation. Based on an 18-month data monitoring, the surface water quality variation was spatially and temporally evaluated with reference to the Turkish Surface Water Quality Regulation. First, the teaching–learning based optimization (TLBO) algorithm and conventional regression analysis (CRA) were applied to three different regression forms, i.e., exponential, power, and linear functions, to predict LDO concentrations. Then, the multivariate adaptive regression splines (MARS) method was employed and three performance measures, namely, mean absolute error (MAE), root means square error (RMSE), and Nash Sutcliffe coefficient of efficiency (NSCE) were used to evaluate the performances of the MARS, TLBO, and CRA methods. The monitoring results revealed that all streams showed the same trend in that lower WT values in the winter months resulted in higher LDO concentrations, while higher WT values in summer led to lower LDO concentrations. Similarly, autumn, which presented the higher TDS concentrations brought about higher EC values, while spring, which presented the lower TDS concentrations gave rise to lower EC values. It was concluded that the water quality of the streams in the EBS basin was high-quality water in terms of the parameters monitored in situ, of which the LDO concentration varied from 9.13 to 10.12 mg/L in summer and from 12.31 to 13.26 mg/L in winter. When the prediction accuracies of the three models were compared, it was seen that the MARS method provided more successful results than the other methods. The results of the TLBO and the CRA methods were very close to each other. The RMSE, MAE, and NSCE values were 0.2599 mg/L, 0.2125 mg/L, and 0.9645, respectively, for the best MARS model, while these values were 0.4167 mg/L, 0.3068 mg/L, and 0.9086, respectively, for the best TLBO and CRA models. In general, the LDO concentration could be successfully predicted using the MARS method with various input combinations of WT, EC, and pH variables.