Sutcliffe Model Efficiency Research Articles

Impact of Climate Change on Soil Water Content in Southern Saskatchewan, Canada

The main objective of this research was to understand the effects of climate change on soil water content (SWC) across the Qu’Appelle River basin in southern Saskatchewan, Canada. The Soil and Water Assessment Tool (SWAT) and output from 11 high-resolution (0.22°) regional climate models (RCM) were used over three 30-year periods: the near future (2021–2050) and distant future (2051–2080) and the historical reference (1975–2005). The RCM data are from the CORDEX North American domain, which employs the RCP8.5 high-emission scenario. SWC was modeled at the hydrological response units (HRU) level and at daily and monthly (warm season only) intervals for 2015–2020. The model was calibrated and validated using SUFI-2 in SWAT-CUP based on observations for streamflow and SWC, including measured data and Soil Moisture Active Passive (SMAP) Level 4 for surface (up to 5 cm deep) soil moisture. Values of the Nash–Sutcliffe model efficiency (NS) ranged from 0.616 and 0.784 and the coefficient of determination (R2) was 0.8 for calibration and 0.82 for validation. Likewise, the correlation coefficients between ground measurements and SWAT were 0.698 and 0.633, respectively. Future climate forcing of the calibrated SWAT model revealed that warmer and drier growing seasons will prevail in the region. Similarly, the ensemble of all RCMs indicated that the mean temperature will increase by 2.1 °C and 3.4 °C for the middle and late periods, respectively, along with a precipitation increase of 10% and 11.2%. SWC is expected to decrease with an increase in potential evapotranspiration, despite an increase in precipitation. Likewise, the annual SWC is expected to decrease by 3.6% and 4% in the middle and late periods, respectively. The monthly SWC changes showed the highest decreases (5.4%) in April in the late period. The spatial pattern of SWC for 11 RCMs was similar such that the northwest and west of the river basin are wetter than the south and east. SWC projections suggest that southern Saskatchewan could experience significant SWC deficiencies in the summer by the end of this century.

Estimation of rainfall-induced surface runoff for the Assam region, India, using the GIS-based NRCS-CN method

ABSTRACT The NRCS-CN method, integrated with GIS and remote sensing, can be used for estimating curve numbers (CN) and surface runoff in geohydrological systems. The study area is divided into 63 sub-basins, and the land use land cover (LULC)-hydrologic soil group (HSG) complex is identified for each sub-basin. The CN values for three antecedent soil moisture (AMC) conditions are calculated and corrected for surface slope variations. The surface runoff depth is determined using the rainfall data for 16 years (2005–2020). The average runoff depth and mean annual precipitation ranges from 444.50 to 1960.55 mm and 936.99 to 3520.55 mm, respectively. For all sub-basins, strong correlations between runoff depth and rainfall (R2 ≥ 0.8) as well as between simulated runoff and measured runoff (R2 ≥ 0.8) are observed. The Nash–Sutcliffe model efficiency coefficient (NSE) values suggest that the model's efficiency is good to satisfactory.

Rainfall-runoff modeling using long short-term memory based step-sequence framework

Rainfall-runoff modeling, a nonlinear time series process, is challenging and important in hydrological sciences. Among the data-driven approaches, those ones based on the long short-term memory (LSTM) network show their promising performance. In this paper, for rainfall-runoff modeling, we propose a novel data-driven framework named long short-term memory based step-sequence (LSTM-SS) framework, which contains m specific models for m-step-ahead runoff predictions. This model uses the sequential information of runoff series and follows the causality in practice: the current runoff is not affected by the later meteorological data. To show its performance and advantages, we test it on 241 basins of the Catchment Attributes and Meteorology for Large-Sample Studies (CAMELS) data set and predict the 7-day-ahead runoff. The results show that our rainfall-runoff models outperform the benchmark (physically-based or data-driven) models significantly employing for the CAMELS data set, including the Sacramento Soil Moisture Accounting Model (SAC-SMA) coupled with the Snow-17 snow routine, a two-layer LSTM network, and a LSTM-based sequence-to-sequence network. For 1-day-ahead runoff predictions, the median of Nash–Sutcliffe model efficiency for the 241 basins provided by our model is 0.85, while that provided by the two-layer LSTM network is 0.65. Furthermore, the results also show that our proposed LSTM-SS framework not only can significantly improve the performance of a single daily runoff prediction, but also has good performance for multiple-step-ahead runoff predictions.

Long-term multi-step ahead forecasting of root zone soil moisture in different climates: Novel ensemble-based complementary data-intelligent paradigms

The root zone soil moisture (RZSM) is essential for monitoring and forecasting agricultural, hydrological, and meteorological systems. Accordingly, researchers are determined to improve robust machine learning (ML) models to increase the accuracy of the RZSM predictions. This paper designed new complementary forecasting paradigms hybridizing Empirical Wavelet Transform (EWT) and two modern ensemble-based ML models, namely, extreme gradient boosting (XGBoost) and categorical boosting (CatBoost), to forecast long-term multi-step ahead daily RZSM in very cold and very warm semi-arid regions of Iran. For this purpose, the required datasets consisting of soil properties and meteorological information were extracted from the satellite datasets during 2005–2020 for Ardabil and Minab sites. Afterward, the significant lags of RZSM time series and optimal influence candidate inputs were sought based on the partial autocorrelation function (PACF) and mutual information techniques, respectively. Selected lagged components of RZSM time series were decomposed using EWT into different sub-sequences and consequently concatenated with candidate inputs to feed the ensemble ML models to forecast one-, three-, and seven-day-ahead RZSM at each case study. The performance of EWT-CatBoost and EWT-XGBoost and their counterpart standalone approaches was firstly evaluated in forecasting one-, three-, and seven-day-ahead RZSM using satellite data in this study and their accuracy were compared with a standalone kernel ridge regression (KRR) and complementary EWT-KRR models based on several statistical metrics (e.g., correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe model efficiency coefficient (NSE)) and diagnostic analysis. The outcomes of testing phase in Ardabil site ascertained that the EWT-CatBoost (for RZSM(t + 1), R= 0.9979, RMSE= 0.0019, and NSE= 0.9985; for RZSM(t + 3), R= 0.9934, RMSE= 0.0035, and NSE= 0.9885; for RZSM(t + 7), R= 0.9489, RMSE= 0.0109, and NSE= 0.8634) outperformed the other models. On the other hand, the EWT-XGBoost model according to its best results (for RZSM(t + 1), R= 0.9911, RMSE= 0.0064, and NSE= 0.9805; for RZSM(t + 3), R= 0.9807, RMSE= 0.0092, and NSE= 0.9589; for RZSM(t + 7), R= 0.9680, RMSE= 0.0120, and NSE= 0.9309) yielded the most promising accuracy in forecasting multi-step ahead daily RZSM followed by the EWT-CatBoost, and EWT-KRR, respectively.

Modeling Groundwater Nitrate Contamination Using Artificial Neural Networks

The scope of the present study is the estimation of the concentration of nitrates (NO3−) in groundwater using artificial neural networks (ANNs) based on easily measurable in situ data. For the purpose of the current study, two feedforward neural networks were developed to determine whether including land use variables would improve the model results. In the first network, easily measurable field data were used, i.e., pH, electrical conductivity, water temperature, air temperature, and aquifer level. This model achieved a fairly good simulation based on the root mean squared error (RMSE in mg/L) and the Nash–Sutcliffe Model Efficiency (NSE) indicators (RMSE = 26.18, NSE = 0.54). In the second model, the percentages of different land uses in a radius of 1000 m from each well was included in an attempt to obtain a better description of nitrate transport in the aquifer system. When these variables were used, the performance of the model increased significantly (RMSE = 15.95, NSE = 0.70). For the development of the models, data from chemical and physical analyses of groundwater samples from wells located in the Kopaidian Plain and the wider area of the Asopos River Basin, both in Greece, were used. The simulation that the models achieved indicates that they are a potentially useful tools for the estimation of groundwater contamination by nitrates and may therefore constitute a basis for the development of groundwater management plans.

Balancing environmental impacts and economic benefits of agriculture under the climate change through an integrated optimization system

The present study proposes a framework to mitigate impact of climate change on the rice production by maximizing the yield while the energy use and ecological impacts on the river ecosystem as the irrigation source are mitigated. Coupled general circulation model- soil and water assessment tool (SWAT) was utilized to project the impact of climate change on the stream flow. Fuzzy physical habitat simulation was applied to develop the ecological impact function of the river. Moreover, a data-driven model was developed to predict the rice yield through changing water and energy consumption. Finally, all the simulations were utilized in the structure of the optimization model in which minimizing loss of the production, greenhouse gas emission by reducing energy use and physical habitat loss were considered as the objectives. Based on the results, the Nash–Sutcliffe model efficiency coefficient of the SWAT is 0.7 that demonstrates its reliability for simulating the impact of climate change on river flow. The optimization model is able to reduce the impact of climate change on yield of production by balancing water and energy use. In the most pessimistic scenario, water use should approximately be reduced 25% for protecting river ecosystem. However, the optimization model approximately increased energy use 16% for preserving the yield of the rice. Conversely, model decreased the energy use 40% compared with the current condition due to increasing water supply. Moreover, physical habitat loss is less than 50% that means the combined optimization model is able to protect river habitats properly.

Prediction of Pile Bearing Capacity Using XGBoost Algorithm: Modeling and Performance Evaluation

The major criteria that control pile foundation design is pile bearing capacity (Pu). The load bearing capacity of piles is affected by the various characteristics of soils and the involvement of multiple parameters related to both soil and foundation. In this study, a new model for predicting bearing capacity is developed using an extreme gradient boosting (XGBoost) algorithm. A total of 200 driven piles static load test-based case histories were used to construct and verify the model. The developed XGBoost model results were compared to a number of commonly used algorithms—Adaptive Boosting (AdaBoost), Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM) using various performance measure metrics such as coefficient of determination, mean absolute error, root mean square error, mean absolute relative error, Nash–Sutcliffe model efficiency coefficient and relative strength ratio. Furthermore, sensitivity analysis was performed to determine the effect of input parameters on Pu. The results show that all of the developed models were capable of making accurate predictions however the XGBoost algorithm surpasses others, followed by AdaBoost, RF, DT, and SVM. The sensitivity analysis result shows that the SPT blow count along the pile shaft has the greatest effect on the Pu.

EPIC model simulation to assess effective agro-ecological practices for climate change mitigation and adaptation in organic vegetable system

Mediterranean agriculture is markedly threatened by climate change and extreme events (drought and flooding). For the first time, the EPIC model was used in a long-term organic vegetable field experiment to evaluate the performance of agro-ecological practices, as adaptation and mitigation measures to cope with climate change in Southern Italy. These practices were a soil hydraulic arrangement (consisting of ridges and flat strips) combined with crop rotation (winter and summer cash crops), organic fertilization (poultry manure vs. no fertilization), and cover crops (pure or in mixture vs. no cover) managed as living mulch, green manure, or flattened by roller crimper. Seven treatments were selected for the simulation procedure. EPIC was calibrated and validated using measured crop yield and soil organic carbon stock values. The statistical metrics of EPIC showed r to be between 0.96 and 0.97, the Nash–Sutcliffe model efficiency between 0.54 and 0.94, and the relative root mean square error between 2 and 18%. Then, the model was run under baseline current climate (1985–2014) and near-future climate change (2015–2044) scenarios. Climate change increased both microbial respiration and nitrate leaching compared to the baseline, while soil organic carbon stock change and nitrous oxide emissions were mainly influenced by agro-ecological practices. Cover crop management could be an effective solution to limit negative climate effects, since it allowed improving summer cash crop yield (32%) and soil organic carbon stock change (2%), and reducing nitrogen losses (–34%), as compared to the no-cover-crop system. Finally, under climate change, green manure increased microbial respiration (5%) and reduced nitrogen losses (− 19%), compared to roller crimper flattening. Our findings indicated that the tested agro-ecological practices contribute to re-designing new climate change-resilient vegetable systems, by involving the stakeholders in promoting a co-innovation and co-research knowledge platform and fine-tuning agro-ecological practices in a wider range of environments.

Predicting Compressive Strength of Concrete Containing Industrial Waste Materials: Novel and Hybrid Machine Learning Model

In the construction and cement manufacturing sectors, the development of artificial intelligence models has received remarkable progress and attention. This paper investigates the capacity of hybrid models conducted for predicting the compressive strength (CS) of concrete where the cement was partially replaced with ground granulated blast‐furnace slag (FS) and fly ash (FA) materials. Accurate estimation of CS can reduce the cost and laboratory tests. Since the traditional method of calculation CS is complicated and requires lots of effort, this article presents new predictive models called SVR − PSO and SVR − GA, that are a hybridization of support vector regression (SVR) with improved particle swarm algorithm (PSO) and genetic algorithm (GA). Furthermore, the hybrid models (i.e., SVR − PSO and SVR − GA) were used for the first time to predict CS of concrete where the cement component is partially replaced. The improved PSO and GA are given essential roles in tuning the hyperparameters of the SVR model, which have a significant influence on model accuracy. The suggested models are evaluated against extreme learning machine (ELM) via quantitative and visual evaluations. The models are evaluated using eight statistical parameters, and then the SVR‐PSO has provided the highest accuracy than comparative models. For instance, the SVR − PSO during the testing phase provided fewer root mean square error (RMSE) with 1.386 MPa, a higher Nash–Sutcliffe model efficiency coefficient (NE) of 0.972, and lower uncertainty at 95% (U95) with 28.776%. On the other hand, the SVR − GA and ELM models provide lower accuracy with RMSE of 2.826 MPa and 2.180, NE with 0.883 and 0.930, and U95with 518.686 183.182, respectively. Sensitivity analysis is carried out to select the influential parameters that significantly affect CS. Overall, the proposed model showed a good prediction of CS of concrete where cement is partially replaced and outperformed 14 models developed in the previous studies.

Reducing impacts of rice fields nitrate contamination on the river ecosystem by a coupled SWAT reservoir operation optimization model

The present study proposes a multipurpose reservoir operation optimization for mitigating impact of rice fields’ contamination on the downstream river ecosystem. The developed model was applied in the Tajan River basin in Mazandaran Province, Iran, in which the rice is the main crop. We used soil and water assessment tool (SWAT) to simulate inflow of the reservoir and nitrate load at downstream river reach. Nash–Sutcliffe model efficiency coefficient was used to measure the robustness of SWAT. NSE indicated that SWAT is acceptable to simulate nitrate load of the rice fields. The results of SWAT was applied in the structure of a multipurpose reservoir operation optimization in which three metaheuristic algorithms including differential evolution algorithm, particle swarm optimization and biogeography-based algorithm were utilized in the optimization process. Reliability index, mean absolute error and failure index were used to measure the robustness of the optimization algorithms. Fuzzy Technique for Order of Preference by Similarity to Ideal Solution was utilized to select the best algorithm. Based on results, particle swarm optimization is the best method to optimize reservoir operation in the case study. The reliability index and mean absolute error for water supply are 0.6 and 5 million cubic meters, respectively. Furthermore, the failure index of contamination is 0.027. Hence, it could be concluded that the proposed optimization system is reliable and robust to mitigate losses and nitrate contamination simultaneously. However, its performance is not perfect for minimizing impact of contamination in all the simulated months.

Insights into green roof modeling using SWMM LID controls for detention-based designs

Rainfall–runoff responses were observed in a laboratory environment using a rainfall simulator and a 7.43 m2 green roof cassette equipped with weighing lysimeters. SWMM LID controls were developed for various green roof profile configurations based on the physical properties of the composite materials. Unknown parameters affecting the drainage layer were adjusted in calibration. The cassette was modeled both as a typical Green Roof LID control using Manning’s equation at the drainage layer and a Bioretention LID control using an orifice equation in the drainage layer. Key parameters from a sensitivity analysis that were not directly measured were Manning’s roughness of the drainage layer, the drainage coefficient at the orifice, and the conductivity slope (HCO). The hydraulics of roof drains were considered by varying the width of the drain outlet from 0.25 m–1.22 m. During calibration and validation of multiple events, SWMM modeling resulted in a good fit compared to observed results (Nash–Sutcliffe model efficiency coefficient values of 0.70–0.89). Key limitations of SWMM green roof modeling are discussed with suggested improvements for future consideration.

Short-Term River Flood Forecasting Using Composite Models and Automated Machine Learning: The Case Study of Lena River

The paper presents a hybrid approach for short-term river flood forecasting. It is based on multi-modal data fusion from different sources (weather stations, water height sensors, remote sensing data). To improve the forecasting efficiency, the machine learning methods and the Snowmelt-Runoff physical model are combined in a composite modeling pipeline using automated machine learning techniques. The novelty of the study is based on the application of automated machine learning to identify the individual blocks of a composite pipeline without involving an expert. It makes it possible to adapt the approach to various river basins and different types of floods. Lena River basin was used as a case study since its modeling during spring high water is complicated by the high probability of ice-jam flooding events. Experimental comparison with the existing methods confirms that the proposed approach reduces the error at each analyzed level gauging station. The value of Nash–Sutcliffe model efficiency coefficient for the ten stations chosen for comparison is 0.80. The other approaches based on statistical and physical models could not surpass the threshold of 0.74. Validation for a high-water period also confirms that a composite pipeline designed using automated machine learning is much more efficient than stand-alone models.

Deep learning model for daily rainfall prediction: case study of Jimma, Ethiopia

Abstract Rainfall prediction is a critical task because many people rely on it, particularly in the agricultural sector. Rainfall forecasting is difficult due to the ever-changing nature of weather conditions. In this study, we carry out a rainfall predictive model for Jimma, a region located in southwestern Oromia, Ethiopia. We propose a Long Short-Term Memory (LSTM)-based prediction model capable of forecasting Jimma's daily rainfall. Experiments were conducted to evaluate the proposed models using various metrics such as Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Nash–Sutcliffe model efficiency (NSE), and R2, and the results were 0.01, 0.4786, 0.81 and 0.9972, respectively. We also compared the proposed model with existing machine-learning regressions like Multilayer Perceptron (MLP), k-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Tree (DT). The RMSE of MLP was the lowest of the four existing learning models i.e., 0.03. The proposed LSTM model outperforms the existing models, with an RMSE of 0.01. The experimental results show that the proposed model has a lower RMSE and a higher R2.

The wave overtopping load on landward slopes of grass-covered flood defences: Deriving practical formulations using a numerical model

Overtopping waves exert a high hydraulic load on the landward slopes of flood defences leading to erosion of the grass cover and finally to a dike breach. The hydraulic load is an important variable in erosion models and a detailed description of the load is necessary to determine where and when the grass cover erodes. We use a numerical model to simulate the flow of a single overtopping event over a flood defence with a grass-covered crest and landward slope. The model results show that the flow velocity, the shear stress and the pressure are maximal at the landward toe and can be used to describe grass erosion by shear forces. For steep slopes, the flow separates at the crest line and impacts on the upper slope. The normal stress is maximal at the location of impact and describes the grass erosion by normal forces. Practical formulations are developed for the maximum flow velocity, the maximum pressure, the maximum shear stress, the maximum normal stress and the impact location using three main design parameters for the landward slope: the overtopping volume, the slope steepness and the slope length. The formulations are able to accurately predict the overtopping load with Nash–Sutcliffe model efficiency factors between 0.41 and 0.90. The model output and these new formulations are used to calculate the erosive power of the overtopping waves predicted by eight erosion indices to show how the simulated load can be used in erosion models.

Application of PCSWMM for the 1-D and 1-D–2-D Modeling of Urban Flooding in Damansara Catchment, Malaysia

Coupled with climate change, the urbanization-driven increase in the frequency and intensity of floods can be seen in both developing and developed countries, and Malaysia is no exemption. As part of flood hazard mitigation, this study aimed to simulate the urban flood scenarios in Malaysia’s urbanized catchments. The flood simulation was performed using the Personal Computer Storm Water Management Model (PCSWMM) modeling of the Damansara catchment as a case study. An integrated hydrologic-hydraulic model was developed for the 1-D river flow modeling and 1-D–2-D drainage overflow modeling. The reliability of the 1-D river flow model was confirmed through the calibration and validation, in which the water level in TTDI Jaya was satisfactorily predicted, supported by the coefficient of determination (R2), Nash–Sutcliffe model efficiency coefficient (NSE), and relative error (RE). The performance of the 1-D–2-D model was further demonstrated based on the flood depth, extent, and risk caused by the drainage overflow. Two scenarios were tested, and the comparison results showed that the current drainage effectively reduced the drainage overflow due to the increased size of drains compared to the historic drainage in 2015. The procedure and findings of this study could serve as references for the application in flood mitigation planning worldwide, especially for developing countries.

Assessment of Data-based Models (ANN, ANFIS and SVR) for Estimation of Exchangeable Sodium Percentage (ESP) of Bafra Plain Soils

ABSTRACT The objective of the present study was to estimate the exchangeable sodium percentage (ESP) of the soil from the Bafra plain utilizing easily determined soil characteristics (EC and pH) with the use of artificial intelligence-based models. A total of 448 soil samples were taken from different points of the study area. Artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector regression (SVR) models were developed and compared. The present database was randomly divided into training and test data sets (70:30). Coefficient of determination (R2), normalized root mean square error (NRMSE), normalized mean absolute error (NMAE), Nash and Sutcliffe model efficiency (NS) and Akaike’s Information Criterion (AIC) were used as statistical performance indicators to assess the accuracy of the models. Present findings revealed that both ANN (R2 = 0.91, NMAE = 0.21, NRMSE = 0.05, NS = 0.91 and AIC = 191.86) and ANFIS (R2 = 0.91, NMAE = 0.21, NRMSE = 0.05, NS = 0.91 and AIC = 195.51) models had greater general estimation performance than SVR (R2 = 0.89, NMAE = 0.49, NRMSE = 0.08, NS = 0.74 and AIC = 334.57) model. Comparative assessments revealed that ANN and ANFIS approaches could successfully be used in estimation of ESP from EC and pH data. It was concluded based on present findings that artificial intelligence-based techniques could reliably be used in estimation of soil ESP as a promising alternative of traditional approaches.

Evaluating the capability of hybrid data-driven approaches to forecast monthly streamflow using hydrometric and meteorological variables

AbstractStreamflow forecasting, as one of the most important issues in hydrological studies, plays a vital role in several aspects of water resources management such as reservoir operation, water allocation, and flood forecasting. In this study, wavelet-gene expression programming (WGEP) and wavelet-M5 prime (WM5P) techniques, as two robust artificial intelligence (AI) models, were applied for forecasting the monthly streamflow in Khoshkroud and Polroud Rivers located in two basins with the same names. Results of hybrid AI techniques were compared with those achieved by two stand-alone models of GEP and M5P. Seven combinations of hydrological (H) and meteorological (M) variables were considered to investigate the effect of climatic variables on the performance of the proposed techniques. Moreover, the performance of both stand-alone and hybrid models were evaluated by statistical criteria of correlation of coefficient, root-mean-square error, index of agreement, the Nash–Sutcliffe model efficiency coefficient, and relative improvement. The statistical results revealed that there is a dependency between ‘the M5P and GEP performance’ and ‘the geometric properties of basins (e.g., area, shape, slope, and river network density)’. It was found that a preprocessed technique could increase the performance of M5P and GEP models. Compared to the stand-alone techniques, the hybrid AI models resulted in higher performance. For both basins, the performance of the WM5P model was higher than the WGEP model, especially for extreme events. Overall, the results demonstrated that the proposed hybrid AI approaches are reliable tools for forecasting the monthly streamflow, while the meteorological and hydrometric variables are taken into account.

Impact of Stream-Groundwater Interactions on Peak Streamflow in the Floods

Floods are the one of the most significant natural disasters, with a damaging effect on human life and properties. Recent global warming and climate change exacerbate the flooding by increasing the frequency and intensity of severe floods. This study explores the role of groundwater during the floods at the Miho catchment in South Korea. The Hydrological-Ecological Integrated watershed-scale Flow model (HEIFLOW) model is used for the flood simulations to investigate the impact of groundwater and streamflow interactions during floods. The HEIFLOW model is assessed by the Nash–Sutcliffe model efficiency coefficient (NSE) and Root Mean Square Error (RMSE) for the surface water and groundwater domains, respectively. The model evaluation shows the acceptable model performance (0.64 NSE and 0.25 m–2.06 m RMSE) with the hourly time steps. The HEIFLOW shows potential as one of the methods for the flood risk management in South Korea. The major findings of this study indicate that the stream runoff at the Miho catchment is highly affected by the groundwater flows during the dry and flood seasons. Thus, the interactions between surface water and groundwater domains should be fully considered to mitigate the water hazards at the catchment scale.

Predicting relative energy dissipation for vertical drops equipped with a horizontal screen using soft computing techniques

AbstractThis study was designed to evaluate the ability of Artificial Intelligence (AI) methods including ANN, ANFIS, GRNN, SVM, GP, LR, and MLR to predict the relative energy dissipation (ΔE/Eu) for vertical drops equipped with a horizontal screen. For this study, 108 experiments were carried out to investigate energy dissipation. In the experiments, the discharge rate, drop height, and porosity of the screens were varied. Parameters yc/h, yd/yc, and p were input variables, and ΔE/Eu was the output variable. The efficiencies of the models were compared using the following metrics: correlation coefficient (CC), mean absolute error (MAE), root-mean-square error (RMSE), Normalized root mean square error (NRMSE) and Nash–Sutcliffe model efficiency (NSE). Results indicate that the performance of the ANFIS_gbellmf based model with a CC value of 0.9953, RMSE value of 0.0069, MAE value of 0.0042, NRMSE value as 0.0092 and NSE value as 0.9895 was superior to other applied models. Also, a linear regression yielded CC = 0.9933, RMSE = 0.0083, and MAE = 0.0067. This linear model outperformed multiple linear regression models. Results from a sensitivity study suggest that yc/h is the most effective parameter for predicting ΔE/Eu.

An Improved Multivariate Weather Prediction Model Using Deep Neural Networks and Particle Swarm Optimisation

Accurate weather prediction is always a challenge for meteorologists. This paper suggests a Deep Neural Network (DNN) model to predict minimum and maximum values of temperature based on various weather parameters such as humidity, dew point, and wind speed. Particle Swarm Optimisation (PSO) algorithm is applied to select relevant and important features of the datasets to improve the prediction accuracy of the model. The grid search algorithm is employed to determine the hyperparameters of the proposed DNN model. The statistical indicators Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, Nash–Sutcliffe model efficiency coefficient, and Correlation Coefficient are used to evaluate the accuracy of the prediction model. Performance comparison of the proposed model is performed with the Support Vector Machine (SVM) and Vector Autoregression (VAR) models. The experimental outcomes show that the proposed model optimised using PSO achieves better prediction accuracy than traditional approaches.