Sutcliffe Efficiency Coefficient Research Articles

A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration

Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (NES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Qt-n) and suspended sediment concentration (St-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (St-1, St-2, St-3, St-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest NES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest NES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships.

Modeling of Grapefruit External Color as Affected by Drought Stress

Grapefruit are well-adapted to arid and warm climatic conditions, but well-irrigated trees usually produce better-quality fruits. Because water is a major component of the fruits, there is a strong relationship between drought stress and fruits quality traits such as fruits size, external fruits color, and juice quality. The object of this study was to develop a computer model to predict postharvest external grapefruit color as a function of drought stress. During model development, drought stress was quantified using a concise water balance model based on crop evapotranspiration, precipitation, and irrigation. Data collected from Murcia, Spain, during the 2007 and 2008 growing seasons were used for model development, and the model was optimized by comparing model predictions and observations for each growing season. The root mean square error and Nash and Sutcliffe coefficient of efficiency (NSE) were used to evaluate model performance. Then, the model was evaluated with independent data collected from Florida during the 2005–06 growing season. A second-order polynomial relationship was found between external fruits color and drought stress, with less drought stress resulting in better external fruits color. Model optimization revealed good model performance for predicting external fruits color in Murcia, with NSE values of 0.975 and 0.979 for the 2007 and 2008 growing seasons, respectively. Model evaluation with the data from Florida showed that model predictions were reliable, with a NSE value of 0.984. A robust model to predict external grapefruit color as affected by drought stress was developed during the present study and could be potentially applied to supply information for suitable irrigation management of various grapefruit cultivars grown under different climatic conditions. Model performance could be confirmed by future research with data collection during further multiple seasons for different cultivars and a range of climatic conditions.

Deep learning approach for one-hour ahead forecasting of weather data

ABSTRACT Weather is made up of multiple parameters, including solar radiation (SR), atmospheric pressure (AP), soil temperature (ST), atmospheric temperature (AT), wind speed (WS), relative humidity (RH), and sunshine duration (SD). These factors are also crucial for the renewable energy sector, solar simulation, agriculture, air pollution, water supply and distribution, avalanche warning, forestry, and town and regional planning. A deep learning method based on a neural network with Long Short-Term Memory (LSTM) was employed in this investigation for one-hour-ahead weather data forecasting. The ability of the LSTM model was compared with the Adaptive Neuro-Fuzzy Inference System (ANFIS) with that of the fuzzy c-means (FCM), Autoregressive Integrated Moving Average (ARIMA) model, and the Autoregressive Moving Average (ARMA) model. Mean absolute error (MAE), correlation coefficient (R), root means square error (RMSE), average bias, Nash – Sutcliffe efficiency coefficient (NSE), and mean absolute percentage error (MAPE) were selected as evaluation criteria. Results indicated that the proposed LSTM model presented good enough results compared to other used methods. 7 different types of meteorological data from a total of 4 years (35040 hours) were divided into 25% test data and 75% training data for the models. The best result was obtained for the hourly ST estimation of Adana province using the LSTM method, the MAE, RMSE, R, bias, NSE, and MAPE values were computed as 0.016°C, 0.078°C, 0.9999, −0.00018°C, 0.0805%, and 0.9999, respectively. On the other hand, the worst result was obtained for the hourly SD for Mardin province when ARIMA was used, and the statistical measures were derived as 0.128 hours for MAE, 0.215 hours for RMSE, 0.8851 for R, 0.00091 hours for bias, and 0.7657 for NSE. In this regard, it is demonstrated that the LSTM technique outperformed the other models in terms of all-weather data estimates and delivered highly sensitive outcomes.

Machine Learning Approaches for One-Day Ahead Soil Temperature Forecasting

Present study investigates the capabilities of six distinct machine learning techniques such as ANFIS network with fuzzy c-means (ANFIS-FCM), grid partition (ANFIS-GP), subtractive clustering (ANFIS-SC), feed-forward neural network (FNN), Elman neural network (ENN), and long short-term memory (LSTM) neural network in one-day ahead soil temperature (ST) forecasting. For this aim, daily ST data gathered at three different depths of 5 cm, 50 cm, and 100 cm from the Sivas meteorological observation station in the Central Anatolia Region of Turkey was used as training and testing datasets. Forecasting values of the machine learning models were compared with actual data by assessing with respect to four statistic metrics such as the mean absolute error, root mean square error (RMSE), Nash−Sutcliffe efficiency coefficient, and correlation coefficient (R). The results showed that the ANFIS-FCM, ANFIS-GP, ANFIS-SC, ENN, FNN and LSTM models presented satisfactory performance in modeling daily ST at all depths, with RMSE values ranging 0.0637-1.3276, 0.0634-1.3809, 0.0643-1.3280, 0.0635-1.3186, 0.0635-1.3281, and 0.0983-1.3256 °C, and R values ranging 0.9910-0.9999, 0.9903-0.9999, 0.9910-0.9999, 0.9911-0.9999, 0.9910-0.9999 and 0.9910-0.9998 °C, respectively.

Modeling the relationship between air temperature and grapefruit quality traits.

Consumers of grapefruit require consistent fruit quality with a good physical appearance and taste. The air temperature during the growing season affects both the external (external color index (ECI)) and internal (titratable acidity (TA) and total soluble solids ratio (TSS/TA)) fruit quality of grapefruit. The objective of this study was to develop computer models that encompass the relationship between preharvest air temperature and fruit quality to predict fruit quality of grapefruit at harvest. There was a logarithmic relationship between the number of days with a daily minimum air temperature ≤13 °C and ECI, with a greater number of days resulting in higher ECI. In addition, there was a second-order polynomial relationship between the number of hours ≥21 °C and both TA and TSS/TA, with a greater number of hours resulting in lower TA and higher TSS/TA. Model performance for predicting the ECI, TA, and TSS/TA during 2004-05 and 2005-06 growing seasons was good, with Nash and Sutcliffe coefficient of efficiency (NSE) values for each season of 0.835 and 0.917 respectively for ECI, 0.896 and 0.965 respectively for TA and 0.898 and 0.966 respectively for TSS/TA. Applying the model to statistical survey data covering 13 growing seasons demonstrated that the TSS/TA model was robust. Statistical models were developed that predicted the development of grapefruit ECI, TA, and TSS/TA. The TSS/TA model was confirmed after application to long-term statistical survey data covering 13 growing seasons. © 2022 Society of Chemical Industry.

Apply Machine Learning to Predict Saltwater Intrusion in the Ham Luong River, Ben Tre Province

Saltwater intrusion is a major problem particularly in the Mekong Delta, Việt Nam. In order to better manage the salinity problem, it is important to be able to predict the saltwater intrusion in rivers. The objective of this research is to apply several machine learning algorithms, including Multiple Linear Regression (MLR), Random Forest Regression (RFR), Artificial Neural Networks (ANN) for predicting the saltwater intrusion in Ham Luong River, Ben Tre Province. The input data is is composed of 207 weekly saltwater intrusion data points from 2012 to 2020. Yearly salinity was measured during the 23 weeks of the dry season, from January to June. The Nash - Sutcliffe efficiency coefficient (NSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) are used to evaluate the performances of machine learning algorithms. The research results indicated that the ANN model achieved a high performance for salinity forecasting with NSE = 0.907, RMSE = 0.11, MAE = 0.08 for training period, NSE = 0.842, RMSE = 1.16, MAE = 0.11 for testing period. The findings of this study suggest that the ANN algorithm is a promising tool to forecast salinity in Ham Luong River.
 
 
 

An Improved Empirical Model for Estimating the Geometry of the Soil Wetting Front with Surface Drip Irrigation

Wetting pattern geometry is useful in determining the spacing between emitters and the irrigation time in drip irrigation systems. This research aimed to generate an empirical model to estimate the width and depth of the wetting front in surface drip irrigation based on experimental tests in a cube-shaped container with transparent walls in soils with a sandy clay loam texture, with hydraulic conductivities from 2.316 to 3.945 cm h−1, and organic matter contents from 1.7 to 2.8%, and different irrigation conditions: discharge rates of 1.44, 2.90, 3.00, 3.75, and 4.00 L h−1, initial moisture levels between permanent wilting point and field capacity, and irrigation times from 0.58 to 9.50 h. The experimental conditions and the strategy for measuring the wetting front and soil moisture are detailed so the experiment is verifiable. The proposed model performed better than five other empirical models, with average values of 3 cm for the root mean square error and 0.88 for the Nash and Sutcliffe efficiency coefficient. The generated model is efficient and simple and can be a very useful tool for the design and operation of surface drip irrigation systems in soils with conditions similar to those of this study.

Estimating land evapotranspiration from potential evapotranspiration constrained by soil water at daily scale

Accurate simulation of evapotranspiration is of substantial importance to hydrology, ecology, agriculture, and water resources management. Evapotranspiration is equal to the fraction of potential evapotranspiration (PET) constrained by soil water. PET can be calculated from meteorological observations with a wide global distribution and high density. However, it is necessary to determine how to accurately simulate daily evapotranspiration through PET. We have developed a non-linear function for simulating evapotranspiration through PET constrained by soil water at daily scale. The evaluation results show that the accuracy of the evapotranspiration simulation using the non-linear function was higher than that of linear relations and complementary relationship (CR) methods. In the temperature-based PET equations, the Hargreaves-Samani equation was the closest to the Penman-Monteith calculation values. The simulation accuracy of the CR methods obviously improved after parameter calibration. The accuracy has a large variability at the global scale. Daily evapotranspiration can be simulated with PET data in some regions with a high accuracy (Nash and Sutcliffe efficiency coefficient > 0.60), including most regions of Eurasia, eastern and southern North America, and northern South America. However, other regions showed a poor performance (Nash and Sutcliffe efficiency coefficient < 0.20), including western North America, the Mediterranean region, and the eastern and western coastal regions of Australia. Our results indicate that the accurate simulation of daily evapotranspiration can be achieved based on meteorological data in most regions of the world. Owing to the wide distribution of global meteorological observations, the accurate simulation of the daily evapotranspiration method proposed in this study can be applied in other regions across the globe.

Reservoir Inflow Prediction by Employing Response Surface-Based Models Conjunction with Wavelet and Bootstrap Techniques

Reservoir inflow prediction is a vital subject in the field of hydrology because it determines the flood event. The negative impact of the floods could be minimized greatly if the flood frequency is predicted accurately in advance. In the present study, a novel hybrid model, bootstrap quadratic response surface is developed to test daily streamflow prediction. The developed bootstrap quadratic response surface model is compared with multiple linear regression model, first-order response surface model, quadratic response surface model, wavelet first-order response surface model, wavelet quadratic response surface model, and bootstrap first-order response surface model. Time series data of monsoon season (1 July to 30 September) for the year 2010 of the Chenab river basin are analyzed. The studied models are tested by using performance indices: Nash–Sutcliffe coefficient of efficiency, mean absolute error, persistence index, and root mean square error. Results reveal that the proposed model, i.e., bootstrap quadratic response surface shows good performance and produces optimum results for daily reservoir inflow prediction than other models used in the study.

Comparison of hydrological model ensemble forecasting based on multiple members and ensemble methods

Abstract Ensemble hydrologic forecasting which takes advantages of multiple hydrologic models has made much contribution to water resource management. In this study, four hydrological models (the Xin’anjiang model (XAJ), Simhyd, GR4J, and artificial neural network (ANN) models) and three ensemble methods (the simple average, black box-based, and binomial-based methods) were applied and compared to simulate the hydrological process during 1979–1983 in three representative catchments (Daixi, Hengtangcun, and Qiaodongcun). The results indicate that for a single model, the XAJ model and the GR4J model performed relatively well with averaged Nash and Sutcliffe efficiency coefficient (NSE) values of 0.78 and 0.83, respectively. For the ensemble models, the results show that the binomial-based ensemble method (dynamic weight) outperformed with water volume error reduced by 0.8% and NSE value increased by 0.218. The best performance on runoff forecasting occurs in the Hengtang catchment by integrating four hydrologic models based on binomial ensemble method, achieving the water volume error of 2.73% and NSE value of 0.923. Finding would provide scientific support to water engineering design and water resources management in the study areas.

Modelling of total dissolved solids in water supply systems using regression and supervised machine learning approaches

Monitoring of water quality through accurate predictions provides adequate information about water management. In the present study, three different modelling approaches: Gaussian process regression (GPR), backpropagation neural network (BPNN) and principal component regression (PCR) models were used to predict the total dissolved solids (TDS) as water quality indicator for the water quality management. The performance of each model was evaluated based on three different sets of inputs from groundwater (GW), surface water (SW) and drinking water (DW). The GPR, BPNN and PCR models used in this study gave an accurate prediction of the observed data (TDS) in GW, SW and DW, with the R2 consistently greater than 0.850. The GPR model gave a better prediction of TDS concentration, with an average R2, MAE and RMSE of 0.987, 4.090 and 7.910, respectively. For the BPNN, an average R2, MAE and RMSE of 0.913, 9.720 and 19.137, respectively, were achieved, while the PCR gave an average R2, MAE and RMSE of 0.888, 11.327 and 25.032, respectively. The performance of each model was assessed using efficiency based indicators such as the Nash and Sutcliffe coefficient of efficiency (ENS) and the index of agreement (d). The GPR, BPNN and PCR models, respectively, gave an ENS of (0.967, 0.915, 0.874) and d of (0.992, 0.977, 0.965). It is understood from this study that advanced machine learning approaches (e.g. GPR and BPNN) are appropriate for the prediction of water quality indices and would be useful for future prediction and management of water quality parameters of various water supply systems in mining communities where artificial intelligence technology is yet to be fully explored.

Soil water infiltration under different land use conditions: in situ tests and modeling

ABSTRACT The efficiency and suitability of different models to estimate infiltration rates in Ferralic Arenosols and Rhodic Ferralsols in southern Brazil are evaluated in this paper. The influence of nine types of land use and soil management practices on infiltration modeling is also assessed. Model parameterization was performed fitting 42 experimental infiltration curves obtained by in situ tests with a double-ring infiltrometer. Soil characterization was also performed in laboratory. The results were assessed using basic statistical descriptors and model accuracy indicators (Nash and Sutcliffe efficiency coefficient and root mean square error). The investigated models satisfactorily simulated the infiltration rates and the most accurate model was modified Kostiakov, followed by the Horton; Singh and Yu; modified Holtan; Holtan; Philip; Green and Ampt/Mein and Larson and Kostiakov. Different types of land uses and soil management practices significantly affect the infiltration rates, mainly those combination with great presence of macroporosity that resulted in an erratic infiltration behavior and affected the infiltration model accuracy.

Simulation and evaluation of actual evapotranspiration based on inverse hydrological modeling at a basin scale

Reliable estimation of actual evapotranspiration (AET) is essential for hydrological, ecological, and land-surface models. The water balance method is a useful tool for estimating AET. However, it usually neglects soil moisture (SM), which is a dominant factor in AET simulation. Based on field observations, an inverse hydrological modeling method was proposed for regional AET simulation. The method can be applied to estimate AET in other basins, where observations of SM are available. A nonlinear relationship between AET and potential evapotranspiration, a soil water constraint factor, was developed and calibrated for the studied basin. Results of the AET evaluation indicated this relationship was able to estimate AET accurately for both monthly and two-week series, as the Nash and Sutcliffe efficiency coefficient (NSE) was 0.903 and 0.613, respectively. The meteorologically based complementary relationship (CR) method was also able to estimate monthly AET accurately, in particular the revised CR method. But it showed poor performance when estimating AET at a shorter timescale. The performance of the revised CR method with a calibrated parameter was better than that of the initial CR method, as the NSE improved from 0.52 to 0.70. Overall, the performance of the nonlinear relationship with calibrated parameters was better than that of the CR method. In conclusion, monthly AET can be accurately estimated using the CR method based only on meteorological data.

Prediction of the sodium absorption ratio using data-driven models: a case study in Iran

ABSTRACTIn this investigation, two data-driven models, i.e., Gaussian Process (GP) and Support Vector Machine (SVM), were used to predict the sodium absorption ratio (SAR) in three sub-watersheds (Khorramabad, Biranshahr, and Alashtar) in Iran. A comparison was also done with these data-driven models with Artificial Neural Network (ANN). The parameters total dissolved solids, electrical conductivity, pH value, CO3, HCO3, chlorine (Cl), SO4, calcium (Ca), magnesium (Mg), sodium (Na), and potassium (K) were used as input variables and SAR as output. For SVM and GP regression, two kernel functions (radial-based kernel and Person VII kernel function) were used. The results from this investigation suggest that the ANN model (correlation coefficient [CC], root mean square error [RMSE], Nash–Sutcliffe coefficient of efficiency [NSC], and mean absolute relative error [MARE] = 0.9966, 0.0286, 0.9906, and 0.0194) is more precise as compared to the GP (CC, RMSE, NSC, and MARE = 0.9570, 0.2982, 0.8288, and 0.3705) and SVM (CC, RMSE, NSC, and MARE = 0.9948, 0.0365, 0.9847, and 0.063). Among GP and SVM, SVM with PUK kernel is more accurate for estimating the SAR of the watershed. Thus, ANN is a technique which could be used for predicting the SAR for given study area.

Performance evaluation of AquaCrop in simulating soil water storage, yield, and water productivity of rainfed soybeans (Glycine max L. merr) in Ile-Ife, Nigeria

In this study, experiments were carried out for two seasons at the teaching and research farms, Obafemi Awolowo, Nigeria to evaluate the performance of FAO AquaCrop version 5.0 in simulating canopy cover, soil water storage, above ground biomass, evapotranspiration, grain yield and water productivity of soybeans (TGX 1448 2E) under rainfed conditions. The Experimental treatments consisted of conventional and six water conservation practices: Tied ridges; Mulching; Bund; Tied ridges plus mulch; Tied ridges plus bund and Bund plus mulch. The experimental treatments were arranged in randomised complete block design with four replicates. The 2012 and 2011 data sets were used for calibration and validation respectively. The performance of AquaCrop was tested using the regression coefficient (b), coefficient of determination (R2), Root mean square error (RMSE), Normalised root mean square error (NRMSE), Nash and Sutcliffe efficiency coefficient (EF), Willmott’s index of agreement (d-index) and percentage bias (PBIAS). AquaCrop simulated canopy cover adequately for the two seasons, 0.95 ≤ b ≤ 0.99; R2 ≥ 0.95 and RMSE ≤ 11.6%. The model captured well the variability in soil water storage with 0.95 ≤ b ≤ 1.01; R2 ≥ 0.74 and RMSE ≤ 10.2 mm. AquaCrop simulated evapotranspiration with R2 = 0.66 and RMSE = 64.6 mm. The model simulated dry above ground biomass with RMSE ≤ 0.25 t ha−1 and d-index ≥ 0.98. Grain yield was simulated with b = 1.01; R2 = 0.99; RMSE of 0.03 t ha−1d-index = 1.00 and the maximum deviation between the simulated and predicted grain yields is 3%. The water productivity was simulated with R2 = 0.78 and RMSE = 0.08 kg m-3. Considering the overall performance, the AquaCrop model is adequate in simulating canopy cover, dry above ground biomass and grain yield. However, it has low aptitude in simulating evapotranspiration and water productivity of rainfed soybeans under soil surfaces management practices.

Effects of Climate Change and Human Activities on Soil Erosion in the Xihe River Basin, China

Climate change and human activities are the major factors affecting runoff and sediment load. We analyzed the inter-annual variation trend of the average rainfall, air temperature, runoff and sediment load in the Xihe River Basin from 1969–2015. Pettitt’s test and the Soil and Water Assessment Tool (SWAT) model were used to detect sudden change in hydro-meteorological variables and simulate the basin hydrological cycle, respectively. According to the simulation results, we explored spatial distribution of soil erosion in the watershed by utilizing ArcGIS10.0, analyzed the average erosion modulus by different type of land use, and quantified the contributions of climate change and human activities to runoff and sediment load in changes. The results showed that: (1) From 1969–2015, both rainfall and air temperature increased, and air temperature increased significantly (p &lt; 0.01) at 0.326 °C/10 a (annual). Runoff and sediment load decreased, and sediment load decreased significantly (p &lt; 0.01) at 1.63 × 105 t/10 a. In 1988, air temperature experienced a sudden increase and sediment load decreased. (2) For runoff, R2 and Nash and Sutcliffe efficiency coefficient (Ens) were 0.92 and 0.91 during the calibration period and 0.90 and 0.87 during the validation period, for sediment load, R2 and Ens were 0.60 and 0.55 during the calibration period and 0.70 and 0.69 during the validation period, meeting the model’s applicability requirements. (3) Soil erosion was worse in the upper basin than other regions, and highest in cultivated land. Climate change exacerbates runoff and sediment load with overall contribution to the total change of −26.54% and −8.8%, respectively. Human activities decreased runoff and sediment load with overall contribution to the total change of 126.54% and 108.8% respectively. Runoff and sediment load change in the Xihe River Basin are largely caused by human activities.

A Comparative Study of Groundwater Level Forecasting Using Data-Driven Models Based on Ensemble Empirical Mode Decomposition

The reliable and accurate prediction of groundwater levels is important to improve water-use efficiency in the development and management of water resources. Three nonlinear time-series intelligence hybrid models were proposed to predict groundwater level fluctuations through a combination of ensemble empirical mode decomposition (EEMD) and data-driven models (i.e., artificial neural networks (ANN), support vector machines (SVM) and adaptive neuro fuzzy inference systems (ANFIS)), respectively. The prediction capability of EEMD-ANN, EEMD-SVM, and EEMD-ANFIS hybrid models was investigated using a monthly groundwater level time series collected from two observation wells near Lake Okeechobee in Florida. The statistical parameters correlation coefficient (R), normalized mean square error (NMSE), root mean square error (RMSE), Nash&ndash;Sutcliffe efficiency coefficient (NS), and Akaike information criteria (AIC) were used to assess the performance of the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models. The results achieved from the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models were compared with those from the ANN, SVM and ANFIS models. The three hybrid models (i.e., EEMD-ANN, EEMD-SVM, and EEMD-ANFIS) proved to be applicable to forecast the groundwater level fluctuations. The values of the statistical parameters indicated that the EEMD-ANFIS and EEMD-SVM models achieved better prediction results than the EEMD-ANN model. Meanwhile, the three models coupled with EEMD were found have better prediction results than the models that were not. The findings from this study indicate that the proposed nonlinear time-series intelligence hybrid models could improve the prediction capability in forecasting groundwater level fluctuations, and serve as useful and helpful guidelines for the management of sustainable water resources.

Hydrodynamic Modeling of a Tropical Tidal River Using the Dynamic Estuary Model (DYNHYD5): A Case Study in Sibu Laut River, Sarawak, Malaysia

Application of the Dynamic Estuary Model (DYNHYD5) in a tropical tidal river is limited. The successfully calibrated and validated hydrodynamic model is valuable in subsequent water quality simulation for environmental management. Hence, a hydrodynamic modeling approach using the DYNHYD5 was conducted in a tropical tidal river in Malaysia. Samplings were conducted in the Sibu Laut River to collect the hydrology data for model simulation. The model was calibrated and validated by comparing the simulated flow and mean depth with the field data at different simulation periods of time. The results showed that the model DYNHYD5 was successfully calibrated with channel flows and mean depths and then reproduced with good agreement in validation. The observed and simulated data were linearly correlated (R2 &gt; 0.8) with values of slope γ ranging from 0.891 to 1.204 in both calibration and validation. The Nash–Sutcliffe coefficient of efficiency (NSE) of more than 0.7 in both calibration and validation also indicated satisfactory comparison between the observed and simulated data. The result indicated that the application of the DYNHYD5 is feasible in a tropical tidal river in Malaysia.

Prediction of friction capacity of driven piles in clay using artificial intelligence techniques

Driven piles are widely used due to their easy installation set up and are economical. In this paper, prediction models for predicting friction capacity of piles in clay soils based on experimental test results are developed using two recently developed artificial intelligence techniques; multivariate adaptive regression splines (MARS) and functional networks (FN). The efficacy of developed MARS and FN models has been compared with previously developed models as given in the literature in terms of statistical parameters like correlation coefficient (R), Nash–Sutcliffe coefficient of efficiency (E), absolute average error, maximum average error, root mean square error and normalised mean bias error. Based on statistical performances, MARS and FN models are found to have a better predictive capacity than existing models.

A stochastic simulation model to early predict susceptible areas to water table level fluctuations in North Sinai, Egypt

Water table depth (WTD) is an important map layer for many environmental models’ assessments. To develop an early water table prediction model for North Sinai, Egypt, four approaches were considered in this study: GIS, remote sensing, simulation and stochastic methods. Stochastic (using time-series) modeling enables us to characterize the water table dynamics in terms of risk, and it allows model uncertainty to be taken into account without the complexity of physical mechanistic models. The results indicate that, time-series modeling is an effective method to characterize the seasonal patterns of WTDs in the area. The model performs very well using Nash and Sutcliffe coefficient of efficiency (NSE) which indicates a fit of the model to the data. Sequential Gaussian Simulation was explored as a way to model water table spatial variability. A 95% probability level was calculated as a measure for risk of shallow water tables. The limits established for risks of shallow WTDs at April 1st were 0.5m below the ground surface. A map showing the risk that the WTD at April 1st and October 1st in a future year will be shallower than 0.5m was presented. If the risk is close to 50%, it will be difficult to take a decision in water management or land use planning. The results found a negligible risk of shallow water tables for this date. The level of WTD will be about 0.30–0.45m higher than the present level in the next 20years. There is a better agreement between the simulated and measured data (8cm difference) which may be associated with an overestimation of the evaporative losses from the surface. Finally, Landsat image was not useful for WTD prediction; however, it may be useful for soil moisture prediction.