Nash-Sutcliffe Efficiency Research Articles

Modeling the impact of long-term land use changes on deep soil hydrological processes in the Loess Plateau, China

Land use change can significantly affect soil hydrology in arid and semi-arid regions, making it crucial to understand the relationship between vegetation roots and soil moisture. Current models often fail to predict root growth and its impacts on water dynamics accurately. Our work presents a novel model that seamlessly integrates the Community Land Model (CLM) with the Soil & Water Assessment Tool (SWAT). Furthermore, it enhances the root module within the CLM, enabling more accurate simulations of dynamic root depth and distribution across varying tree ages. This improvement particularly considers the crucial processes of dormancy and plant maturity. Soil moisture and root patterns under apple trees of varying ages and in wheat fields on the Loess Plateau was analyzed. Our findings indicate that our dynamic root depth model outperforms traditional static models, and can accurately reflect soil moisture levels with high precision (R2 = 0.80–0.81; Nash-Sutcliffe efficiency (NSE) = 0.65–0.75). In contrast to methods that utilize fixed root depths, dynamic root simulation can provide new insights. As apple orchards mature, the roots of 22-year-old apple trees have been found to reach a depth of 21 m in the soil. Conversely, the maximum root depth of wheat is limited to 1.9 m. This latter finding aligns more closely with the measured root depths, highlighting the accuracy of dynamic simulations. This model reveals that older apple orchards show decreased soil moisture at greater depths (>20 m), contrasting with wheat fields that affect moisture mostly within the top 2 m. Our results underscore the crucial role of dynamic modeling in comprehending root-soil water interactions. Furthermore, they imply that extended orchard cultivation practices can lead to a substantial depletion of deep soil moisture. Specifically, over a period of 1 to 22 years, a water deficit of up to 85 mm yr−1 has been observed. For a 22-year-old forest, the D-D (dynamic distributions of coarse and fine roots) method calculates a significant cumulative deep Soil Water Storage loss. Over the course of 22 years, this loss amounts to 1664 mm, which is almost three times compare to the annual rainfall recorded. Such a large loss has the potential to significant impact on groundwater recharge. This highlights the need for careful consideration in future afforestation efforts to prevent increased soil aridity.

Assessing the suitability of groundwater resources based on farmers’ predicted intentions and human–water feedbacks

In this study, a behavioral −hydrological simulation modeling framework is developed to explore the functioning of human-water systems. The main objective is to identify the psycho-social factors affecting water conservation intentions among farmers, and then realize the interactions and bidirectional feedback between humans and water resources. For this purpose, the agent-based modeling (ABM) and extended theory of planned behavior (TPB) is recruited to reflect on the agents’ behaviors. As the first step, the framework of the extended TPB together with the agent behavior was designed via field researches through the completion of 169 questionnaires upon proportional-to-size (PPS) random sampling. The partial least squares-structural equation modeling (PLS-SEM) is then implemented, at the second step, to analyze the data and obtain the weights of the extended TPB constructs. The results reveal that the constructs supplemented to the TPB, including moral norms (MNs) and perceived risk (PR), could have significant effects on water conservation intentions and behaviors among farmers. At the last step, the farmers and their decision-making as the dynamic elements by obtaining feedbacks of water resources were modeled using the ABM. To evaluate the proposed framework, the recorded data of groundwater fluctuations and cultivated areas in the Lenjanat plain is utilized and compared with the socio-hydrological simulation modeling outcomes using the Nash-Sutcliffe efficiency (NSE) coefficient. Then, five scenarios are defined to shed light on the changes in the agent behavior on the aquifer suitability, including water consumption rate and groundwater levels in the aquifer. The results correspondingly demonstrated that merging the second and third scenarios in an effort to raise the prices of crops with low water need along with the increase in utility costs (here, water and electricity) could lead to a 75% increase of farmers’ income and a 21.5% reduction in the surface and groundwater uses in this region, implying the highest level of water conservation among other scenarios.

A comprehensive method for error separation in hydrological modelling

AbstractEvaluation metrics play a pivotal role in the calibration process of hydrological models, serving as objective functions that directly influence the final values of model parameters and significantly affect users' perceptions of model performance. However, the choice and interpretation of evaluation metrics are subjective; therefore, this study provides a more objective framework for assessing model performance. This paper initially explored the applicability of various commonly used evaluation metrics, providing an overview of their limitations. Following this, we decomposed errors by analysing their physical significance and geometric representation in scatter plots, categorizing them into systematic and unsystematic errors. Through the decomposition and derivation of the Nash–Sutcliffe efficiency (NSE) formula, we established the quantitative relationship among various evaluation metrics. The soil and water assessment tool (SWAT) model was utilized to simulate monthly runoff in the Baishan basin (China), for the period 1994–2017, with NSE serving as the objective function for calibration. Our findings are consistent with previous studies, indicating that the model tends to slightly underestimate high flows while significantly overestimating low flows. Further analysis through error decomposition and the examination of relationships among various evaluation metrics revealed that unsystematic errors were dominant during the spring snowmelt runoff period, while systematic errors prevailed in the dry season. By evaluating the runoff series based on the magnitude of runoff or by categorizing it according to seasons and months, a more stringent assessment of the model's performance was achieved. These findings not only highlight the necessity for careful selection of evaluation metrics but also underscore the significance of our methodological advancements in enhancing hydrological model precision and reliability.

Forward and inverse river contaminant transport modeling using group preserving scheme

Environmental concerns have necessitated the development of computational models predicting pollutant dispersion in natural water systems. Due to the ill-posed nature of the inverse contaminant transport equation, solving this equation using all stable and convergent inverse methods is impossible. Factors such as river geometry, unsteady and non-uniform flow, and tidal influences add to the complexity of the inverse problem. These factors have prompted the evaluation of Group Preserving Scheme for environmental applications. The inverse solution method derives a general equation for solving ordinary differential equations by addressing a dynamical system at negative time steps, ensuring convergence. Three test cases have been presented to evaluate Backward Group Preserving Scheme (BGPS). These have included validation using observational data from Missouri River, inverse simulation in a tidal river, and sensitivity analysis of parameters such as pollutant patterns, advection, dispersion, and decay coefficients. The dataset includes calibrated data from Missouri River, which demonstrated high accuracy, with Mean Relative Error (MRE) ranging from 2.8% to 5.0% for the inverse model. Under tidal conditions, accuracy decreases over time but remains robust, with a Nash–Sutcliffe efficiency of 0.77–0.96 and an MRE of 0.9%–5.9%. Sensitivity analysis revealed optimal model performance for Péclet numbers greater than 500. The model performed best with gradual, wide-peaked pollutant patterns and moderate decay rates (Damköhler number between 5 and 10). BGPS proves effective for transport simulation and concentration history reconstruction in complex rivers, including those with tidal influences, offering a robust tool for water contamination analysis in various flow conditions.

Estimating the Ebro river discharge at 1 km/daily resolution using indirect satellite observations

Estimating river discharge Q at global scale from satellite observations is not yet fully satisfactory in part because of limited space/time resolution. Furthermore, on highly anthropized basins, it is essential to anchor the analysis to reliable Q measurements. Gauge networks are however very sparse and limited in time, and SWOT (Surface Water Ocean Topography) river discharge estimates at global scale are not yet available. The method proposed here is able to obtain continuous daily Q estimates at 1 km/daily resolution, using indirect satellite data and ground-based estimates. We focus here on the Ebro. Over such an anthropized basin (e.g. change of land use, irrigation), the exploitation of 205 available gauges at their nominal resolution (i.e., daily point measurements) is a necessity. The hydrological Continuum model is used to help interpolate spatially and temporally the observations into our optimal interpolation scheme. The proposed Q-mapping is similar to an assimilation scheme were Earth observations (precipitation, evapotranspiration and total water storage change) and model simulations are constrained by in situ gauge measurements. The Q estimates are evaluated using a rigorous leave-one-out experiment, showing a good agreement with the in situ data: a correlation of 0.72 (median), and a 75th percentile of Nash-Sutcliffe Efficiency up to 0.62. Our spatio-temporal continuous Q estimates at high spatial/temporal resolution can describe complex continental water dynamics, including extreme events. SWOT estimates will soon be available, at the global scale but with irregular space/time sampling: our method should help exploit them to obtain a regular space-temporal description of the water cycle at high resolution.

Dynamics of the risk of algal blooms induced by surface water temperature in an alpine eutrophic lake under climate warming: Insights from Lake Dianchi

Climate change-induced higher water temperature is increasing the risk of algal blooms (ABs) in eutrophic water bodies. However, it is not well known how and to what extent warming affects ABs risk. In this work, with simple data input (satellite product, lake surface observation, and climate) and method structure (ensemble learning, statistical downscaling, and hierarchical clustering), a systematic lake surface water temperature (LSWT) and ABs risk evaluation system are constructed and applied in a typical eutrophic freshwater lake. The main results are as follows: 1. The warming rate of LSWT and air temperature from 2000 to 2023 reached 0.21 °C/10a and 0.30 °C/10a respectively, resulting in an extended ABs risk in the historical period. 2. The Nash–Sutcliffe efficiency between climate and LSWT reached 0.89, and LSWT showed a significant (p < 0.05) positive correlation with algal density. 3. The escalation of ABs risks mainly spread to spring and autumn in the forthcoming future, the adverse effect of high emission scenarios will evidently emerge in the mid-21st century. Policymakers and catchment managers should be cautious of lake warming and develop countermeasures in advance.

Enhancing hydrological model efficiency through satellite image classification

ABSTRACT This paper aims to evaluate the performance of a hydrological model by using satellite image classification (SIM) to extract Land Use (LU) information. Four methods, namely Naive Bayes (NB), Classification and Regression Trees (CART), Support Vector Machine (SVM), and Random Forest (RF), are assessed for SIM using satellite images. CART demonstrated the highest Overall Accuracy (OA) of 0.996, followed by RF (OA=0.994), SVM (OA=0.797), and NB (OA=0.543). The Soil and Water Assessment Tool (SWAT) model was employed in this study to construct and refine the hydrological model for simulating the streamflow in the basin. For this purpose, the ground-based layer was replaced by LU generated from the classification algorithms. Integrating the four classification approaches yielded a significant improvement in Nash-Sutcliffe efficiency of the SWAT model, increasing it from 0.37 to approximately 0.76. These findings highlight the effectiveness of using satellite image classification in enhancing the efficiency of hydrological models.

Prediction of carbon dioxide emissions from Atlantic Canadian potato fields using advanced hybridized machine learning algorithms – Nexus of field data and modelling

In this study, three novel machine learning algorithms of additive regression-random forest (AR-RF), Iterative Classifier Optimizer (ICO-AR-RF), and multi-scheme (MS-RF) were explored for carbon dioxide (CO2) flux rate prediction from three agricultural fields. To build the dataset, 401 samples were collected from two fields in Prince Edward Island (PEI) and 122 samples from the New Brunswick (NB), Canada. In addition, soil moisture (SM), temperature (ST), and electrical conductivity (EC), alongside eight climatic variables including wind speed (WS), solar radiation (SR), relative humidity (RH), precipitation (PCP), air temperature (AT), dew point (DP), vapour pressure difference (VPD) and reference evapotranspiration (ETo) were also collected. Greedy stepwise (GS) approach was implemented for feature selection. Finally, different qualitative (scatter plot, line graph, Taylor diagram, box plot, and Rug plot), and quantitative (uncertainty analysis, root mean square error (RMSE), percent of BIAS (PBIAS), Nash Sutcliff efficiency (NSE) and RMSE-observations standard deviation ratio (RSR)) techniques were used for model evaluation and comparison. Results of feature selection approaches revealed that DP, AT, SM, and ST are the four most effective variables at CO2 prediction in PEI, while AT, RH, DP, and ST are the most effective in the NB study area. For optimum input scenario, the GS algorithm was applied, and results showed that a combination of DP, AT, ST, SM, and ETo was the best for the PEI study area, while for NB, all input variables should be involved. Our analysis, for prediction of CO2 fluxes, confirmed that the ICO-AR-RF model performed the best at both PEI (RMSE=0.70, NSE=0.76, PBIAS=-5.11, RSR=0.48) and NB (RMSE=0.74, NSE=0.75, PBIAS=3.23, RSR=0.50), followed by MS-RF and AR-RF. Uncertainty analysis showed that CO2 prediction is more sensitive to input scenario selection than models in both study areas. Results revealed that climatic variables are more effective in CO2 prediction than soil characteristics and the developed hybrid model ICO-AR-RF can be a promising tool for decision-makers and beneficial for stakeholders.

ANN based optimization of nano-beam oscillations with intermolecular forces and geometric nonlinearity

In this study, we investigate the effect of Van der Waals and Casimir forces on the mathematical model of nano-electromechanical systems (NEMS) such as nano-beam actuators that contain cantilever and double cantilever beams. The singular nonlinear boundary value problem governing the beam-type actuators, including geometric nonlinearity is solved by using an intelligent strength of feedforward artificial neural networks (ANNs) and hybridization of optimization algorithms such as arithmetic optimization algorithm (AOA) and active set algorithm (ASA). The proposed ANN-AOA-AS algorithm is employed to quantify the effect of changes in applied voltage, dispersion forces, geometric nonlinearity parameters, and initial axial strain on the deflection of the beam. Furthermore, to validate the results obtained by the proposed algorithm, statistical analyses are conducted to compare the approximate solutions with state-of-the-art methodologies available in the latest literature. In addition, performance indicators are defined such as mean square error (MSE), Nash–Sutcliffe efficiency (NSE), mean absolute deviations (MAD), root mean square error (RMSE), and Error in Nash–Sutcliffe efficiency (ENSE) to study the accuracy and efficiency of the solutions. The results show that these indicators’ mean percentage values lie around 10−4 to 10−6 which reflects the perfect modeling of the approximate solutions.

Flood risk assessment of a small river with limited available data

Flood risk modeling of small watercourses is challenging when only limited input data are available. Therefore, this study assessed the flood characteristics of a small river (Tarna River: entire watershed-C, upper-VS, middle-TMS, and lower section-TOS) from 1990 to 2019. The assessment focused on modeling, model calibration, and validation using feature event-based time-series data in data-scarce environments. We showed that since the 2000s, the number of high-water levels above 250 cm, and the frequency of three flood types had increased. Flood simulation results showed the largest flooded area in the TMS section, followed by the VS, and then the TOS. The outcomes from the VS, TMS, and TOS sections did not exhibit superior performance compared to the C area. Models performed well for larger flood events, with Kling Gupta Efficiency corresponding well to NRMSE and Nash-Sutcliffe efficiency metrics. Accordingly, flood events characterized by the longest duration and high-water levels yielded outstanding results across all areas, followed by moderate flood events with good accuracy. Normal water level events exhibited significant deviations from the reference across all sections. In summary, despite the event-based modeling challenges in data-limited environments, such models can still mitigate potential flood events and improve decision-making processes.

An approach on the estimation and temporal interaction of runoff: the band similarity method

ABSTRACT This study is based on the investigation of the performance of the band similarity (BS) method, which is quite new in the literature, in the prediction of flow and in determining the memory properties of the flow phenomenon. For this purpose, flow prediction models for the monthly flow data of the Sarız station, located in the Seyhan Basin in Türkiye, were produced first with the particle swarm optimization (PSO) algorithm. Second, these models were used in the BS method to create the BSPSO approach. Then, flow prediction was made for the same data set with support vector regression (SVR). In the test period, the standalone PSO, BSPSO, and SVR models achieved the most successful Nash–Sutcliffe efficiency (NSE) values of 0.516, 0.691, and 0.659, respectively. As a result, it was seen that BS increased the success of PSO by approximately 35%.

Assessing and mapping of soil organic carbon at multiple depths in the semi-arid Trans-Ural steppe zone

The quantification of soil organic carbon (SOC) and its vertical distribution is crucial for understanding carbon dynamics in terrestrial ecosystems. This study aimed to 2.5D digital mapping of SOC content in the Trans-Ural steppe zone (Russia) using a quantile regression forest (QRF) approach. The study utilized a dataset comprising 2495 SOC measurements collected from 1316 locations across three soil depths: 0–20 cm, 20–40 cm, and 40–60 cm. Environmental covariates were incorporated into the SOC modeling process, capturing major soil formation factors, and the uncertainty of the generated maps was estimated. The results revealed that SOC content ranged from 0.59 to 9.05 % in the topsoil, from 0.5 to 6.61 % in the subsurface layer and from 0.06 to 4.64 % in the subsoil. Based on the error metrics, including root mean square error (RMSE), coefficient of determination (R2), and Nash-Sutcliffe efficiency coefficient (NSE), we found a decrease in prediction accuracy with increasing soil depth. Furthermore, climate and vegetation variables, as well as elevation, emerged as key factors influencing the prediction of SOC concentrations at all depths. We also made an attempt to assess the future change of SOC under the influence of climate and anthropogenic impact. We anticipate that climate aridization and plowing will lead to a decline in SOC content in the Trans-Ural steppe region. Our findings contribute to the existing knowledge of SOC dynamics in steppe ecosystems at several depths, supporting informed decision-making for sustainable land use and climate change mitigation strategies.

Comparison of novel physics-guided machine learning models with empirical equations for predicting longitudinal dispersion coefficient in diverse natural river systems

Accurate calculation of the longitudinal dispersion coefficient (LDC) is crucial for assessing river fate and transport processes. Traditional methods, including experimental, analytical, and empirical equations, each have their challenges, such as complexity and susceptibility to errors. This study introduces and evaluates advanced physics-guided machine learning (ML) models, including hybrid hydrodynamic-particle simulation (HHPS), physics-enhanced ML (PEML), and physics-regularized regression trees (PRRT). Our dataset includes hydraulic and geometric parameters collected from 50 diverse rivers across the US and the UK, encompassing variables such as river width (W), flow depth (H), average flow velocity (U), flow shear velocity (U*), concentration of the solute (μgL) and LDC (ε). Input parameters were dimensioned using the UU∗ and WHratios, while the dimensionless LDC (εHU∗) served as the model output. By embedding core hydrodynamic principles such as continuity, mass and momentum conservation, and Navier-Stokes equations into the ML algorithms, these models achieved high predictive accuracy. Specifically, the HHPS model reached a coefficient of determination of 0.997, and both PEML and PRRT demonstrated Nash-Sutcliffe efficiencies exceeding 0.950, significantly outperforming traditional empirical equations. Additionally, SHapley Additive exPlanations (SHAP) sensitivity analysis revealed the substantial influence of channel width and flow conditions on LDC predictions. Our study highlights the superior performance of physics-guided ML models in providing accurate and reliable tools for river water quality management, demonstrating their substantial improvements over traditional methods and their potential broader applications in environmental studies.

Floodplain Zoning and Mapping for Lower Kelani River, Sri Lanka

Flood risk mapping and floodplain zoning are emerging as practical tools to reduce flood damage. The study intended to develop floodplain zoning maps in the lower Kelani River basin using Flood frequency analysis and MIKE 11 modeling. Flood quantiles estimated for River gauging station at Hanwella and Lower Kelani basin have been used for the flood map developments. The river gauge at Hanwella to the estuary River strip has been considered for floodplain zoning using MIKE 11 modeling software. The hydrologic modeling was performed using MIKE 11 Nedbor Afstromnings Model (NAM), while the hydraulic modeling was performed using MIKE 11 Hydro-Dynamic (HD) model. MIKE 11 rainfall-runoff (RR) NAM calibration and validation Nash-Sutcliffe efficiency (NSE) results were 0.766 and 0.607, respectively. Similarly, coupled NAM and HD model on Mike-Zero platform calibration and validation NSE results were 0.917 and 0.871, respectively. The return period floods estimated to the Hanwella River gauge and Lower Kelani River basin have been availed to generate flood inundation maps. Finally, the flood plain zoning maps have been developed for the Lower Kelani River for 10-, 25-, and 50-year return periods. These maps can be use to limit cultivations and reduce crop losses during monsoons.

Stream salinity prediction in data-scarce regions: Application of transfer learning and uncertainty quantification

Scarcity of stream salinity data poses a challenge to understanding salinity dynamics and its implications for water supply management in water-scarce salt-prone regions around the world. This paper introduces a framework for generating continuous daily stream salinity estimates using instance-based transfer learning (TL) and assessing the reliability of the synthetic salinity data through uncertainty quantification via prediction intervals (PIs). The framework was developed using two temporally distinct specific conductance (SC) datasets from the Upper Red River Basin (URRB) located in southwestern Oklahoma and Texas Panhandle, United States. The instance-based TL approach was implemented by calibrating Feedforward Neural Networks (FFNNs) on a source SC dataset of around 1200 instantaneous grab samples collected by United States Geological Survey (USGS) from 1959 to 1993. The trained FFNNs were subsequently tested on a target dataset (1998-present) of 220 instantaneous grab samples collected by the Oklahoma Water Resources Board (OWRB). The framework's generalizability was assessed in the data-rich Bird Creek watershed in Oklahoma by manipulating continuous SC data to simulate data-scarce conditions for training the models and using the complete Bird Creek dataset for model evaluation. The Lower Upper Bound Estimation (LUBE) method was used with FFNNs to estimate PIs for uncertainty quantification. Autoregressive SC prediction methods via FFNN were found to be reliable with Nash Sutcliffe Efficiency (NSE) values of 0.65 and 0.45 on in-sample and out-of-sample test data, respectively. The same modeling scenario resulted in an NSE of 0.54 for the Bird Creek data using a similar missing data ratio, whereas a higher ratio of observed data increased the accuracy (NSE = 0.84). The relatively narrow estimated PIs for the North Fork Red River in the URRB indicated satisfactory stream salinity predictions, showing an average width equivalent to 25 % of the observed range and a confidence level of 70 %.

Ensemble of artificial intelligence and physically based models for rainfall–runoff modeling in the upper Blue Nile Basin

ABSTRACT This study investigated the performance of the adaptive neuro-fuzzy inference system (ANFIS), feed forward neural network (FFNN), Soil and Water Analysis Tool (SWAT), Hydrologic Engineering Center's Hydraulic Modeling System (HEC-HMS), Hydrologiska Byråns Vattenbalansavdelning (HBV), and support vector regression (SVR) models for rainfall–runoff modeling using gauged and satellite rainfall, and their fusions in the Gilgel Abay watershed, Ethiopia. Afterward, simple average ensemble (SAE), weighted average ensemble (WAE), and neural network ensemble (NNE) techniques were applied to combine the outputs of individual models under three scenarios. The performance of the models was evaluated using Nash–Sutcliffe efficiency (NSE) and root mean square error (RMSE). The results demonstrated that the ANFIS model outperformed all the other single models with validation stage NSE values of 0.864 and 0.875, and RMSE values of 23.58 and 21.84 m3/s for gauge and fusion rainfall data, respectively. Among the physical-based models, SWAT gave better modeling performance with the validation stage NSE values of 0.81 and 0.821 for gauge and fusion rainfall data, respectively. Moreover, an ensemble of artificial intelligence and physical-based models greatly improved the overall modeling performance. The NNE improved the performance of single models up to 15.7 and 21.2 5% for fusion and satellite-based rainfall modeling, respectively.

Multi-mission virtual monitoring station for streamflow monitoring and hydrodynamic model calibration

A comprehensive understanding of the streamflow dynamic along the river system is one of the significant components for preserving biodiversity and ensuring sustainable ecological processes. Understanding this requirement, streamflow estimation using remote sensing (RS) has evolved as an alternate approach in the hydrologic literature during the last decade due to its extensive spatiotemporal coverage. However, the existing RS-based approaches have limited applications for deriving the continuous time series in tropical river reaches due to narrow water widths during the low flow and frequent cloud covers during the high flow periods. Therefore, this study proposed frameworks to establish a virtual monitoring station (VMS) where multi-mission satellites are being used to derive continuous streamflow time series. From the multi-mission satellites, the optical RS images are used to develop a Copula-based fusion (CFUS) model by integrating the Frank copula with the 30m × 1-day resolution synthetic Landsat images, derived from the fusion of 250m × 1-day resolution MODIS images and 30m × 16-days resolution Landsat images; whereas the water levels are retrieved from the altimeters to derive discharge using the rating curve. Additionally, the potential utility of the established VMS for hydrodynamic model (MIKE11-NAM-HD) calibration under data-scarce conditions is also demonstrated. Finally, a coupled RS-hydrodynamic (RS-HD) framework is also proposed to establish VMS both at semi-gauged and ungauged sections of the rivers. The efficacy of the aforementioned framework was tested along the lower Brahmani river reach. The results reveal that the advocated framework could perform satisfactorily with the Nash-Sutcliffe efficiency (NSE) and Kling-Gupta efficiency (KGE) ≥0.8. This approach has the potential to be upscaled to other river reaches as one of the next-generation hydrometry for daily streamflow monitoring using high-frequent observation of multi-mission satellites.

A multimethod interpolation approach for mapping the spatial distribution of rainfall in southwest Iberian Peninsula

ABSTRACT Eight spatial interpolation models were used to map the spatial distribution of precipitation in the southwestern sector of the Iberian Peninsula (22330 km2) over 40 years (1980/1981–2019/2020). Rainfall data from 103 meteorological stations were used to generate the interpolation models, namely inverse distance weight (IDW) with 6, 12 and 24 points, regression spline (RS), thin spline (TS), universal kriging with spherical and Gaussian variogram (UK_Sphe and UK_gauss, respectively) and multilinear regression (MR), based on physiographic and geographic variables. Furthermore, 32 rainfall stations were used to assess the performance of the previous methods through 7 statistical metrics Ordinary Least Squares (OLS), Root Mean Square Error (RMSE), Normalized root mean square error (NRMSE), Coefficient of determination (R2), Nash-Sutcliffe efficiency coefficient (NSE), Mean Absolute Error (Bias and MAE). Based on these metrics, UK_gauss and IDW_6 provided the best adjustments, whereas MR presented the highest errors. All methods were suitable to predict the spatial distribution of rainfall, but adjustments are conditioned by the features of the study area, gauge density and gauge spatial distribution.

Effective design of sustainable energy productivity based on the experimental investigation of the humidification-dehumidification-desalination system using hybrid optimization

Reliable and cost-effective industrial-based sustainable desalination technologies are crucial for efficient and effective desalination of saline water. Seawater desalination emerges as a vital treatment, with humidification-dehumidification identified as a promising technology due to its simple, low-maintenance design and compatibility with renewable energy sources. The present work was developed using a large-scale experimental test rig based on the performance of a humidification-dehumidification system operated by the heat pump. As such, the study presents an advanced approach for optimizing humidification-dehumidification desalination systems using hybrid machine learning optimization techniques. The effectiveness of a neuro-fuzzy model, a decision algorithm based on a boosted tree, and a simple averaging ensemble in enhancing the performance of humidification-dehumidification systems were investigated. Experimental data includes cold water flowrate (L/min), hot water flowrate (L/min), inlet air temperature (°C), inlet cold water temperature (°C), inlet hot water temperature (°C), and inlet air relative humidity (%) as input variables combination and freshwater productivity (L/h), recovery ratio (%) as target variables. Several statistical indicators were used to evaluate the models’ prediction skills; similarly, a 2-dimensional Taylor diagram and error-radial plot were also utilized. In the calibration phase, boosted tree models slightly outperform neuro-fuzzy models, particularly for recovery ratio, demonstrating high accuracy and low bias. However, all models exhibit robust predictive accuracy in the verification phase, especially for recovery ratio, emphasizing their potential in generalizing to unseen data. The result indicated that the boosted tree outperformed others with Nash–Sutcliffe Efficiency = 94 % and 88 % for recovery ratio and freshwater productivity, respectively. The simple averaging ensemble shows marginal improvement with 95 % accuracy for the recovery ratio. Integrating hybrid artificial intelligence optimization with humidification-dehumidification desalination systems marks a transformative step in addressing freshwater shortages. By utilizing cutting-edge machine learning techniques, we achieve a more efficient, accurate, and reliable prediction of desalination performance.

Runoff simulation modeling method integrating spatial element dynamics and neural network for remote sensing precipitation data

Effective management of water resources amidst global climate change necessitates advancements in runoff simulation techniques. This study introduces a novel methodology that integrates a spatial element dynamic model with a neural network designed for satellite precipitation product (SPP) and remote sensing data to address the complex dynamics of precipitation-runoff processes. Implemented in the Songhua River basin of China, the methodology features a runoff estimation module that operates across both high-resolution and SPP grid scales. This module synergizes spatial attributes with fuzzy classification for refined confluence optimization, and yielding simulations through long short-term memory network. The results indicate that the proposed multi-scale production-confluence scheme achieved Nash-Sutcliffe efficiency (NSE) scores of 0.87 and 0.84 during calibration (2011–2015) and validation (2017 and 2018) periods, respectively, representing an 8.15% improvement in peak percentage error (PPE10%) over conventional hydrologic models. Additionally, the scheme demonstrated superior simulation performance at tributary sites set compared to main channel sites set, with differences of 0.08 and 0.07 in NSE and Kling-Gupta efficiency (KGE), respectively. The introduction of the surface Ⅱ operator for adjusting precipitation intensity effectively improved runoff estimation accuracy, reducing the average error by 25.48% across both site sets. This study provides a scientific foundation for applying SPP in hydrological modeling and offers decision support for managing water resources.