Nash-Sutcliffe Model Efficiency Research Articles

A novel floodwave response model for time-varying streambed conductivity using space-time collocation Trefftz method

Streambed conductivity can vary substantially over short time intervals during flood events, altering groundwater – surface water interactions. Traditional floodwave response models (FRM) developed by linking a unit step response function with the convolution integral are limited by the conditions of a stationary aquifer-stream system and a hydrostatic equilibrium initial condition. However, these two conditions can hardly be satisfied when streambed conductivity changes with time. As a result, in this study a new nonstationary FRM (NFRM) that can consider time-varying streambed conductivity was developed using a space–time collocation Trefftz method. In this new model, the aquifer was assumed homogeneous, and the groundwater flow was simplified to be one-dimensional and perpendicular to a partially penetrating river. The NFRM can be applied to both the forward calculation of groundwater responses to fluctuations of river stage and the inverse calculation of time-varying streambed conductivity. A wide range of synthetic cases generated by the numerical simulations of aquifer-stream interactions was used for validation. Good agreement between the results computed from the NFRM and the synthetic data can be found in all cases (Nash-Sutcliffe model efficiency coefficient > 0.90; Mean Absolute Relative Error < 0.03), showing the accuracy and robustness of the NFRM. The NFRM was then successfully applied to a study site on the Tallahatchie River (Mississippi, USA). The estimated streambed conductivity was found to vary between 10-3 m/d to 10-2 m/d over the studied period. It generally increased during high-stage events and decreased when the river stayed in a low-stage condition, but also generally depended on seepage direction with increases occurring while groundwater discharged to the river and decreases while river water recharged the aquifer.

TreeLSTM: A spatiotemporal machine learning model for rainfall-runoff estimation

Study regionThe Jinsha River (JRB) and Han River basins (HRB), China. Study focusDue to challenges in interpreting neural network algorithms in hydrological runoff processes, our research focuses on enhancing the temporal dependency and spatial correlation learning capacities. To address these issues, we proposed a multi-layer spatiotemporal model, i.e., the tree long short-term memory model (treeLSTM), for runoff estimations. Because downstream hydrological stations are affected by their own historical and current upstream rainfall and runoff, the treeLSTM’s horizontal and vertical inputs are historical and upstream rainfall-runoff for temporal and spatial features extraction, respectively. The daily rainfall-runoff from 1992 to 2016 in JRB and that from 2011 to 2020 in HRB are predicted. New hydrological insights for the regionResults of validation periods (2012–2016 in JRB, 2019–2020 in HRB) indicate that the treeLSTM in terms of (JRB: RMSE (root mean square error) = 0.5375, MAPE (mean absolute percent error) = 8.27 %, NSE (Nash–Sutcliffe model efficiency coefficient) = 0.9621; HRB: RMSE = 3.3562, MAPE = 2.91 %, NSE = 0.9934) outperformed the backpropagation neural network (BP) and LSTM models. Therefore, the treeLSTM has considerable advantages in runoff estimation due to its integration of time dependence in historical hydrological data with the spatial correlation of meteorological and hydrological elements, which may be useful for enhancing the physical interpretability of machine learning algorithms.

Assessment of the Streamflow and Evapotranspiration at Wabiga Juba Basin Using a Water Evaluation and Planning (WEAP) Model

Rapid population growth, industrialization, and agricultural activities have impacted water resources in the arid and semi-arid areas of Somalia. The Lower Juba region in Somalia has been the most affected region. Therefore, an analysis of the hydrological patterns is essential. This paper assesses streamflow and evapotranspiration in the Wabiga Juba basin in Somalia using a hydrological simulation model, namely, the water evaluation and planning (WEAP) system via the soil moisture method. The datasets included 53 (average precipitation) and 13 (streamflow) year periods from two meteorological stations. The estimated values for potential evapotranspiration (11,921.98 to 20,775.39 MCM) were higher than the actual evapotranspiration (4904.10 to 8242.72 MCM) by 50 to 79.5%, respectively. The annual streamflow in Juba Dolow and runoff proportion of the Wabiga Juba River was estimated to be 10% of the annual precipitation. Most of the surface runoff occurred in April (47%), May (31%), October (5%), and November (14%). The streamflow variation responded to the pattern of precipitation. The model performance achieved a Nash–Sutcliffe model efficiency (NSE) coefficient of 0.71, coefficient of determination (R2) of 0.91, and percent bias (PBIAS) of 14%. The WEAP model of the Wabiga Juba basin is a baseline study for water resource management in Somalia to mitigate water shortage impacts due to limited water resources.

Investigation of the ENVI-met model sensitivity to different wind direction forcing data in a heterogeneous urban environment

Abstract. As the frequency of extreme heat events in cities is significantly increasing due to climate change, the implementation of adaptation measures is important for urban planning. Microclimate modelling approaches enable scenario analyses and evaluations of adaptation potentials. An ENVI-met microclimate model was setup for a heterogeneous urban study area in Cologne/Germany characterized by closed building structures in the eastern part and an urban park area in the western part. The goal of this paper is to evaluate the model sensitivity and performance to different wind direction forcing and demonstrate the importance of accurate wind forcing data for precise microclimate modelling evaluated with sensor measurements. To this end, we compared simulated air temperatures at 3 m height level using measured wind direction forcing data with simulated air temperatures using constant wind direction forcing from west, north, east and south direction. All other forcing data like wind speed were kept exactly the same as in the reference run. This sensitivity study was performed for a warm summer day in 2022. The model results of all five model runs (reference plus four scenarios) were compared to microclimatological measurements derived from one station of a dense meteorological sensor network located in the study area using the simulated mean air temperatures. We found significant temperature differences between the four sensitivity tests and the reference run as well as to the sensor measurements. Temperature differences between the reference run and the measurements were small and a high statistical model fit could be determined (Nash Sutcliffe Model Efficiency Coefficient/NSE = 0.91). The four model runs with constant wind directions showed significantly larger differences to measurement data and a worse statistical correlation between simulated and observed data (NSE between 0.62 and 0.15). For constant west winds, cooler air temperatures and higher wind speeds were found in the urban park and in the streets and courtyards east of the park. Constant east wind causes warmer air temperatures in the urban park area and lower wind speeds in the street canyons and inner courtyards. This shows that cooling effects in adjacent building blocks due to the greened urban park largely depend on the wind direction. The sensitivity tests show that the wind direction effect can result in local air temperature differences of up to 4 K on average. These results shows that even on summer days with low wind speeds, accurate wind direction data is highly relevant for accurate air temperature simulation. This finding can have important implications for urban planning and the design of green infrastructures in cities, e. g. for the design of fresh air corridors.

Assessment of DSSAT and AquaCrop models to simulate soybean and maize yield under water stress conditions

Aim of study: To evaluate the performance of DSSAT and AquaCrop models in the estimation of soybean and grain maize yield under water stress conditions in a semi-arid region. Area of study: Kermanshah, Iran. Material and methods: AquaCrop and DSSAT were assessed to simulate soybean and maize. Both models were calibrated using field data. Field experiments were performed in a randomized complete block design with eight and four irrigation treatments for soybeans and maize, respectively with three replications. Measures of Normalized Root Mean Square Error (nRMSE) and Nash-Sutcliffe Model Efficiency were used to evaluate the accuracy of the models. For this purpose, simulated values of leaf area index / green crop canopy, grain yield, biomass, and soil moisture were compared with measured data. Main results: Results indicated that the CROPGRO-Soybean in DSSAT software simulated more accurate crop growth of soybean than AquaCrop. The average nRMSE of the DSSAT model for estimating soil moisture, leaf area index, grain yield, and biomass were 6%, 14%, 16% and 20%, respectively. For maize, AquaCrop simulated crop growth more reliably than CERES-maize. The average nRMSE of 3%, 10%, 13% and 27% of the Aquacrop model in simulating the parameters of soil moisture, green crop canopy, biomass, and grain yield. Research highlights: Considering the better performance of AquaCrop for maize and DSSAT for soybean in the study area, it is not possible to propose a specific model to simulate the growth of all crops in a region.

A Machine Learning Approach for the Estimation of Total Dissolved Solids Concentration in Lake Mead Using Electrical Conductivity and Temperature

Total dissolved solids (TDS) concentration determination in water bodies is sophisticated, time-consuming, and involves expensive field sampling and laboratory processes. TDS concentration has, however, been linked to electrical conductivity (EC) and temperature. Compared to monitoring TDS concentrations, monitoring EC and temperature is simpler, inexpensive, and takes less time. This study, therefore, applied several machine learning (ML) approaches to estimate TDS concentration in Lake Mead using EC and temperature data. Standalone models including the support vector machine (SVM), linear regressors (LR), K-nearest neighbor model (KNN), the artificial neural network (ANN), and ensemble models such as bagging, gradient boosting machine (GBM), extreme gradient boosting (XGBoost), random forest (RF), and extra trees (ET) models were used in this study. The models’ performance were evaluated using several performance metrics aimed at providing a holistic assessment of each model. Metrics used include the coefficient of determination (R2), mean absolute error (MAE), percent mean absolute relative error (PMARE), root mean square error (RMSE), the scatter index (SI), Nash–Sutcliffe model efficiency (NSE) coefficient, and percent bias (PBIAS). Results obtained showed varying model performance at the training, testing, and external validation stage of the models, with obtained R2 of 0.77–1.00, RMSE of 2.28–37.68 mg/L, an MAE of 0.14–22.67 mg/L, a PMARE of 0.02–3.42%, SI of 0.00–0.06, NSE of 0.77–1.00, and a PBIAS of 0.30–0.97 across all models for the three datasets. We utilized performance rankings to assess the model performance and found the LR to be the best-performing model on the external validation datasets among all the models (R2 of 0.82 and RMSE of 33.09 mg/L), possibly due to the established existence of a relationship between TDS and EC, although this may not always be linear. Similarly, we found the XGBoost to be the best-performing ensemble model based on the external validation with R2 of 0.81 and RMSE of 34.19 mg/L. Assessing the overall performance of the models across all the datasets, however, revealed GBM to produce a superior performance based on the ranks, possibly due to its ability to reduce overfitting and improve generalizations. The findings from this study could be employed in assisting water resources managers and stakeholders in effective monitoring and management of water resources to ensure their sustainability.

Eco-hydrological modeling of soil wetting pattern dimensions under drip irrigation systems

Reliable information on the horizontal and vertical dimensions of the wetted soil beneath a point source is critical for designing accurate, cost-effective, and efficient surface and subsurface drip irrigation systems. Several factors, including soil properties, initial soil conditions, dripper flow rate, number of drippers, spacing between drippers, irrigation management, plant root characteristics, and evapotranspiration, influence the dimensions and shape of wetting patterns. The objective of this study was to briefly review previous studies, collect the analytical, numerical, and empirical models developed, and evaluate the effectiveness of the most common empirical method for predicting the dimensions of soil wetted around drippers using measured data from field surveys. With this review study, we aim to promote a better understanding of soil water dynamics under point-source drip irrigation systems, help improve soil water dynamics under point-source drip irrigation systems, and identify issues that should be better addressed in future modeling efforts. A drip irrigation system was configured with three different emitters with different capacities (2, 4, and 8 l h-1) in the point source to determine the soil wetting front under the point source. The five most selected empirical equations (Al-Ogaidi, Malek and Peters, Amin and Ekhmaj, Li and Schwartzman and Zur) were statistically analyzed to test the efficiency in sandy loam soil. According to the results of the field investigation, statistical comparisons of the empirical models with the field investigation data were performed using the mean absolute error (MAE), root mean square error (RMSE), Nash–Sutcliffe model efficiency (CE), and coefficients of determination (R2). The advanced simulation of the wetting front was used based on the best accuracy of the selected empirical model. In general, the Li model (MAE, RMSE, EF, and R2 were 0.698 cm, 0.894 cm, 0.970 cm2 cm-2, and 0.970, respectively, for the wetted soil width and 1.800 cm, 1.974 cm, 0.927 cm2 cm-2, and 0.986, for the vertical advance) proved to be the best after statistical analysis with field data.

The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment

Abstract. As a genre of physics-informed machine learning, differentiable process-based hydrologic models (abbreviated as δ or delta models) with regionalized deep-network-based parameterization pipelines were recently shown to provide daily streamflow prediction performance closely approaching that of state-of-the-art long short-term memory (LSTM) deep networks. Meanwhile, δ models provide a full suite of diagnostic physical variables and guaranteed mass conservation. Here, we ran experiments to test (1) their ability to extrapolate to regions far from streamflow gauges and (2) their ability to make credible predictions of long-term (decadal-scale) change trends. We evaluated the models based on daily hydrograph metrics (Nash–Sutcliffe model efficiency coefficient, etc.) and predicted decadal streamflow trends. For prediction in ungauged basins (PUB; randomly sampled ungauged basins representing spatial interpolation), δ models either approached or surpassed the performance of LSTM in daily hydrograph metrics, depending on the meteorological forcing data used. They presented a comparable trend performance to LSTM for annual mean flow and high flow but worse trends for low flow. For prediction in ungauged regions (PUR; regional holdout test representing spatial extrapolation in a highly data-sparse scenario), δ models surpassed LSTM in daily hydrograph metrics, and their advantages in mean and high flow trends became prominent. In addition, an untrained variable, evapotranspiration, retained good seasonality even for extrapolated cases. The δ models' deep-network-based parameterization pipeline produced parameter fields that maintain remarkably stable spatial patterns even in highly data-scarce scenarios, which explains their robustness. Combined with their interpretability and ability to assimilate multi-source observations, the δ models are strong candidates for regional and global-scale hydrologic simulations and climate change impact assessment.

Predicting Water Quality Distribution of Lakes through Linking Remote Sensing–Based Monitoring and Machine Learning Simulation

The present study links monitoring and simulation models to predict water quality distribution in lakes using an optimized neural network and remote sensing data processing. Two data driven models were developed. First, a monitoring model was established that is able to convert spectral images to TDS distribution. Moreover, a simulation model was developed to generate a TDS distribution map for unseen scenarios for which no spectral images are available. Outputs of the monitoring model were applied as the observations for training the simulation model. The Nash–Sutcliffe model efficiency coefficient (NSE) was utilized in the system performance measurement of the models. Based on the results in the case study, the monitoring model was sufficiently robust to convert the operational land imager spectral bands of Landsat 8 to the TDS distribution map. The NSE was more than 0.6 for the monitoring model, which confirms the predictive skills of the model. Furthermore, the simulation model was highly reliable in generating the TDS distribution map of the lakes. Three tests were carried out to demonstrate the reliability of the model. When comparing the results of the monitoring model and simulation model, an NSE of more than 0.6 was found for all the tests. It is recommendable to apply the proposed method instead of conventional hydrodynamic models that might be highly time consuming for simulating water quality parameters distribution in lakes. Low computational complexity is the main advantage of the proposed method.

A Neural Network-Based Hydrological Model for Very High-Resolution Forecasting Using Weather Radar Data

Many hydro-meteorological disasters in small and steep watersheds develop quickly and significantly impact human lives and infrastructures. High-resolution rainfall data and machine learning methods have been used as modeling frameworks to predict those events, such as flash floods. However, a critical question remains: How long must the rainfall input data be for an empirical-based hydrological forecast? The present article employed an artificial neural network (ANN)hydrological model to address this issue to predict river levels and investigate its dependency on antecedent rainfall conditions. The tests were performed using observed water level data and high-resolution weather radar rainfall estimation over a small watershed in the mountainous region of Rio de Janeiro, Brazil. As a result, the forecast water level time series only archived a successful performance (i.e., Nash–Sutcliffe model efficiency coefficient (NSE) &gt; 0.6) when data inputs considered at least 2 h of accumulated rainfall, suggesting a strong physical association to the watershed time of concentration. Under extended periods of accumulated rainfall (&gt;12 h), the framework reached considerably higher performance levels (i.e., NSE &gt; 0.85), which may be related to the ability of the ANN to capture the subsurface response as well as past soil moisture states in the watershed. Additionally, we investigated the model’s robustness, considering different seeds for random number generating, and spacial applicability, looking at maps of weights.

A multicriteria approach to different land use scenarios in the Western Carpathians with the SWAT model

Water erosion in mountainous areas is a major problem, especially on steep slopes exposed to intense precipitation. This paper presents the analysis of the topsoil loss using the SWAT (Soil and Water Assessment Tool) model. The SWAT model is a deterministic catchment model with a daily time step. It was designed to anticipate changes taking place in the catchment area, such as climate change and changes in land use and development, including the quantity and quality of water resources, soil erosion and agricultural production. In addition to hydrological and environmental aspects, the SWAT model is used to address socio-economic and demographic issues, such as water supply and food production. This program is integrated with QGIS software. The results were evaluated using the following statistical coefficients: determination (R2), Nash–Sutcliff model efficiency ( NS), and percentage deviation index ( PBIAS). An assessment of modelling results was made in terms of their variation according to different land cover scenarios. In the case of the scenario with no change in use, the average annual loss of topsoil (average upland sediment yield) was found to be 14.3 Mg∙ha –1. The maximum upland sediment yield was 94.6 Mg∙ha –1. On the other hand, there is an accumulation of soil material in the lower part of the catchment (in-stream sediment change), on average 13.27 Mg∙ha –1 per year.

Comparison of machine learning algorithms to predict dissolved oxygen in an urban stream.

Water quality monitoring for urban watersheds is critical to identify the negative urbanization impacts. This study sought to identify a successful predictive machine learning model with minimal parameters from easy-to-deploy, low-cost sensors to create a monitoring system for the urban stream network, Hunnicutt Creek, in Clemson, SC, USA. A multiple linear regression model was compared to machine learning algorithms k-nearest neighbor, decision tree, random forest, and gradient boosting. These algorithms were evaluated to understand which best predicted dissolved oxygen (DO) from water temperature, conductivity, turbidity, and water level change at four locations along the urban stream. The random forest algorithm had the highest performance in predicting DO for all four sites, with Nash-Sutcliffe model efficiency coefficient (NSE) scores > 0.9 at three sites and > 0.598 at the fourth site. The random forest model was further examined using explainable artificial intelligence (XAI) and found that temperature influenced the DO predictions for three of the four sites, but there were different water quality interactions depending on site location. Calculating the land cover type in each site's sub-watershed revealed that different amounts of impervious surface and vegetation influenced water quality and the resulting DO predictions. Overall, machine learning combined with land cover data helps decision-makers better understand the nuances of urban watersheds and the relationships between urban land cover and water quality.

Predictive modeling of oil and water saturation during secondary recovery with supervised learning

In the petroleum reservoir, the secondary oil recovery (SOR) process is employed by injecting water into wells to enhance the moment of oil toward the production wells. The SOR process gives rise to the instability (fingering) phenomena due to the injecting force and the difference in the wettability and viscosity of the oil and water at the common interface. Since the late 1800s, mathematical models of petroleum reservoirs have been extensively used in the oil and gas industry. In this paper, we investigated the saturation of two immiscible fluid (oil and water) flows through homogeneous porous media during the SOR process by solving the modeled partial differential equation using the supervised machine learning algorithm based on feedforward back-propagated neural networks (FFBNNs) and Levenberg–Marquardt (LM) optimization algorithm. The designed scientific computing technique (FFBNN-LMA) is further employed to study the detailed sensitivity analysis of the approximate solutions. Performance measures like average absolute deviations, Theils' inequality measure, regression, and Nash–Sutcliffe model efficiency coefficient.

Modelling coagulant dosage in drinking water treatment plant using advance machine learning model: Hybrid extreme learning machine optimized by Bat algorithm.

Despite the high importance of coagulation process in drinking water treatment plant (DWTP), challenge remains in effectively linking raw water quality measured at the inlet of the DWTP with coagulant dosage rate. This study proposes an integral modelling framework using hybrid extreme learning machine and Bat metaheuristic algorithm (ELM-Bat) for modelling coagulant dosage rate using water temperature, pH, specific conductance, dissolved oxygen, and water turbidity. The aluminum sulphate (Al2 (SO4)3.18H2O) coagulant is determined using conventional Jar-Test procedure. Results obtained using the hybrid ELM-Bat were compared to those obtained using standalone ELM, outlier robust extreme learning machine (ORELM), online sequential extreme learning machine (OSELM), optimally pruned extreme learning machine (OPELM), and kernel extreme learning machine (KELM). First, the models have been calibrated during the training stage and in a second stage; they are validated using various statistical metrics, i.e., RMSE, MAE, the correlation coefficient (R), and the Nash-Sutcliffe model efficiency (NSE). We found that the hybrid ELM-Bat was significantly more accurate and it has yielded accuracy higher than all other models. During the validation stage, the R and NSE values calculated using the ELM-Bat were ≈0.959 and ≈0.918 exhibiting an improvement rates of approximately (≈15.26% and ≈33.82%), (≈10.35% and ≈21.92%), (≈14.98% and ≈31.89%), (≈7.63% and ≈16.35%), (≈10.99% and ≈23.05%), compared to the values obtained using the ELM, OPELM, OSELM, KELM and ORELM, respectively. Besides, the new ELM-Bat model has shown to have high predictive capabilities, which can be used optimally for calculating the optimal coagulant dosage with high accuracy.

Analysis of the hydraulic performance of permeable pavements on a layer-by-layer basis

Permeable pavement systems are a sustainable urban drainage technique created with a highly porous base and subbase. This study first analyses the hydraulic performance of several new permeable pavement systems based on 189 experimental hydrographs. In addition, the analysis explores the influence of rain intensity, slope, and, as a novelty, individual layers. Analysed variables were outflow peak, time to peak, and time to specific cumulative discharges. Secondly, based on the experimental hydrographs, the study explores the performance of the permeable pavement module defined in the Storm Water Management Model, carried out in two steps. First, single-layer outflows were used to calibrate parameter values that could not be measured physically, using the differential evolution algorithm and Nash–Sutcliffe model efficiency coefficient as an objective function. Later, complete layout hydrographs were tested without calibration, and model performance was checked. Results show that the superficial permeable interlocking paver layer provides a notably higher retention capacity than the porous asphalt mixture. Individual modelling results show that the soil layer definition is inappropriate for gravel-type layers, even with a geotextile. Despite this, complete section performance is quite good without calibration if the soil layer is not selected on the model. These results are expected to reduce modelling uncertainty, especially when no calibration data is available.

LSTM-Based Model-Predictive Control with Rationality Verification for Bioreactors in Wastewater Treatment

With the increasing demands for higher treatment efficiency, better effluent quality, and energy conservation in Urban Wastewater Treatment Plants (WWTPs), research has already been conducted to construct an optimized control system for Anaerobic-Anoxic-Oxic (AAO) process using a data-driven approach. However, existing data-driven optimization control systems for AAO mainly focus on improving effluent water quality and reducing energy consumption, therefore they lack consideration for the stability of bioreactors. Meanwhile, safety in the optimization control process is still missing, resulting in a lack of reliability in practical applications. In this study, long short-term memory based model-predictive control (LSTM-MPC) with safety verificationis developed for the real-time control of AAO. It is used to optimize the control of aeration volume, internal recirculation, and sludge internal recycle processes for both saving energy and maintaining the stability of the bioreactor operation. To ensure the safety of the control process, this study proposes three rationality verification methods based on historical operation experience. These methods are validated through data from a real-world WWTP in eastern China. The results show that the prediction model of LSTM-MPC is capable of accurately predicting the water quality variables of the AAO system, with mean square error (MSE) close to 2.64 and Nash–Sutcliffe model efficiency coefficient (NSE) of 0.99 on the validation dataset. The combination of LSTM-MPC and rationality verification achieves a stable control trajectory with a 7% reduction in oxygen usage compared to a conventional controller, demonstrating its efficacy as a safe and reliable control strategy for WWTPs.

Forage Biomass Estimation Using Sentinel-2 Imagery at High Latitudes

Forages are the most important kind of crops at high latitudes and are the main feeding source for ruminant-based dairy industries. Maximizing the economic and ecological performances of farms and, to some extent, of the meat and dairy sectors require adequate and timely supportive field-specific information such as available biomass. Sentinel-2 satellites provide open access imagery that can monitor vegetation frequently. These spectral data were used to estimate the dry matter yield (DMY) of harvested forage fields in northern Sweden. Field measurements were conducted over two years at four sites with contrasting soil and climate conditions. Univariate regression and multivariate regression, including partial least square, support vector machine and random forest, were tested for their capability to accurately and robustly estimate in-season DMY using reflectance values and vegetation indices obtained from Sentinel-2 spectral bands. Models were built using an iterative (300 times) calibration and validation approach (75% and 25% for calibration and validation, respectively), and their performances were formally evaluated using an independent dataset. Among these algorithms, random forest regression (RFR) produced the most stable and robust results, with Nash–Sutcliffe model efficiency (NSE) values (average ± standard deviation) for the calibration, validation and evaluation of 0.92 ± 0.01, 0.55 ± 0.22 and 0.86 ± 0.04, respectively. Although relatively promising, these results call for larger and more comprehensive datasets as performances vary largely between calibration, validation and evaluation datasets. Moreover, RFR, as any machine learning algorithm regression, requires a very large dataset to become stable in terms of performance.

Water level prediction using soft computing techniques: A case study in the Malwathu Oya, Sri Lanka.

Hydrologic models to simulate river flows are computationally costly. In addition to the precipitation and other meteorological time series, catchment characteristics, including soil data, land use, land cover, and roughness, are essential in most hydrologic models. The unavailability of these data series challenged the accuracy of simulations. However, recent advances in soft computing techniques offer better approaches and solutions at less computational complexity. These require a minimum amount of data, while they reach higher accuracies depending on the quality of data sets. The Gradient Boosting Algorithms and Adaptive Network-based Fuzzy Inference System (ANFIS) are two such systems that can be used in simulating river flows based on the catchment rainfall. In this paper, the computational capabilities of these two systems were tested in simulated river flows by developing the prediction models for Malwathu Oya in Sri Lanka. The simulated flows were then compared with the ground-measured river flows for accuracy. Correlation of coefficient (R), Per cent-Bias (bias), Nash Sutcliffe Model efficiency (NSE), Mean Absolute Relative Error (MARE), Kling-Gupta Efficiency (KGE), and Root mean square error (RMSE) were used as the comparative indices between Gradient Boosting Algorithms and Adaptive Network-based Fuzzy Inference Systems. Results of the study showcased that both systems can simulate river flows as a function of catchment rainfalls; however, the Cat gradient Boosting algorithm (CatBoost) has a computational edge over the Adaptive Network Based Fuzzy Inference System (ANFIS). The CatBoost algorithm outperformed other algorithms used in this study, with the best correlation score for the testing dataset having 0.9934. The extreme gradient boosting (XGBoost), Light gradient boosting (LightGBM), and Ensemble models scored 0.9283, 0.9253, and 0.9109, respectively. However, more applications should be investigated for sound conclusions.

Suspended sediment transport in Rio Colorado agricultural basin, Argentina

The nutrient input from inland water discharges is vital for the development of marine aquatic fauna, being significantly sensitive to changes in water quality (WQ). The assessment of the contribution and distribution of some water quality parameters (e.g., nutrients, metals and inland organic compounds) is of vital importance, especially in irrigation basins. The study area is the Bonaerense Valley of the Colorado River (BVCR) and Mar Argentino, near the mouth of the Colorado River (Buenos Aires, Argentina). The study of water quality parameters is performed in an indirect way, by studying the spatiotemporal dynamics of cohesive sediment (CS), this is possible because the CS has a fundamental role in the transport of substances by adsorption/desorption interactions. We used numerical models (MOHID Land and MOHID Water) in a coupled way, evaluating the complex dynamics involved. The evaluated parameters (flow, velocity, cohesive sediment, salinity and temperature) were calibrated and subsequently validated with data from 7 monitoring stations, located along the Colorado River and adjacent water collectors. Calibration and validation values are within an acceptable range for the purposes, with mean values of 0.8 for NSE (Nash-Sutcliffe model efficiency coefficient), 0.9 (Pearson correlation) for calibration and 0.6 (NSE), 0.9 (Pearson) for validation. The irrigation zone (through the collectors) shows a significative contribution of cohesive sediment, on the order of 300 ppm. The river presents approximately 100 ppm and generates a plume along the coast to the northwest.

Assessing the sensitivity of multi-frequency passive microwave vegetation optical depth to vegetation properties

Abstract. Vegetation attenuates the microwave emission from the land surface. The strength of this attenuation is quantified in models in terms of the parameter vegetation optical depth (VOD) and is influenced by the vegetation mass, structure, water content, and observation wavelength. Earth observation satellite sensors operating in the microwave frequencies are used for global VOD retrievals, enabling the monitoring of vegetation at large scales. VOD has been used to determine above-ground biomass, monitor phenology, or estimate vegetation water status. VOD can be also used for constraining land surface models or modelling wildfires at large scales. Several VOD products exist, differing by frequency/wavelength, sensor, and retrieval algorithm. Numerous studies present correlations or empirical functions between different VOD datasets and vegetation variables such as the normalized difference vegetation index, leaf area index, gross primary production, biomass, vegetation height, or vegetation water content. However, an assessment of the joint impact of land cover, vegetation biomass, leaf area, and moisture status on the VOD signal is challenging and has not yet been done. This study aims to interpret the VOD signal as a multi-variate function of several descriptive vegetation variables. The results will help to select VOD at the most suitable wavelength for specific applications and can guide the development of appropriate observation operators to integrate VOD with large-scale land surface models. Here we use VOD from the Land Parameter Retrieval Model (LPRM) in the Ku, X, and C bands from the harmonized Vegetation Optical Depth Climate Archive (VODCA) dataset and L-band VOD derived from Soil Moisture and Ocean Salinity (SMOS) and Soil Moisture Active Passive (SMAP) sensors. The leaf area index, live-fuel moisture content, above-ground biomass, and land cover are able to explain up to 93 % and 95 % of the variance (Nash–Sutcliffe model efficiency coefficient) in 8-daily and monthly VOD within a multi-variable random forest regression. Thereby, the regression reproduces spatial patterns of L-band VOD and spatial and temporal patterns of Ku-, X-, and C-band VOD. Analyses of accumulated local effects demonstrate that Ku-, X-, and C-band VOD are mostly sensitive to the leaf area index, and L-band VOD is most sensitive to above-ground biomass. However, for all VODs the global relationships with vegetation properties are non-monotonic and complex and differ with land cover type. This indicates that the use of simple global regressions to estimate single vegetation properties (e.g. above-ground biomass) from VOD is over-simplistic.