Coupling hydrological modeling and support vector regression to model hydropeaking in alpine catchments

Application of classification machine learning algorithms for characterizing nutrient transport in a clay plain agricultural watershed

Excess nutrients in surface water and groundwater can lead to water quality deterioration in available water resources. Thus, the classification of nutrient concentrations in water resources has gained significant attention during recent decades. Machine learning (ML) algorithms are considered an efficient tool to describe nutrient loss from agricultural land to surface water and groundwater. Previous studies have applied regression and classification ML algorithms to predict nutrient concentrations in surface water and/or groundwater, or to categorize an output variable using a limited number of input variables. However, there have been no studies that examined the application of different ML classification algorithms in agricultural settings to classify various output variables using a wide range of input variables. In this study, twenty-four ML classification algorithms were implemented on a dataset from three locations within the Upper Parkhill watershed, an agricultural watershed in southern Ontario, Canada. Nutrient concentrations in surface water were classified using geochemical and physical water parameters of surface water and groundwater (e.g., pH), climate and field conditions as the input variables. The performance of these algorithms was evaluated using four evaluation metrics (e.g., classification accuracy) to identify the optimal algorithm for classifying the output variables. Ensemble bagged trees was found to be the optimal ML algorithm for classifying nitrate concentration in surface water (accuracy of 90.9%), while the weighted KNN was the most appropriate algorithm for categorizing the total phosphorus concentration (accuracy of 87%). The ensemble subspace discriminant algorithm gave the highest overall classification accuracy for the concentration of soluble reactive phosphorus and total dissolved phosphorus in surface water with an accuracy of 79.2% and 77.9%, respectively. This study exemplifies that ML algorithms can be used to signify exceedance of recommended concentrations of nutrients in surface waters in agricultural watersheds. Results are useful for decision makers to develop nutrient management strategies.

Towards a Comprehensive Assessment of Statistical versus Soft Computing Models in Hydrology: Application to Monthly Pan Evaporation Prediction

This paper evaluates six soft computational models along with three statistical data-driven models for the prediction of pan evaporation (EP). Accordingly, improved kriging—as a novel statistical model—is proposed for accurate predictions of EP for two meteorological stations in Turkey. In the standard kriging model, the input data nonlinearity effects are increased by using a nonlinear map and transferring input data from a polynomial to an exponential basic function. The accuracy, precision, and over/under prediction tendencies of the response surface method, kriging, improved kriging, multilayer perceptron neural network using the Levenberg–Marquardt (MLP-LM) as well as a conjugate gradient (MLP-CG), radial basis function neural network (RBFNN), multivariate adaptive regression spline (MARS), M5Tree and support vector regression (SVR) were compared. Overall, all the applied models were highly capable of predicting monthly EP in both stations with a mean absolute error (MAE) < 0.77 mm and a Willmott index (d) > 0.95. Considering periodicity as an input parameter, the MLP-LM provided better results than the other methods among the soft computing models (MAE = 0.492 mm and d = 0.981). However, the improved kriging method surpassed all the other models based on the statistical measures (MAE = 0.471 mm and d = 0.983). Finally, the outcomes of the Mann–Whitney test indicated that the applied soft computational models do not have significant superiority over the statistical ones (p-value > 0.65 at α = 0.01 and α = 0.05).

Enhanced streamflow prediction with SWAT using support vector regression for spatial calibration: A case study in the Illinois River watershed, U.S

Accurate streamflow prediction plays a pivotal role in hydraulic project design, nonpoint source pollution estimation, and water resources planning and management. However, the highly non-linear relationship between rainfall and runoff makes prediction difficult with desirable accuracy. To improve the accuracy of monthly streamflow prediction, a seasonal Support Vector Regression (SVR) model coupled to the Soil and Water Assessment Tool (SWAT) model was developed for 13 subwatersheds in the Illinois River watershed (IRW), U.S. Terrain, precipitation, soil, land use and land cover, and monthly streamflow data were used to build the SWAT model. SWAT Streamflow output and the upstream drainage area were used as two input variables into SVR to build the hybrid SWAT-SVR model. The Calibration Uncertainty Procedure (SWAT-CUP) and Sequential Uncertainty Fitting-2 (SUFI-2) algorithms were applied to compare the model performance against SWAT-SVR. The spatial calibration and leave-one-out sampling methods were used to calibrate and validate the hybrid SWAT-SVR model. The results showed that the SWAT-SVR model had less deviation and better performance than SWAT-CUP simulations. SWAT-SVR predicted streamflow more accurately during the wet season than the dry season. The model worked well when it was applied to simulate medium flows with discharge between 5 m³ s^-1 and 30 m³ s^-1, and its applicable spatial scale fell between 500 to 3000 km². The overall performance of the model on yearly time series is “Satisfactory”. This new SWAT-SVR model has not only the ability to capture intrinsic non-linear behaviors between rainfall and runoff while considering the mechanism of runoff generation but also can serve as a reliable regional tool for an ungauged or limited data watershed that has similar hydrologic characteristics with the IRW.

Reservoir Sediment Management Using Artificial Neural Networks: A Case Study of the Lower Section of the Alpine Saalach River

Reservoir sedimentation is a critical issue worldwide, resulting in reduced storage volumes and, thus, reservoir efficiency. Moreover, sedimentation can also increase the flood risk at related facilities. In some cases, drawdown flushing of the reservoir is an appropriate management tool. However, there are various options as to how and when to perform such flushing, which should be optimized in order to maximize its efficiency and effectiveness. This paper proposes an innovative concept, based on an artificial neural network (ANN), to predict the volume of sediment flushed from the reservoir given distinct input parameters. The results obtained from a real-world study area indicate that there is a close correlation between the inputs—including peak discharge and duration of flushing—and the output (i.e., the volume of sediment). The developed ANN can readily be applied at the real-world study site, as a decision-support system for hydropower operators.

Multi-temporal scale analysis of complementarity between hydro and solar power along an alpine transect

Variable renewable energy sources display different space-time variability driving the availability of energy generated from these sources. Complementarity among variable renewable energies in time and space allows reducing the variability of power supply and helps matching the electricity demand curve. This work investigates the temporal structure of complementarity along an alpine transect in North-East Italy, considering a 100% renewable energy mix scenario composed by photovoltaic and run-of-the-river energy. We analyze the dominant scales of variability of variable renewable energy sources and electricity demand. In addition, we introduce a new metric, the wavelet-based complementarity index, to quantify the potential complementarity between two different energy sources. We show that this index varies at different temporal scales and it helps explaining the discrepancy between demand and supply in the study area. Continuous and discrete wavelet analyses are applied to assess the energy balance variability at multiple temporal scales and to identify the optimal mix of renewable energies, respectively. This work describes therefore an effective approach to investigate the temporal-scale dependency of the variance in the energy balance and can be further extended to different and more complex situations.

How does climate variability affect water quality dynamics in Canada's oil sands region?

In Canada's oil sands region, classic boreal hydrology (i.e., winter low flow followed by peaks during spring freshet and then summer flow recession) combined with erosion of both natural and anthropogenically-exposed bitumen results in seasonal and inter-annual variability in stream water chemistry. Using data collected from all seasons over three years (2012-2015), we investigated the mechanisms driving spatial and temporal change in the concentration of 26 water quality parameters for six rivers draining Canada's oil sands region. Mantel tests showed a strong spatial aggregation of climatic drivers (average daily precipitation, accumulated precipitation, snow water equivalent) associated with west versus east discharge patterns. Wavelet analysis highlighted unique watershed attributes, in particular the importance of developed area in lowering responsiveness to seasonal precipitation. Concentrations of most chemical parameters (20 of 23) showed distinct temporal patterns that were correlated with seasonal changes in hydrology which, in turn, were related to changes in weather. Comparison of concentrations observed in this study with those reported in the scientific literature for the same watersheds showed 81% of comparisons differed significantly. This was likely due to the short duration of previous field campaigns and thus the sampling of a very narrow window of the annual streamflow regime.

Review of Watershed-Scale Water Quality and Nonpoint Source Pollution Models

Watershed-scale nonpoint source (NPS) pollution models have become important tools to understand, evaluate, and predict the negative impacts of NPS pollution on water quality. Today, there are many NPS models available for users. However, different types of models possess different form and structure as well as complexity of computation. It is difficult for users to select an appropriate model for a specific application without a clear understanding of the limitations or strengths for each model or tool. This review evaluates 14 more commonly used watershed-scale NPS pollution models to explain how and when the application of these different models are appropriate for a given effort. The models that are assessed have a wide range of capacities that include simple models used as rapid screening tools (e.g., Long-Term Hydrologic Impact Assessment (L-THIA) and Nonpoint Source Pollution and Erosion Comparison Tool (N-SPECT/OpenNSPECT)), medium-complexity models that require detail data input and limited calibration (e.g., Generalized Watershed Loading Function (GWLF), Loading Simulation Program C (LSPC), Source Loading and Management Model (SLAMM), and Watershed Analysis Risk Management Frame (WARMF)), complex models that provide sophisticated simulation for NPS pollution processes with intensive data and rigorous calibration (e.g., Agricultural Nonpoint Source pollution model (AGNPS/AnnAGNPS), Soil and Water Assessment Tool (SWAT), Stormwater Management Model (SWMM), and Hydrologic Simulation Program Fortran (HSPF)), and modeling systems that integrate various sub-models and tools, and contain the highest complexity to solve all phases of hydrologic, hydraulic, and chemical dynamic processes (e.g., Automated Geospatial Watershed Assessment Tool (AGWA), Better Assessment Science Integrating Point and Nonpoint Sources (BASINS) and Watershed Modeling System (WMS)). This assessment includes model intended use, components or capabilities, suitable land-use type, input parameter type, spatial and temporal scale, simulated pollutants, strengths and limitations, and software availability. Understanding the strengths and weaknesses of each watershed-scale NPS model will lead to better model selection for suitability and help to avoid misinterpretation or misapplication in practice. The article further explains the crucial criteria for model selection, including spatial and temporal considerations, calibration and validation, uncertainty analysis, and future research direction of NPS pollution models. The goal of this work is to provide accurate and concise insight for watershed managers and planners to select the best-suited model to reduce the harm of NPS pollution to watershed ecosystems.

Predicting Habitat Suitability and Conserving Juniperus spp. Habitat Using SVM and Maximum Entropy Machine Learning Techniques

Support vector machine (SVM) and maximum entropy (MaxEnt) machine learning techniques are well suited to model the habitat suitability of species. In this study, SVM and MaxEnt models were developed to predict the habitat suitability of Juniperus spp. in the Southern Zagros Mountains of Iran. In recent decades, drought extension and climate alteration have led to extensive changes in the geographical occurrence of this species and its growth and regeneration are extremely limited in this area. This study evaluated the habitat suitability of Juniperus through spatial modeling and predicts appropriate regions for future cultivation and resource conservation. We modeled the natural habitat of Juniperus for an area of 700 ha in Sepidan Area in the Fars province using (1) data regarding the presence of the species (295 samples) collected through field surveys and GPS, (2) habitat soil information and indices derived from 60 soil samples collected in the study area, and (3) climatic and topographic datasets collected from various sources. In total, 15 conditioning factors were used for this spatial modeling approach. Receiver operator characteristic (ROC) curves were applied to estimate the accuracy of the habitat suitability models produced by the SVM and MaxEnt techniques. Results indicated logical and similar area under the curve (AUC)-ROC values for the SVM (0.735) and MaxEnt (0.728) models. Both the SVM and MaxEnt methods revealed a significant relationship between the Juniperus spp. distribution and conditioning factors. Environmental factors played a vital role in evaluating the presence of Juniperus sp. as Max and Min temperatures and annual mean rainfall were the three most important factors for habitat suitability in the study area. Finally, an area with high and very high suitability for the future cultivation of Juniperus sp. and for landscape conservation was suggested based on the SVM model.