Integrating Support Vector Regression and a geomorphologic Artificial Neural Network for daily rainfall-runoff modeling

Optimization of Fly Ash-Slag One-Part Geopolymers with Improved Properties

One-part geopolymer concrete/mortar is a pre-mixed material made from industrial by-products and solid alkaline activators that only requires the addition of water for activation. Apart from being environmentally friendly, it also reduces complexity and improves consistency in the mixing process, leading to more efficient production and consistent material properties. However, developing one-part geopolymer concrete with desirable compressive strength is challenging because of the complexity of the chemical reaction involved, the variability of the raw materials used, and the need for precise control of curing conditions. Therefore, 80 different one-part geopolymer mixtures were compiled from the open literature in this study, and the effects of the constituent materials, the dosage of alkaline activators, curing condition, and water/binder ratio on the 28-day compressive strength of one-part geopolymer paste were examined in detail. An ANN model with the Levenberg-Marquardt algorithm was developed to estimate one-part geopolymer's compressive strength and its sensitivity to binder constituents and alkaline dosage. The ANN model's weights and biases were also used to develop a CPLEX-based optimization method for achieving maximum compressive strength. The results confirm that the compressive strength of one-part geopolymer pastes increased by increasing the Na₂O content of the alkaline source and the slag dosage; however, increasing the Na₂O content in alkaline sources beyond 6% by fly ash weight led to decreasing the compressive strength; therefore, the optimum alkaline activator dosage by weight of fly ash was to be 12% (i.e., 6% Na₂O). The proposed ANN model developed in this study can aid in the production and performance tuning of sustainable one-part geopolymer concrete and mortar for broader full-scale applications.

Physics-Informed Data-Driven Model for Predicting Streamflow: A Case Study of the Voshmgir Basin, Iran

Accurate rainfall-runoff modeling is crucial for water resource management. However, the available models require more field-measured data to produce accurate results, which has been a long-term issue in hydrological modeling. Machine learning (ML) models have shown superiority in the hydrological field over statistical models. The primary aim of the present study was to advance a new coupled model combining model-driven models and ML models for accurate rainfall-runoff simulation in the Voshmgir basin in northern Iran. Rainfall-runoff data from 2002 to 2007 were collected from the tropical rainfall measuring mission (TRMM) satellite and the Iran water resources management company. The findings revealed that the model-driven model could not fully describe river runoff patterns during the investigated time period. The extreme learning machine and support vector regression models showed similar performances for 1-day-ahead rainfall–runoff forecasting, while the long short-term memory (LSTM) model outperformed these two models. Our results demonstrated that the coupled physically based model and LSTM model outperformed other models, particularly for 1-day-ahead forecasting. The present methodology could be potentially applied in the same hydrological properties catchment.

Prediction of Flow Based on a CNN-LSTM Combined Deep Learning Approach

Although machine learning (ML) techniques are increasingly used in rainfall-runoff models, most of them are based on one-dimensional datasets. In this study, a rainfall-runoff model with deep learning algorithms (CNN-LSTM) was proposed to compute runoff in the watershed based on two-dimensional rainfall radar maps directly. The model explored a convolutional neural network (CNN) to process two-dimensional rainfall maps and long short-term memory (LSTM) to process one-dimensional output data from the CNN and the upstream runoff in order to calculate the flow of the downstream runoff. In addition, the Elbe River basin in Sachsen, Germany, was selected as the study area, and the high-water periods of 2006, 2011, and 2013, and the low-water periods of 2015 and 2018 were used as the study periods. Via the fivefold validation, we found that the Nash–Sutcliffe efficiency (NSE) and Kling–Gupta efficiency (KGE) fluctuated from 0.46 to 0.97 and from 0.47 to 0.92 for the high-water period, where the optimal fold achieved 0.97 and 0.92, respectively. For the low-water period, the NSE and KGE ranged from 0.63 to 0.86 and from 0.68 to 0.93, where the optimal fold achieved 0.86 and 0.93, respectively. Our results demonstrate that CNN-LSTM would be useful for estimating water availability and flood alerts for river basin management.

Remote-Sensing-Based Streamflow Forecasting Using Artificial Neural Network and Support Vector Machine Models

In this study, we aimed to investigate the hydrological performance of three gridded precipitation products—CHIRPS, RFE, and TRMM3B42V7—in monthly streamflow forecasting. After statistical evaluation, two monthly streamflow forecasting models—support vector machine (SVM) and artificial neural network (ANN)—were developed using the monthly temporal resolution data derived from these products. The hydrological performance of the developed forecasting models was then evaluated using several statistical indices, including NSE, MAE, RMSE, and R2. The performance measures confirmed that the CHIRPS product has superior performance compared to RFE 2.0 and TRMM data, and it could provide reliable rainfall estimates for use as input in forecasting models. Likewise, the results of the forecasting models confirmed that the ANN and SVM both achieved acceptable levels of accuracy for forecasting streamflow; however, the ANN model was superior (R2 = 0.898–0.735) to the SVM (R2 = 0.742–0.635) in both the training and testing periods.

How do urban rainfall-runoff pollution control technologies develop in China? A systematic review based on bibliometric analysis and literature summary

Rapid urbanization in China is driving the need of urban rainfall-runoff pollution control technologies due to adverse impacts on water environment. In this study, literature from China National Knowledge Infrastructure, Web of Science and Scopus in 1995/1/1-2019/5/15 are used to review research hotspots, development process and future directions of urban rainfall-runoff pollution control technologies in China and global world. Temporal evolution of publications showed that source reduction played better growing trend in urban rainfall-runoff pollution control field for both China and global world. Furthermore, with bibliometric tool, density visualization maps and co-occurrence network maps were created to identify research hotspots in China and global world. By comprehensively analyzing research hotspots above and development process from extracted literature, future directions of urban rainfall-runoff pollution control technologies were predicted. For model and strategy, both China and global world would concern on the accuracy of models to evaluate combination technologies. For source reduction, China would explore rainwater purification in sponge city, while global world would investigate match characteristics between specific regions and control technologies, combination between model and technologies, and improvement of pollutants removal. For process control, China would enhance ecological gutter inlet performance, whereas global world would concentrate on optimization of rainwater harvesting system. For post treatment, China would estimate modified hydrocylone and coagulation technology, and improve performance of filtration systems, riparian buffers and constructed wetlands, while global world would explore ecological and landscape function of constructed wetlands. Since China ranked first in producing Western publications and was the second most cited country for Western publications recently, China would significantly influence future development of urban rainfall-runoff pollution control technologies around the world. Meanwhile, some directions including infiltration basin and rainwater harvesting system were still shortcomings for China due to a late start of urban rainfall-runoff pollution control technologies in China.

The Short-Term Load Forecasting for Special Days Based on Bagged Regression Trees in Qingdao, China

There are many factors that affect short-term load forecasting performance, such as weather and holidays. However, most of the existing load forecasting models lack more detailed considerations for some special days. In this paper, the applicability of the bagged regression trees (BRT) model combined with eight variables is investigated to forecast short-term load in Qingdao. The comparative experiments show that the accuracy and speed of forecasting have some improvements using the BRT than the artificial neural network (ANN). Then, an indicator variable is newly proposed to capture the abnormal information during special days, which include national statutory holidays, bridging days, and proximity days. The BRT model combined with this indicator variable is tested on the load series measured in 2018. Experiments demonstrate that the improved model generates more accurate predictive results than BRT model combined with previously variables on special days.

Prediction of River Stage Using Multistep-Ahead Machine Learning Techniques for a Tidal River of Taiwan

Time-series prediction of a river stage during typhoons or storms is essential for flood control or flood disaster prevention. Data-driven models using machine learning (ML) techniques have become an attractive and effective approach to modeling and analyzing river stage dynamics. However, relatively new ML techniques, such as the light gradient boosting machine regression (LGBMR), have rarely been applied to predict the river stage in a tidal river. In this study, data-driven ML models were developed under a multistep-ahead prediction framework and evaluated for river stage modeling. Four ML techniques, namely support vector regression (SVR), random forest regression (RFR), multilayer perceptron regression (MLPR), and LGBMR, were employed to establish data-driven ML models with Bayesian optimization. The models were applied to simulate river stage hydrographs of the tidal reach of the Lan-Yang River Basin in Northeastern Taiwan. Historical measurements of rainfall, river stages, and tidal levels were collected from 2004 to 2017 and used for training and validation of the four models. Four scenarios were used to investigate the effect of the combinations of input variables on river stage predictions. The results indicated that (1) the tidal level at a previous stage significantly affected the prediction results; (2) the LGBMR model achieves more favorable prediction performance than the SVR, RFR, and MLPR models; and (3) the LGBMR model could efficiently and accurately predict the 1–6-h river stage in the tidal river. This study provides an extensive and insightful comparison of four data-driven ML models for river stage forecasting that can be helpful for model selection and flood mitigation.

Comparative Analysis of Artificial Intelligence Models for Accurate Estimation of Groundwater Nitrate Concentration

Prediction of the groundwater nitrate concentration is of utmost importance for pollution control and water resource management. This research aims to model the spatial groundwater nitrate concentration in the Marvdasht watershed, Iran, based on several artificial intelligence methods of support vector machine (SVM), Cubist, random forest (RF), and Bayesian artificial neural network (Baysia-ANN) machine learning models. For this purpose, 11 independent variables affecting groundwater nitrate changes include elevation, slope, plan curvature, profile curvature, rainfall, piezometric depth, distance from the river, distance from residential, Sodium (Na), Potassium (K), and topographic wetness index (TWI) in the study area were prepared. Nitrate levels were also measured in 67 wells and used as a dependent variable for modeling. Data were divided into two categories of training (70%) and testing (30%) for modeling. The evaluation criteria coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE), and Nash–Sutcliffe efficiency (NSE) were used to evaluate the performance of the models used. The results of modeling the susceptibility of groundwater nitrate concentration showed that the RF (R² = 0.89, RMSE = 4.24, NSE = 0.87) model is better than the other Cubist (R² = 0.87, RMSE = 5.18, NSE = 0.81), SVM (R² = 0.74, RMSE = 6.07, NSE = 0.74), Bayesian-ANN (R² = 0.79, RMSE = 5.91, NSE = 0.75) models. The results of groundwater nitrate concentration zoning in the study area showed that the northern parts of the case study have the highest amount of nitrate, which is higher in these agricultural areas than in other areas. The most important cause of nitrate pollution in these areas is agriculture activities and the use of groundwater to irrigate these crops and the wells close to agricultural areas, which has led to the indiscriminate use of chemical fertilizers by irrigation or rainwater of these fertilizers is washed and penetrates groundwater and pollutes the aquifer.

Annual Runoff Forecasting Based on Multi-Model Information Fusion and Residual Error Correction in the Ganjiang River Basin

Accurate forecasting of annual runoff time series is of great significance for water resources planning and management. However, considering that the number of forecasting factors is numerous, a single forecasting model has certain limitations and a runoff time series consists of complex nonlinear and nonstationary characteristics, which make the runoff forecasting difficult. Aimed at improving the prediction accuracy of annual runoff time series, the principal components analysis (PCA) method is adopted to reduce the complexity of forecasting factors, and a modified coupling forecasting model based on multiple linear regression (MLR), back propagation neural network (BPNN), Elman neural network (ENN), and particle swarm optimization-support vector machine for regression (PSO-SVR) is proposed and applied in the Dongbei Hydrological Station in the Ganjiang River Basin. Firstly, from two conventional factors (i.e., rainfall, runoff) and 130 atmospheric circulation indexes (i.e., 88 atmospheric circulation indexes, 26 sea temperature indexes, 16 other indexes), principal components generated by linear mapping are screened as forecasting factors. Then, based on above forecasting factors, four forecasting models including MLR, BPNN, ENN, and PSO-SVR are developed to predict annual runoff time series. Subsequently, a coupling model composed of BPNN, ENN, and PSO-SVR is constructed by means of a multi-model information fusion taking three hydrological years (i.e., wet year, normal year, dry year) into consideration. Finally, according to residual error correction, a modified coupling forecasting model is introduced so as to further improve the accuracy of the predicted annual runoff time series in the verification period.

A Hybrid Approach Combining Conceptual Hydrological Models, Support Vector Machines and Remote Sensing Data for Rainfall-Runoff Modeling

Understanding catchment response to rainfall events is important for accurate runoff estimation in many water-related applications, including water resources management. This study introduced a hybrid model, the Tank-least squared support vector machine (LSSVM), that incorporated intermediate state variables from a conceptual tank model within the least squared support vector machine (LSSVM) framework in order to describe aspects of the rainfall-runoff (RR) process. The efficacy of the Tank-LSSVM model was demonstrated with hydro-meteorological data measured in the Yongdam Catchment between 2007 and 2016, South Korea. We first explored the role of satellite soil moisture (SM) data (i.e., European Space Agency (ESA) CCI) in the rainfall-runoff modeling. The results indicated that the SM states inferred from the ESA CCISWI provided an effective means of describing the temporal dynamics of SM. Further, the Tank-LSSVM model’s ability to simulate daily runoff was assessed by using goodness of fit measures (i.e., root mean square error, Nash Sutcliffe coefficient (NSE), and coefficient of determination). The Tank-LSSVM models’ NSE were all classified as “very good” based on their performance during the training and testing periods. Compared to individual LSSVM and Tank models, improved daily runoff simulations were seen in the proposed Tank-LSSVM model. In particular, low flow simulations demonstrated the improvement of the Tank-LSSVM model compared to the conventional tank model.

Prediction of Precipitation Based on Recurrent Neural Networks in Jingdezhen, Jiangxi Province, China

Precipitation is a critical input for hydrologic simulation and prediction, and is widely used for agriculture, water resources management, and prediction of flood and drought, among other activities. Traditional precipitation prediction researches often established one or more probability models of historical data based on the statistical prediction methods and machine learning techniques. However, few studies have been attempted deep learning methods such as the state-of-the-art for Recurrent Neural Networks (RNNs) networks in meteorological sequence time series predictions. We deployed Long Short-Term Memory (LSTM) network models for predicting the precipitation based on meteorological data from 2008 to 2018 in Jingdezhen City. After identifying the correlation between meteorological variables and the precipitation, nine significant input variables were selected to construct the LSTM model. Then, the selected meteorological variables were refined by the relative importance of input variables to reconstruct the LSTM model. Finally, the LSTM model with final selected input variables is used to predict the precipitation and the performance is compared with other classical statistical algorithms and the machine learning algorithms. The experimental results show that the LSTM is suitable for precipitation prediction. The RNN models, combined with meteorological variables, could predict the precipitation accurately in Jingdezhen City and provide sufficient time to prepare strategies against potential related disasters.

Flash Flood Forecasting Using Support Vector Regression Model in a Small Mountainous Catchment

Flash floods in mountainous catchments are often caused by the rainstorm, which may result in more severe consequences than plain area floods due to less timescale and a fast-flowing front of water and debris. Flash flood forecasting is a huge challenge for hydrologists and managers due to its instantaneity, nonlinearity, and dependency. Among different methods of flood forecasting, data-driven models have become increasingly popular in recent years due to their strong ability to simulate nonlinear hydrological processes. This study proposed a Support Vector Regression (SVR) model, which is a powerful artificial intelligence-based model originated from statistical learning theory, to forecast flash floods at different lead times in a small mountainous catchment. The lagged average rainfall and runoff are identified as model input variables, and the time lags associated with the model input variables are determined by the hydrological concept of the time of response. There are 69 flash flood events collected from 1984 to 2012 in a mountainous catchment in China and then used for the model training and testing. The contribution of the runoff variables to the predictions and the phase lag of model outputs are analyzed. The results show that: (i) the SVR model has satisfactory predictive performances for one to three-hours ahead forecasting; (ii) the lagged runoff variables have a more significant effect on the predictions than the rainfall variables; and (iii) the phase lag (time difference) of prediction results significantly exists in both two- and three-hours-ahead forecasting models, however, the input rainfall information can assist in mitigating the phase lag of peak flow.

Integrated Real-Time Flood Forecasting and Inundation Analysis in Small–Medium Streams

This study presents the application of an adaptive neuro-fuzzy inference system (ANFIS) and one dimensional (1-D) and two dimensional (2-D) hydrodynamic models to improve the problems of hydrological models currently used for flood forecasting in small–medium streams of South Korea. The optimal combination of input variables (e.g., rainfall and water level) in ANFIS was selected based on a statistical analysis of the observed and forecasted values. Two membership functions (MFs) and two ANFIS rules were determined by the subtractive clustering (SC) approach in the processes of training and checking. The developed ANFIS was applied to Jungrang Stream and water levels for six lead times (0.5, 1.0, 1.5, 2.0, 2.5, and 3.0 hour) were forecasted. Based on point forecasted water levels by ANFIS, 1-D section flood forecast and 2-D spatial inundation analysis were carried out. This study demonstrated that the proposed methodology can forecast flooding based only on observed rainfall and water level without extensive physical and topographic data, and can be performed in real-time by integrating point- and section flood forecasting and spatial inundation analysis.

Rainfall-Runoff Modelling Using Hydrological Connectivity Index and Artificial Neural Network Approach

The input selection process for data-driven rainfall-runoff models is critical because input vectors determine the structure of the model and, hence, can influence model results. Here, hydro-geomorphic and biophysical time series inputs, including Normalized Difference Vegetation Index (NDVI) and Index of Connectivity (IC; a type of hydrological connectivity index), in addition to climatic and hydrologic inputs were assessed. Selected inputs were used to develop Artificial Neural Networks (ANNs) in the Haughton River catchment and the Calliope River catchment, Queensland, Australia. Results show that incorporating IC as a hydro-geomorphic parameter and remote sensing NDVI as a biophysical parameter, together with rainfall and runoff as hydro-climatic parameters, can improve ANN model performance compared to ANN models using only hydro-climatic parameters. Comparisons amongst different input patterns showed that IC inputs can contribute to further improvement in model performance, than NDVI inputs. Overall, ANN model simulations showed that using IC along with hydro-climatic inputs noticeably improved model performance in both catchments, especially in the Calliope catchment. This improvement is indicated by a slight increase (9.77% and 11.25%) in the Nash–Sutcliffe efficiency and noticeable decrease (24.43% and 37.89%) in the root mean squared error of monthly runoff from Haughton River and Calliope River, respectively. Here, we demonstrate the significant effect of hydro-geomorphic and biophysical time series inputs for estimating monthly runoff using ANN data-driven models, which are valuable for water resources planning and management.

Assessment of Machine Learning Techniques for Monthly Flow Prediction

Monthly flow predictions provide an essential basis for efficient decision-making regarding water resource allocation. In this paper, the performance of different popular data-driven models for monthly flow prediction is assessed to detect the appropriate model. The considered methods include feedforward neural networks (FFNNs), time delay neural networks (TDNNs), radial basis neural networks (RBFNNs), recurrent neural network (RNN), a grasshopper optimization algorithm (GOA)-based support vector machine (SVM) and K-nearest neighbors (KNN) model. For this purpose, the performance of each model is evaluated in terms of several residual metrics using a monthly flow time series for two real case studies with different flow regimes. The results show that the KNN outperforms the different neural network configurations for the first case study, whereas RBFNN model has better performance for the second case study in terms of the correlation coefficient. According to the accuracy of the results, in the first case study with more input features, the KNN model is recommended for short-term predictions and for the second case with a smaller number of input features, but more training observations, the RBFNN model is suitable.

Flood Forecasting Based on an Improved Extreme Learning Machine Model Combined with the Backtracking Search Optimization Algorithm

Flood forecasting plays an important role in flood control and water resources management. Recently, the data-driven models with a simpler model structure and lower data requirement attract much more attentions. An extreme learning machine (ELM) method, as a typical data-driven method, with the advantages of a faster learning process and stronger generalization ability, has been taken as an effective tool for flood forecasting. However, an ELM model may suffer from local minima in some cases because of its random generation of input weights and hidden layer biases, which results in uncertainties in the flood forecasting model. Therefore, we proposed an improved ELM model for short-term flood forecasting, in which an emerging dual population-based algorithm, named backtracking search algorithm (BSA), was applied to optimize the parameters of ELM. Thus, the proposed method is called ELM-BSA. The upper Yangtze River was selected as a case study. Several performance indexes were used to evaluate the efficiency of the proposed ELM-BSA model. Then the proposed model was compared with the currently used general regression neural network (GRNN) and ELM models. Results show that the ELM-BSA can always provide better results than the GRNN and ELM models in both the training and testing periods. All these results suggest that the proposed ELM-BSA model is a promising alternative technique for flood forecasting.

Future Predictions of Rainfall and Temperature Using GCM and ANN for Arid Regions: A Case Study for the Qassim Region, Saudi Arabia

Future predictions of rainfall patterns in water-scarce regions are highly important for effective water resource management. Global circulation models (GCMs) are commonly used to make such predictions, but these models are highly complex and expensive. Furthermore, their results are associated with uncertainties and variations for different GCMs for various greenhouse gas emission scenarios. Data-driven models including artificial neural networks (ANNs) and adaptive neuro fuzzy inference systems (ANFISs) can be used to predict long-term future changes in rainfall and temperature, which is a challenging task and has limitations including the impact of greenhouse gas emission scenarios. Therefore, in this research, results from various GCMs and data-driven models were investigated to study the changes in temperature and rainfall of the Qassim region in Saudi Arabia. Thirty years of monthly climatic data were used for trend analysis using Mann–Kendall test and simulating the changes in temperature and rainfall using three GCMs (namely, HADCM3, INCM3, and MPEH5) for the A1B, A2, and B1 emissions scenarios as well as two data-driven models (ANN: feed-forward-multilayer, perceptron and ANFIS) without the impact of any emissions scenario. The results of the GCM were downscaled for the Qassim region using the Long Ashton Research Station’s Weather Generator 5.5. The coefficient of determination (R2) and Akaike’s information criterion (AIC) were used to compare the performance of the models. Results showed that the ANNs could outperform the ANFIS for predicting long-term future temperature and rainfall with acceptable accuracy. All nine GCM predictions (three models with three emissions scenarios) differed significantly from one another. Overall, the future predictions showed that the temperatures of the Qassim region will increase with a specified pattern from 2011 to 2099, whereas the changes in rainfall will differ over various spans of the future.