Nonlinear Hydrological Processes Research Articles

An empirical rainfall threshold approach for the civil protection flood warning system on the Milan urban area

Non-structural risk mitigation tools such as civil protection alerts for citizens proves highly beneficial in minimizing the impacts linked to floods. Flood forecasting represents a challenge due to complex and non-linear hydrological processes involved, especially in highly urbanized areas. In this study, a Flood Warning System (FWS) based on the development of catchment-specific empirical Rainfall Thresholds (RTs) is proposed.Seven river catchments in the “Hydraulic node of Milan,” northern Italy, were analyzed using a dataset of 25 years (1998–2022) of hourly rainfall and discharge data.An empirical methodology, based only on historical rainfall-runoff data and applicable to any river catchment, is proposed with the aim to validate and improve the existing Rainfall Threshold (RT) defined on the same area by the Lombardy Region civil protection.The RTs obtained using the proposed method showed improvements with respect to the existing civil protection RTs, because it allows to derive time-continuous and catchment-specific RTs. Additionally, accounting for the Antecedent Moisture Conditions (AMC) with the proposed “equivalent rainfall” approach results in more accurate RTs, suggesting its consideration for issuing civil protection alerts. The accuracy and uncertainty of the RTs were analyzed by means of binary classification measures coupled with bootstrap resampling.The proposed procedure for constructing RTs, which is applicable to any river catchment having sufficiently long time series of rainfall and runoff data, and not necessarily on urban areas only, indicates potential for being an additional and simple FWS to mitigate flood risks for civil protection purposes.

Artificial Intelligence Techniques in Hydrology and Water Resources Management

The sustainable management of water cycles is crucial in the context of climate change and global warming. It involves managing global, regional, and local water cycles—as well as urban, agricultural, and industrial water cycles—to conserve water resources and their relationships with energy, food, microclimates, biodiversity, ecosystem functioning, and anthropogenic activities. Hydrological modeling is indispensable for achieving this goal, as it is essential for water resources management and mitigation of natural disasters. In recent decades, the application of artificial intelligence (AI) techniques in hydrology and water resources management has made notable advances. In the face of hydro-geo-meteorological uncertainty, AI approaches have proven to be powerful tools for accurately modeling complex, non-linear hydrological processes and effectively utilizing various digital and imaging data sources, such as ground gauges, remote sensing tools, and in situ Internet of Things (IoTs). The thirteen research papers published in this Special Issue make significant contributions to long- and short-term hydrological modeling and water resources management under changing environments using AI techniques coupled with various analytics tools. These contributions, which cover hydrological forecasting, microclimate control, and climate adaptation, can promote hydrology research and direct policy making toward sustainable and integrated water resources management.

Translating seasonal climate forecasts into water balance forecasts for decision making

Seasonal rainfall forecasts support early preparedness. These forecasts are typically disseminated at Regional Climate Outlook Forums (RCOFs), in the form of seasonal tercile probability categories—above normal, normal, below normal. However, these categories cannot be related directly to impacts on terrestrial water stores within catchments, since they are mediated by non-linear hydrological processes occurring on fine spatiotemporal scales, including rainfall partitioning into infiltration, evapotranspiration, runoff and groundwater recharge. Hydrological models are increasingly capable of capturing these processes, but there is no simple way to drive such models with a specific RCOF seasonal tercile rainfall forecast. Here we demonstrate a new method, “Quantile Bin Resampling” (QBR), for producing seasonal water forecasts for a drainage basin by integrating a tercile seasonal rainfall forecast with a hydrological model. QBR is based on mapping historical quantiles of basin-average rainfall to historical simulations of the water balance, and circumvents challenges associated with using climate model output to drive impact models directly. We evaluate QBR by generating 35 years of seasonal reforecasts for various water balance stores and fluxes for the Upper Ewaso Ng’iro basin in Kenya. Hindcasts indicate that when input tercile rainfall forecasts have skill, QBR provides accurate water forecasts at kilometre-scale resolution, which is relevant for anticipatory action down to village level. Pilot operational experimental water forecasts were produced for this basin using QBR for the 2022 March-May rainfall season, then disseminated to regional stakeholders at the Greater Horn of Africa Climate Outlook Forum (GHACOF). We discuss this initiative, along with limitations, plans and future potential of the method. Beyond the demonstrated application to water-related forecasts, QBR can be easily adapted to work with any rainfall-driven impact model. It can translate objective tercile climate probabilities into impact-relevant water balance forecasts at high spatial resolution in an efficient, transparent and flexible way.

Experimental evidence that rill-bed morphology is governed by emergent nonlinear spatial dynamics

Past experimental work found that rill erosion occurs mainly during rill formation in response to feedback between rill-flow hydraulics and rill-bed roughness, and that this feedback mechanism shapes rill beds into a succession of step-pool units that self-regulates sediment transport capacity of established rills. The search for clear regularities in the spatial distribution of step-pool units has been stymied by experimental rill-bed profiles exhibiting irregular fluctuating patterns of qualitative behavior. We hypothesized that the succession of step-pool units is governed by nonlinear-deterministic dynamics, which would explain observed irregular fluctuations. We tested this hypothesis with nonlinear time series analysis to reverse-engineer (reconstruct) state-space dynamics from fifteen experimental rill-bed profiles analyzed in previous work. Our results support this hypothesis for rill-bed profiles generated both in a controlled lab (flume) setting and in an in-situ hillside setting. The results provide experimental evidence that rill morphology is shaped endogenously by internal nonlinear hydrologic and soil processes rather than stochastically forced; and set a benchmark guiding specification and testing of new theoretical framings of rill-bed roughness in soil-erosion modeling. Finally, we applied echo state neural network machine learning to simulate reconstructed rill-bed dynamics so that morphological development could be forecasted out-of-sample.

Artificial Neural Network Technique for Groundwater Modelling of Jaspura Block

As a result of economic development and climatic change, arid and semi-arid areas are confronted with significant difficulties in the management of limited freshwater resources. For the most part, groundwater is the most significant water supply in these regions. Groundwater level prediction is a critical component of appropriate sustainable development and must be done correctly. The use of physical-based models is often used in the modelling and prediction of groundwater. However, owing to data shortages in many arid and semi-arid regions, they are not relevant in these areas. The usefulness of data-driven techniques in modelling complicated and nonlinear hydrological processes has been shown in many studies. It is the implementation and comparison of four algorithm-based models for forecasting groundwater levels that is the focal point of this research. This article compares the different Artificial Neural Network method and applies to the Jaspura Block of Banda Districts which is part of the Yamuna River Basin. For the forecast of groundwater levels four distinct algorithms Levenberg Marquardt, Gradient Descent, Scaled Conjugate Gradient and Bayesian regularization are used for optimal design. The ANN training data for input is collected from Recharge and Discharge data while groundwater level data for output layer were being used. The best algorithm comes to the Levenberg Marquardt algorithm in comparison with the other algorithms.

Hybrid CNN-LSTM models for river flow prediction

Abstract River flow prediction is a challenging problem due to highly nonlinear hydrological processes and high spatio-temporal variability. Here we present a hybrid network of convolutional neural network (CNN) and long short-term memory (LSTM) network for river flow prediction. The hybridization enables accurate identification of the spatial and temporal features in precipitation. A shortcut layer is used as an additional channel of passing input features through the deep network to increase feature diversity. The flows in Hun River Basin, China are predicted using the trained hybrid network and are compared with the results from the Soil and Water Assessment Tool (SWAT) model. The results demonstrate the learning efficiency of the hybrid network is greatly affected by its structure and parameters, including the number of convolutional layers and LSTM cell layers, the step size of pooling and training data size. Further, the shortcut layer can effectively solve the diversity reduction problem in a deep network. The hybrid network is shown to have a similar predictive performance to SWAT but is superior in wet seasons due to its nonlinear learning ability. This study shows that the hybrid network has great promise in learning nonlinear and high spatio-temporal variability in river flow forecasting.

Multiscale relationships between monthly sediment load and pertinent factors in a typical karst mountainous watershed

At different time scales, the potential factors influencing changes in sediment transport vary. Because the processes of each impact factor overlaps on different time scales, it is challenging to evaluate the complex multi-scale relationships between monthly sediment load and its potential impact factors. The objective of this study was to investigate the scale-specific main factors influencing monthly sediment loads using the multivariate empirical mode decomposition (MEMD) method. Monthly sediment loads and five potential influencing factors (runoff, precipitation, air temperature, potential evapotranspiration, and enhanced vegetation index) during 2003–2017 were collected in the Wujiang karst watershed of southwest China. The MEMD method was used to decompose the temporal series of monthly sediment load into seven intrinsic mode functions (IMF) and residuals using a Hilbert transform. The sum of variance contribution rates of IMF1 (3.2 months), IMF2 (5.5 months) and IMF3 (12.1 months) was more than 90%. Although temperature and potential evapotranspiration significantly affect monthly sediment loads at the observation scale, no significant relationships were observed between them at some specific scales after MEMD. The accuracy of the prediction model after MEMD was better than that of the prediction model using original data. Runoff and precipitation were important predictors in the prediction model. This study shows the advantages of the MEMD method for analyzing non-stationary and nonlinear hydrological processes, and this useful tool is recommended for application in other karst watersheds.

Spatio-temporal prediction of soil moisture and soil strength by depth-to-water maps

The utilization of detailed digital terrain models entails an enhanced basis for supporting sustainable forest management, including the reduction of soil impacts through predictions of site trafficability during mechanized harvesting operations. Since wet soils are prone to traffic-induced damages, soil moisture is incorporated into several systems for spatial predictions of trafficability. Yet, only few systems consider temporal dynamics of soil moisture, impeding the accuracy and practical value of predictions. The depth-to-water (DTW) algorithm calculates a cartographic index which indicates wet areas. Temporal dynamics of soil moisture are simulated by different DTW map-scenarios derived from set flow initiation areas (FIA). However, the concept of simulating seasonal moisture conditions by DTW map-scenarios was not analyzed so far. Therefore, we conducted field campaigns at six study sites across Europe, capturing time-series of soil moisture and soil strength along several transects which crossed predicted wet areas. Assuming overall dry conditions (FIA = 4.00 ha), DTW predicted 20% of measuring points to be wet. When a FIA of 1.00 ha (moist conditions) or 0.25 ha (wet conditions) were applied, DTW predicted 29% or 58% of points to be wet, respectively. De facto, 82% of moisture measurements were predicted correctly by the map-scenario for overall dry conditions – with 44% of wet measurements deviating from predictions made. The prediction of soil strength was less successful, with 66% of low values occurring on areas where DTW indicated dryer soils and subsequently a sufficient trafficability. The condition-specific usage of different map-scenarios did not improve the accuracy of predictions, as compared to static map-scenarios, chosen for each site. We assume that site-specific and non-linear hydrological processes compromise the generalized assumptions of simulating overall moisture conditions by different FIA.

Can precipitation extremes explain variability in runoff and sediment yield across heterogeneous karst watersheds?

Precipitation extremes are recognized as one of the main factors that influence annual runoff and sediment yield in specific watersheds. However, it is not clear whether precipitation extremes account accurately for the variability in runoff and sediment yield for different karst watersheds, especially in climate-sensitive areas, such as the karst critical zone of southwest China. The objective of this study was to quantify the relative importance of the 11 precipitation extremes variables that explain the total variance in annual runoff and sediment yield with a boosted regression tree (BRT) model for 40 typical karst watersheds in southwest China. Results indicated that the most important precipitation extremes for annual runoff and sediment yield were heavy precipitation amount, consecutive dry days, heavy precipitation days, consecutive wet days, and rainstorm amount. The BRT model accounted for 76% of the variation in runoff, which demonstrated that precipitation extremes were crucial factors for generating runoff. Although precipitation extremes had significant effects on sediment yield, the BRT model only explained 32% of the variability in sediment yield. Hydrogeological conditions and dam construction in these karst watersheds may be responsible for the difference in total variance explained by the BRT model between annual runoff and sediment yield. Because of the inherent nonlinearity present in many hydrological systems, the BRT model provided a robust capability to generate data-driven, objective, insight into complex relationships. We recommend this model for the application of non-stationary and nonlinear hydrological processes.

Advances in Hydrologic Forecasts and Water Resources Management

The impacts of climate change on water resources management as well as the increasing severe natural disasters over the last decades have caught global attention. Reliable and accurate hydrological forecasts are essential for efficient water resources management and the mitigation of natural disasters. While the notorious nonlinear hydrological processes make accurate forecasts a very challenging task, it requires advanced techniques to build accurate forecast models and reliable management systems. One of the newest techniques for modelling complex systems is artificial intelligence (AI). AI can replicate the way humans learn and has the great capability to efficiently extract crucial information from large amounts of data to solve complex problems. The fourteen research papers published in this Special Issue contribute significantly to the uncertainty assessment of operational hydrologic forecasting under changing environmental conditions and the promotion of water resources management by using the latest advanced techniques, such as AI techniques. The fourteen contributions across four major research areas: (1) machine learning approaches to hydrologic forecasting; (2) uncertainty analysis and assessment on hydrological modelling under changing environments; (3) AI techniques for optimizing multi-objective reservoir operation; and (4) adaption strategies of extreme hydrological events for hazard mitigation. The papers published in this issue can not only advance water sciences but can also support policy makers toward more sustainable and effective water resources management.

Correcting Satellite Precipitation Data and Assimilating Satellite-Derived Soil Moisture Data to Generate Ensemble Hydrological Forecasts within the HBV Rainfall-Runoff Model

An implementation of bias correction and data assimilation using the ensemble Kalman filter (EnKF) as a procedure, dynamically coupled with the conceptual rainfall-runoff Hydrologiska Byråns Vattenbalansavdelning (HBV) model, was assessed for the hydrological modeling of seasonal hydrographs. The enhanced HBV model generated ensemble hydrographs and an average stream-flow simulation. The proposed approach was developed to examine the possibility of using data (e.g., precipitation and soil moisture) from the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT) Satellite Application Facility for Support to Operational Hydrology and Water Management (H-SAF), and to explore its usefulness in improving model updating and forecasting. Data from the Sola mountain catchment in southern Poland between 1 January 2008 and 31 July 2014 were used to calibrate the HBV model, while data from 1 August 2014 to 30 April 2015 were used for validation. A bias correction algorithm for a distribution-derived transformation method was developed by exploring generalized exponential (GE) theoretical distributions, along with gamma (GA) and Weibull (WE) distributions for the different data used in this study. When using the ensemble Kalman filter, the stochastically-generated ensemble of the model states generally induced bias in the estimation of non-linear hydrologic processes, thus influencing the accuracy of the Kalman analysis. In order to reduce the bias produced by the assimilation procedure, a post-processing bias correction (BC) procedure was coupled with the ensemble Kalman filter (EnKF), resulting in an ensemble Kalman filter with bias correction (EnKF-BC). The EnKF-BC, dynamically coupled with the HBV model for the assimilation of the satellite soil moisture observations, improved the accuracy of the simulated hydrographs significantly in the summer season, whereas, a positive effect from bias corrected (BC) satellite precipitation, as forcing data, was observed in the winter. Ensemble forecasts generated from the assimilation procedure are shown to be less uncertain. In future studies, the EnKF-BC algorithm proposed in the current study could be applied to a diverse array of practical forecasting problems (e.g., an operational assimilation of snowpack and snow water equivalent in forecasting models).

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.

Decomposition-ANN Methods for Long-Term Discharge Prediction Based on Fisher’s Ordered Clustering with MESA

Precise and reliable long-term streamflow prediction contributes to water resources planning and management. Artificial neural network (ANN) have shown its remarkable ability in forecasting non-linear hydrological processes without involvement of complex, dynamic, hydrological and hydro-climatologic physical process in the water shed. To improve its non-stationary responses, decomposition methods are adopted as pre-processing methods in this study including Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD) and Seasonal-Trend decomposition using Loess (STL). The original time sequence is decomposed to several components, which are then taken as the inputs of the ANN model. EMD and EEMD are data- adaptable methods, and thus the number of Intrinsic Mode Functions (IMFs) might differ for different sequences, leading to the discrepancy of the input number for ANN model in training and predicting. Fisher’s ordered clustering is thus used to classify the IMFs into a determined number of classes based on their frequency spectrum resulting from Maximum Entropy Spectral Analysis (MESA). The proposed methodology is applied on four important hydrological stations on the upper stream of the Yellow River and the Yangtze River in China, respectively, to forecast the streamflow of the next whole year with the historical daily data of the past 6 years. The Nash-Sutcliffe efficiencies of the monthly prediction are higher than 0.85 for all of the four cases, and various indicators indicates that the proposed hybrid method of STL-ANN performs better than other compared methods. The highlights of this study lies in that only historical daily streamflow data is used to derive an accurate long-term prediction by data mining based on decomposition technology and mapping relationships between the decomposed components and the original sequence in the future.

Neural network modeling of hydrological systems: A review of implementation techniques

AbstractThis paper presents a review of procedural steps and implementation techniques used in the development of artificial intelligence models, generally referred to as artificial neural networks (ANNs), within the water resources domain. It focusses on identifying different areas wherein ANNs have found application thereby elucidating its advantages and disadvantages as well as various challenges encountered in its use. Results from this review provide useful insights into how the performance of ANNs can be improved and potential areas of application that are yet to be explored in hydrological modeling.Recommendations for Resource Managers Development of integrated and hybrid artificial intelligent tools is critical to achieving improved forecasts in hydrological modeling studies. Further research into comprehending the internal mechanisms of neural networks is required to obtain a practical meaning of each network component deployed to solve real‐world problems. More robust optimization techniques and tools like differential evolution, particle swarm optimization and deep neural nets, are yet to be fully explored in the water resources analysis, and should be given more attention to enhance neural networks aptitude for modeling complex and nonlinear hydrological processes.

Application of transit data analysis and artificial neural network in the prediction of discharge of Lor River, NW Spain.

Transit data analysis and artificial neural networks (ANNs) have proven to be a useful tool for characterizing and modelling non-linear hydrological processes. In this paper, these methods have been used to characterize and to predict the discharge of Lor River (North Western Spain), 1, 2 and 3 days ahead. Transit data analyses show a coefficient of correlation of 0.53 for a lag between precipitation and discharge of 1 day. On the other hand, temperature and discharge has a negative coefficient of correlation (-0.43) for a delay of 19 days. The ANNs developed provide a good result for the validation period, with R(2) between 0.92 and 0.80. Furthermore, these prediction models have been tested with discharge data from a period 16 years later. Results of this testing period also show a good correlation, with R(2) between 0.91 and 0.64. Overall, results indicate that ANNs are a good tool to predict river discharge with a small number of input variables.

Lake Level Forecasting Using Wavelet-SVR, Wavelet-ANFIS and Wavelet-ARMA Conjunction Models

Accurate predicting of lake level fluctuations is essential and basic in water resources management for water supply purposes. The predicting of lake level is complicated because of it is affected by nonlinear hydrological processes. This paper applies integrated wavelet and auto regressive moving average (ARMA), adaptive neuro fuzzy inference system (ANFIS) and support vector regression (SVR) models for forecasting monthly lake level fluctuations. First, lake level time series is decomposed into low and high frequency components by using discrete wavelet transform. Then, each component is separately predicted by using ARMA, ANFIS and SVR models. Finally, the predicted components are summed to obtain estimated original lake level time series. The performance of the proposed WSVR (Wavelet-SVR), WANFIS (Wavelet-ANFIS) and WARMA (Wavelet-ARMA) models is compared with single ARMA, SVR and ANFIS models. Results show that the integrated models give better precision in forecasting lake levels in the study region when compared to single models. WSVR model is found to be slightly better than the other integrated models.

Subgrid Parameterization of the Soil Moisture Storage Capacity for a Distributed Rainfall-Runoff Model

Spatial variability plays an important role in nonlinear hydrologic processes. Due to the limitation of computational efficiency and data resolution, subgrid variability is usually assumed to be uniform for most grid-based rainfall-runoff models, which leads to the scale-dependence of model performances. In this paper, the scale effect on the Grid-Xinanjiang model was examined. The bias of the estimation of precipitation, runoff, evapotranspiration and soil moisture at the different grid scales, along with the scale-dependence of the effective parameters, highlights the importance of well representing the subgrid variability. This paper presents a subgrid parameterization method to incorporate the subgrid variability of the soil storage capacity, which is a key variable that controls runoff generation and partitioning in the Grid-Xinanjiang model. In light of the similar spatial pattern and physical basis, the soil storage capacity is correlated with the topographic index, whose spatial distribution can more readily be measured. A beta distribution is introduced to represent the spatial distribution of the soil storage capacity within the grid. The results derived from the Yanduhe Basin show that the proposed subgrid parameterization method can effectively correct the watershed soil storage capacity curve. Compared to the original Grid-Xinanjiang model, the model performances are quite consistent at the different grid scales when the subgrid variability is incorporated. This subgrid parameterization method reduces the recalibration necessity when the Digital Elevation Model (DEM) resolution is changed. Moreover, it improves the potential for the application of the distributed model in the ungauged basin.

River Water Prediction Modeling Using Neural Networks, Fuzzy and Wavelet Coupled Model

In this paper, new prediction model introduced by coupling of neural networks model, fuzzy model and wavelet model for the water resources management. Artificial neural network (ANN), fuzzy, wavelet and adaptive neuro-fuzzy inference system (ANFIS) are found to be a sturdy tool to model many non-linear hydrological processes. Wavelet transformation will improve the ability of a prediction model by capturing valuable information on different resolution levels. The target of this research is to compare our model with other famous data-driven models for monthly forecasting of water quality parameter chemical oxygen demand (COD) level monitored at Nizamuddin station, New Delhi, India of river Yamuna based on the past history. The data has been decomposed into wavelet domain constitutive sub series using Daubechies wavelet at level 8 (Db8). Statistical behavior of wavelet domain constitutive series has been studied. The foretelling performance of the wavelet coupled model has been compared with classical neuro fuzzy, artificial neural network and regression models. The result shows that the wavelet coupled model produces considerably higher leads to comparison to neuro fuzzy, neural network, regression models.

Prediction of Ground Water Levels in the Uplands of a Tropical Coastal Riparian Wetland using Artificial Neural Networks

Artificial Neural Networks (ANNs) have been found to be a robust tool to model many non-linear hydrological processes. The present study aims at evaluating the performance of ANN in simulating and predicting ground water levels in the uplands of a tropical coastal riparian wetland. The study involves comparison of two network architectures, Feed Forward Neural Network (FFNN) and Recurrent Neural Network (RNN) trained under five algorithms namely Levenberg Marquardt algorithm, Resilient Back propagation algorithm, BFGS Quasi Newton algorithm, Scaled Conjugate Gradient algorithm, and Fletcher Reeves Conjugate Gradient algorithm by simulating the water levels in a well in the study area. The study is analyzed in two cases-one with four inputs to the networks and two with eight inputs to the networks. The two networks-five algorithms in both the cases are compared to determine the best performing combination that could simulate and predict the process satisfactorily. Ad Hoc (Trial and Error) method is followed in optimizing network structure in all cases. On the whole, it is noticed from the results that the Artificial Neural Networks have simulated and predicted the water levels in the well with fair accuracy. This is evident from low values of Normalized Root Mean Square Error and Relative Root Mean Square Error and high values of Nash-Sutcliffe Efficiency Index and Correlation Coefficient (which are taken as the performance measures to calibrate the networks) calculated after the analysis. On comparison of ground water levels predicted with those at the observation well, FFNN trained with Fletcher Reeves Conjugate Gradient algorithm taken four inputs has outperformed all other combinations.

A novel visual modeling system for time series forecast: application to the domain of hydrology

Accurate and reliable forecasts of key hydrological variables such as stream flow are of importance due to their profound impacts on real world water resources applications. Data-driven methods have proven their applicability to modeling complex and non-linear hydrological processes. This paper presents a novel visual modeling system that has been developed to overcome the problems involved in implementation of data-driven models for hydrological forecasts using conventional programming languages: problems such as the effort and skill needed to program the models, the lack of reusability of existing models, and the lack of shared tools to perform tedious tasks such as preprocessing data. The system provides an integrated visual modeling environment within which users are able to graphically design and verify specific forecasting models for particular problems without writing code. A set of popular data-driven models are offered by the system. Plug-in models created by wrapping existing code are also allowed to run within the system due to the system's open architecture. The system's feasibility and capability is demonstrated through a case study of forecasting 1-day ahead flow in a river basin located in China. The encouraging simulation results show that the system can simplify the process of implementing hydrological forecast.