Hydro-Ecological Modeling

A special issue of Water (ISSN 2073-4441). This special issue belongs to the section "Hydrology".

Deadline for manuscript submissions: closed (31 January 2015) | Viewed by 92967

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors

Landscape, Water and Biogeochemical Cycles, Institute for Landscape Ecology and Resources Management, Justus Liebig University Gießen, Heinrich-Buff-Ring 26, 35392 Gießen, Germany
Interests: hydro-biogeochemistry; landscape; hydrological modeling; C and N turnover; experimental hydrology
Institute for Landscape Ecology and Resources Management, Justus Liebig University Gießen, Heinrich-Buff-Ring 26, 35392 Gießen, Germany
Interests: coupled hydro-biogeochemical modeling systems; modular hydrological model development; sensor networks; scientific data management

Special Issue Information

Dear Colleagues,

Water is not only an interesting object to be studied on its own, it also is an important component driving almost all ecological processes occurring in our landscapes. Plant growth depends on soil water content, as well is nutrient turnover by microbes. Water shapes the environment by erosion and sedimentation. Species occur or are lost depending on hydrological conditions, and many infectious diseases are water-borne.

Modeling the complex interactions of water and ecosystem processes requires the prediction of hydrological fluxes and stages on the one side and the coupling of the ecosystem process model on the other. While much effort has been given to the development of the hydrological model theory in recent decades, we have just begun to explore the difficulties that occur when coupled model applications are being set up.

This Special Issue calls for contributions that span hydrological and ecological model development and application. We seek contributions that deal with the development of new methods in model coupling and innovative solutions to overcome the increasing complexity of such coupled models. Also, case studies from a variety of ecological topics that are directly driven by hydrology are welcome.

Prof. Dr. Lutz Breuer
Dr. Philipp Kraft
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Water is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hydrological modeling
  • ecological modeling
  • model coupling
  • flexible model toolkits
  • hydro-biogeochemistry
  • climate and land use change
  • erosion
  • biodiversity

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

540 KiB  
Article
Catchment-Scale Modeling of Nitrogen Dynamics in a Temperate Forested Watershed, Oregon. An Interdisciplinary Communication Strategy
by Kellie Vaché, Lutz Breuer, Julia Jones and Phil Sollins
Water 2015, 7(10), 5345-5377; https://doi.org/10.3390/w7105345 - 12 Oct 2015
Cited by 2 | Viewed by 5211
Abstract
We present a systems modeling approach to the development of a place-based ecohydrological model. The conceptual model is calibrated to a variety of existing observations, taken in watershed 10 (WS10) at the HJ Andrews Experimental Forest (HJA) in Oregon, USA, a long term [...] Read more.
We present a systems modeling approach to the development of a place-based ecohydrological model. The conceptual model is calibrated to a variety of existing observations, taken in watershed 10 (WS10) at the HJ Andrews Experimental Forest (HJA) in Oregon, USA, a long term ecological research (LTER) site with a long history of catchment-scale data collection. The modeling framework was designed to help document and evaluate an evolving understanding of catchment processing of water, nitrogen, and carbon that has developed over the many years of on-going research at the site. We use the dynamic model to capture the temporal variation in the N and C budgets and to evaluate how different components of the complex system may control the retention and release of N in this pristine forested landscape. Results indicate that the relative roles of multiple competing controls on N change seasonally, between periods of wet/dry and growth/senescence. The model represents a communication strategy to facilitate dialog between disciplinary experimentalists and modelers, to produce a more complete picture of nitrogen cycling in the region. We view this explicit development of complete, yet conceptually simplified models as a useful and important way to evaluate complex environmental dynamics. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

3308 KiB  
Article
Experimenting with Coupled Hydro-Ecological Models to Explore Measure Plans and Water Quality Goals in a Semi-Enclosed Swedish Bay
by Berit Arheimer, Johanna Nilsson and Göran Lindström
Water 2015, 7(7), 3906-3924; https://doi.org/10.3390/w7073906 - 14 Jul 2015
Cited by 11 | Viewed by 6270
Abstract
Measure plans are currently being developed for the Water Framework Directive (WFD) by European water authorities. In Sweden, such plans include measures for good ecological status in the coastal ecosystem. However, the effect of suggested measures is not yet known. We therefore experimented [...] Read more.
Measure plans are currently being developed for the Water Framework Directive (WFD) by European water authorities. In Sweden, such plans include measures for good ecological status in the coastal ecosystem. However, the effect of suggested measures is not yet known. We therefore experimented with different nutrient reduction measures on land and in the sea, using a model system of two coupled dynamic models for a semi-enclosed bay and its catchment. The science question was whether it is worthwhile to implement measures in the local catchment area to reach local environmental goals, or if the status of the Bay is more governed by the water exchange with the Sea. The results indicate that by combining several measures in the catchment, the nutrient load can be reduced by 15%–20%. To reach the same effect on nutrient concentrations in the Bay, the concentrations of the sea must be reduced by 80%. Hence, in this case, local measures have a stronger impact on coastal water quality. The experiment also show that the present targets for good ecological status set up by the Swedish water authorities may be unrealistic for this Bay. Finally, we discuss when and how to use hydro-ecological models for societal needs. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Graphical abstract

5791 KiB  
Article
Climate or Land Use?—Attribution of Changes in River Flooding in the Sahel Zone
by Valentin Aich, Stefan Liersch, Tobias Vetter, Jafet C. M. Andersson, Eva N. Müller and Fred F. Hattermann
Water 2015, 7(6), 2796-2820; https://doi.org/10.3390/w7062796 - 12 Jun 2015
Cited by 52 | Viewed by 8882
Abstract
This study intends to contribute to the ongoing discussion on whether land use and land cover changes (LULC) or climate trends have the major influence on the observed increase of flood magnitudes in the Sahel. A simulation-based approach is used for attributing the [...] Read more.
This study intends to contribute to the ongoing discussion on whether land use and land cover changes (LULC) or climate trends have the major influence on the observed increase of flood magnitudes in the Sahel. A simulation-based approach is used for attributing the observed trends to the postulated drivers. For this purpose, the ecohydrological model SWIM (Soil and Water Integrated Model) with a new, dynamic LULC module was set up for the Sahelian part of the Niger River until Niamey, including the main tributaries Sirba and Goroul. The model was driven with observed, reanalyzed climate and LULC data for the years 1950–2009. In order to quantify the shares of influence, one simulation was carried out with constant land cover as of 1950, and one including LULC. As quantitative measure, the gradients of the simulated trends were compared to the observed trend. The modeling studies showed that for the Sirba River only the simulation which included LULC was able to reproduce the observed trend. The simulation without LULC showed a positive trend for flood magnitudes, but underestimated the trend significantly. For the Goroul River and the local flood of the Niger River at Niamey, the simulations were only partly able to reproduce the observed trend. In conclusion, the new LULC module enabled some first quantitative insights into the relative influence of LULC and climatic changes. For the Sirba catchment, the results imply that LULC and climatic changes contribute in roughly equal shares to the observed increase in flooding. For the other parts of the subcatchment, the results are less clear but show, that climatic changes and LULC are drivers for the flood increase; however their shares cannot be quantified. Based on these modeling results, we argue for a two-pillar adaptation strategy to reduce current and future flood risk: Flood mitigation for reducing LULC-induced flood increase, and flood adaptation for a general reduction of flood vulnerability. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

761 KiB  
Article
Modeling of Soil Water and Salt Dynamics and Its Effects on Root Water Uptake in Heihe Arid Wetland, Gansu, China
by Huijie Li, Jun Yi, Jianguo Zhang, Ying Zhao, Bingcheng Si, Robert Lee Hill, Lele Cui and Xiaoyu Liu
Water 2015, 7(5), 2382-2401; https://doi.org/10.3390/w7052382 - 21 May 2015
Cited by 64 | Viewed by 7895
Abstract
In the Heihe River basin, China, increased salinity and water shortages present serious threats to the sustainability of arid wetlands. It is critical to understand the interactions between soil water and salts (from saline shallow groundwater and the river) and their effects on [...] Read more.
In the Heihe River basin, China, increased salinity and water shortages present serious threats to the sustainability of arid wetlands. It is critical to understand the interactions between soil water and salts (from saline shallow groundwater and the river) and their effects on plant growth under the influence of shallow groundwater and irrigation. In this study, the Hydrus-1D model was used in an arid wetland of the Middle Heihe River to investigate the effects of the dynamics of soil water, soil salinization, and depth to water table (DWT) as well as groundwater salinity on Chinese tamarisk root water uptake. The modeled soil water and electrical conductivity of soil solution (ECsw) are in good agreement with the observations, as indicated by RMSE values (0.031 and 0.046 cm3·cm−3 for soil water content, 0.037 and 0.035 dS·m−1 for ECsw, during the model calibration and validation periods, respectively). The calibrated model was used in scenario analyses considering different DWTs, salinity levels and the introduction of preseason irrigation. The results showed that (I) Chinese tamarisk root distribution was greatly affected by soil water and salt distribution in the soil profile, with about 73.8% of the roots being distributed in the 20–60 cm layer; (II) root water uptake accounted for 91.0% of the potential maximal value when water stress was considered, and for 41.6% when both water and salt stress were considered; (III) root water uptake was very sensitive to fluctuations of the water table, and was greatly reduced when the DWT was either dropped or raised 60% of the 2012 reference depth; (IV) arid wetland vegetation exhibited a high level of groundwater dependence even though shallow groundwater resulted in increased soil salinization and (V) preseason irrigation could effectively increase root water uptake by leaching salts from the root zone. We concluded that a suitable water table and groundwater salinity coupled with proper irrigation are key factors to sustainable development of arid wetlands. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

3073 KiB  
Article
Model Calibration Criteria for Estimating Ecological Flow Characteristics
by Marc Vis, Rodney Knight, Sandra Pool, William Wolfe and Jan Seibert
Water 2015, 7(5), 2358-2381; https://doi.org/10.3390/w7052358 - 20 May 2015
Cited by 46 | Viewed by 9860
Abstract
Quantification of streamflow characteristics in ungauged catchments remains a challenge. Hydrological modeling is often used to derive flow time series and to calculate streamflow characteristics for subsequent applications that may differ from those envisioned by the modelers. While the estimation of model parameters [...] Read more.
Quantification of streamflow characteristics in ungauged catchments remains a challenge. Hydrological modeling is often used to derive flow time series and to calculate streamflow characteristics for subsequent applications that may differ from those envisioned by the modelers. While the estimation of model parameters for ungauged catchments is a challenging research task in itself, it is important to evaluate whether simulated time series preserve critical aspects of the streamflow hydrograph. To address this question, seven calibration objective functions were evaluated for their ability to preserve ecologically relevant streamflow characteristics of the average annual hydrograph using a runoff model, HBV-light, at 27 catchments in the southeastern United States. Calibration trials were repeated 100 times to reduce parameter uncertainty effects on the results, and 12 ecological flow characteristics were computed for comparison. Our results showed that the most suitable calibration strategy varied according to streamflow characteristic. Combined objective functions generally gave the best results, though a clear underprediction bias was observed. The occurrence of low prediction errors for certain combinations of objective function and flow characteristic suggests that (1) incorporating multiple ecological flow characteristics into a single objective function would increase model accuracy, potentially benefitting decision-making processes; and (2) there may be a need to have different objective functions available to address specific applications of the predicted time series. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Graphical abstract

1291 KiB  
Article
The Stability of Revegetated Ecosystems in Sandy Areas: An Assessment and Prediction Index
by Lei Huang and Zhishan Zhang
Water 2015, 7(5), 1969-1990; https://doi.org/10.3390/w7051969 - 30 Apr 2015
Cited by 6 | Viewed by 7816
Abstract
The stability and sustainability of revegetated ecosystems is a central topic in ecological research. In this study, long-term monitoring and focused research on vegetation, soil and soil moisture from 2006 to 2012 were used to develop a model for evaluating indices of ecosystem [...] Read more.
The stability and sustainability of revegetated ecosystems is a central topic in ecological research. In this study, long-term monitoring and focused research on vegetation, soil and soil moisture from 2006 to 2012 were used to develop a model for evaluating indices of ecosystem stability using the analytical hierarchy process method. The results demonstrated that rainfall (R), vegetation coverage (C), and surface soil moisture (S) were the three most influential factors among the 14 indicators considered in a revegetated desert area in the Tengger Desert, China. A stability index (SI) was defined as SI = VAR (R) × VAR (C)/VAR (S), and a comparative study was conducted to examine the stability index of the natural vegetation community. The SI was divided into three regimes: SI < 0.006 was stable, 0.006 ≤ SI < 0.015 was semi-stable, and 0.015 ≤ SI was unstable. The stable, semi-stable and unstable periods of revegetated ecosystems in our simulations were 191, 17 and 11 years, respectively, within the total modeling period of 219 years. These results indicated that the revegetated desert ecosystem would be stable in most years during the vegetation succession, and this study presents new ideas for future artificial vegetation management in arid desert regions. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Graphical abstract

7741 KiB  
Article
Spatial Quantification of Non-Point Source Pollution in a Meso-Scale Catchment for an Assessment of Buffer Zones Efficiency
by Mikołaj Piniewski, Paweł Marcinkowski, Ignacy Kardel, Marek Giełczewski, Katarzyna Izydorczyk and Wojciech Frątczak
Water 2015, 7(5), 1889-1920; https://doi.org/10.3390/w7051889 - 27 Apr 2015
Cited by 22 | Viewed by 7723
Abstract
The objective of this paper was to spatially quantify diffuse pollution sources and estimate the potential efficiency of applying riparian buffer zones as a conservation practice for mitigating chemical pollutant losses. This study was conducted using a semi-distributed Soil and Water Assessment Tool [...] Read more.
The objective of this paper was to spatially quantify diffuse pollution sources and estimate the potential efficiency of applying riparian buffer zones as a conservation practice for mitigating chemical pollutant losses. This study was conducted using a semi-distributed Soil and Water Assessment Tool (SWAT) model that underwent extensive calibration and validation in the Sulejów Reservoir catchment (SRC), which occupies 4900 km2 in central Poland. The model was calibrated and validated against daily discharges (10 gauges), NO3-N and TP loads (7 gauges). Overall, the model generally performed well during the calibration period but not during the validation period for simulating discharge and loading of NO3-N and TP. Diffuse agricultural sources appeared to be the main contributors to the elevated NO3-N and TP loads in the streams. The existing, default representation of buffer zones in SWAT uses a VFS sub-model that only affects the contaminants present in surface runoff. The results of an extensive monitoring program carried out in 2011–2013 in the SRC suggest that buffer zones are highly efficient for reducing NO3-N and TP concentrations in shallow groundwater. On average, reductions of 56% and 76% were observed, respectively. An improved simulation of buffer zones in SWAT was achieved through empirical upscaling of the measurement results. The mean values of the sub-basin level reductions are 0.16 kg NO3/ha (5.9%) and 0.03 kg TP/ha (19.4%). The buffer zones simulated using this approach contributed 24% for NO3-N and 54% for TP to the total achieved mean reduction at the sub-basin level. This result suggests that additional measures are needed to achieve acceptable water quality status in all water bodies of the SRC, despite the fact that the buffer zones have a high potential for reducing contaminant emissions. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

1560 KiB  
Article
A Structurally Simplified Hybrid Model of Genetic Algorithm and Support Vector Machine for Prediction of Chlorophyll a in Reservoirs
by Jieqiong Su, Xuan Wang, Shouyan Zhao, Bin Chen, Chunhui Li and Zhifeng Yang
Water 2015, 7(4), 1610-1627; https://doi.org/10.3390/w7041610 - 16 Apr 2015
Cited by 19 | Viewed by 6579
Abstract
With decreasing water availability as a result of climate change and human activities, analysis of the influential factors and variation trends of chlorophyll a has become important to prevent reservoir eutrophication and ensure water supply safety. In this paper, a structurally simplified hybrid [...] Read more.
With decreasing water availability as a result of climate change and human activities, analysis of the influential factors and variation trends of chlorophyll a has become important to prevent reservoir eutrophication and ensure water supply safety. In this paper, a structurally simplified hybrid model of the genetic algorithm (GA) and the support vector machine (SVM) was developed for the prediction of monthly concentration of chlorophyll a in the Miyun Reservoir of northern China over the period from 2000 to 2010. Based on the influence factor analysis, the four most relevant influence factors of chlorophyll a (i.e., total phosphorus, total nitrogen, permanganate index, and reservoir storage) were extracted using the method of feature selection with the GA, which simplified the model structure, making it more practical and efficient for environmental management. The results showed that the developed simplified GA-SVM model could solve nonlinear problems of complex system, and was suitable for the simulation and prediction of chlorophyll a with better performance in accuracy and efficiency in the Miyun Reservoir. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

2489 KiB  
Article
Combined Impacts of Medium Term Socio-Economic Changes and Climate Change on Water Resources in a Managed Mediterranean Catchment
by Anastassi Stefanova, Cornelia Hesse and Valentina Krysanova
Water 2015, 7(4), 1538-1567; https://doi.org/10.3390/w7041538 - 10 Apr 2015
Cited by 10 | Viewed by 6811
Abstract
Climate projections agree on a dryer and warmer future for the Mediterranean. Consequently, the region is likely to face serious problems regarding water availability and quality in the future. We investigated potential climate change impacts, alone (for three scenario periods) and in combination [...] Read more.
Climate projections agree on a dryer and warmer future for the Mediterranean. Consequently, the region is likely to face serious problems regarding water availability and quality in the future. We investigated potential climate change impacts, alone (for three scenario periods) and in combination with four socio-economic scenarios (for the near future) on water resources in a Mediterranean catchment, whose economy relies on irrigated agriculture and tourism. For that, the Soil and Water Integrated Model (SWIM) was applied to the drainage area of the Mar Menor coastal lagoon, using a set of 15 climate scenarios and different land use maps and management settings. We assessed the long-term average seasonal and annual changes in generated runoff, groundwater recharge and actual evapotranspiration in the catchment, as well as on water inflow and nutrients input to the lagoon. The projected average annual changes in precipitation are small for the first scenario period, and so are the simulated impacts on all investigated components, on average. The negative trend of potential climate change impacts on water resources (i.e., decrease in all analyzed components) becomes pronounced in the second and third scenario periods. The applied socio-economic scenarios intensify, reduce or even reverse the climate-induced impacts, depending on the assumed land use and management changes. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

1577 KiB  
Article
Development of a Prototype Web-Based Decision Support System for Watershed Management
by Dejian Zhang, Xingwei Chen and Huaxia Yao
Water 2015, 7(2), 780-793; https://doi.org/10.3390/w7020780 - 12 Feb 2015
Cited by 30 | Viewed by 10966
Abstract
Using distributed hydrological models to evaluate the effectiveness of reducing non-point source pollution by applying best management practices (BMPs) is an important support to decision making for watershed management. However, complex interfaces and time-consuming simulations of the models have largely hindered the applications [...] Read more.
Using distributed hydrological models to evaluate the effectiveness of reducing non-point source pollution by applying best management practices (BMPs) is an important support to decision making for watershed management. However, complex interfaces and time-consuming simulations of the models have largely hindered the applications of these models. We designed and developed a prototype web-based decision support system for watershed management (DSS-WMRJ), which is user friendly and supports quasi-real-time decision making. DSS-WMRJ is based on integrating an open-source Web-based Geographical Information Systems (Web GIS) tool (Geoserver), a modeling component (SWAT, Soil and Water Assessment Tool), a cloud computing platform (Hadoop) and other open source components and libraries. In addition, a private cloud is used in an innovative manner to parallelize model simulations, which are time consuming and computationally costly. Then, the prototype DSS-WMRJ was tested with a case study. Successful implementation and testing of the prototype DSS-WMRJ lay a good foundation to develop DSS-WMRJ into a fully-fledged tool for watershed management. DSS-WMRJ can be easily customized for use in other watersheds and is valuable for constructing other environmental decision support systems, because of its performance, flexibility, scalability and economy. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Graphical abstract

2335 KiB  
Article
Comparison of Water Flows in Four European Lagoon Catchments under a Set of Future Climate Scenarios
by Cornelia Hesse, Anastassi Stefanova and Valentina Krysanova
Water 2015, 7(2), 716-746; https://doi.org/10.3390/w7020716 - 12 Feb 2015
Cited by 8 | Viewed by 6789
Abstract
Climate change is supposed to remarkably affect the water resources of coastal lagoons as they are highly vulnerable to changes occurring at their catchment and/or ocean or sea boundaries. Probable impacts of projected climate changes on catchment hydrology and freshwater input were assessed [...] Read more.
Climate change is supposed to remarkably affect the water resources of coastal lagoons as they are highly vulnerable to changes occurring at their catchment and/or ocean or sea boundaries. Probable impacts of projected climate changes on catchment hydrology and freshwater input were assessed using the eco-hydrological model SWIM (Soil and Water Integrated Model) for the drainage areas of four European lagoons: Ria de Aveiro (Portugal), Mar Menor (Spain), Tyligulskyi Liman (Ukraine) and Vistula Lagoon (Poland/Russia) under a set of 15 climate scenarios covering the time period until the year 2100. Climate change signals for all regions show continuously increasing trends in temperature, but various trends in precipitation. Precipitation is projected to decrease in two catchments on the Iberian Peninsula and increase in the Baltic region catchment, and does not show a clear trend in the catchment located near the Black Sea. The average projected changes in freshwater inputs reflect these changes in climate conditions, but often show variability between the scenarios, in future periods, and within the catchments. According to the individual degrees of water management influences in the four drainage basins, the climate sensitivity of river inflows is differently pronounced in each. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

2295 KiB  
Article
Short-Term Forecasting of Water Yield from Forested Catchments after Bushfire: A Case Study from Southeast Australia
by Mana Gharun, Mohammad Azmi and Mark A. Adams
Water 2015, 7(2), 599-614; https://doi.org/10.3390/w7020599 - 09 Feb 2015
Cited by 9 | Viewed by 6552
Abstract
Forested catchments in southeast Australia play an important role in supplying water to major cities. Over the past decades, vegetation cover in this area has been affected by major bushfires that in return influence water yield. This study tests methods for forecasting water [...] Read more.
Forested catchments in southeast Australia play an important role in supplying water to major cities. Over the past decades, vegetation cover in this area has been affected by major bushfires that in return influence water yield. This study tests methods for forecasting water yield after bushfire, in a forested catchment in southeast Australia. Precipitation and remotely sensed Normalized Difference Vegetation Index (NDVI) were selected as the main predictor variables. Cross-correlation results show that water yield with time lag equal to 1 can be used as an additional predictor variable. Input variables and water yield observations were set based on 16-day time series, from 20 January 2003 to 20 January 2012. Four data-driven models namely Non-Linear Multivariate Regression (NLMR), K-Nearest Neighbor (KNN), non-linear Autoregressive with External Input based Artificial Neural Networks (NARX-ANN), and Symbolic Regression (SR) were employed for this study. Results showed that NARX-ANN outperforms other models across all goodness-of-fit criteria. The Nash-Sutcliffe efficiency (NSE) of 0.90 and correlation coefficient of 0.96 at the training-validation stage, as well as NSE of 0.89 and correlation coefficient of 0.95 at the testing stage, are indicative of potentials of this model for capturing ecological dynamics in predicting catchment hydrology, at an operational level. Full article
(This article belongs to the Special Issue Hydro-Ecological Modeling)
Show Figures

Figure 1

Back to TopTop