Bayesian belief network models to analyse and predict ecological water quality in rivers

doi:10.1016/j.ecolmodel.2015.05.025

Ecological Modelling

Volume 312, 24 September 2015, Pages 222-238

https://doi.org/10.1016/j.ecolmodel.2015.05.025 Get rights and content

Highlights

•
We developed BBNs for analysing ecological water quality in a tropical river basin.
•
Model evaluation was based on technical criteria and practical simulations.
•
Relevant restoration options were simulated to determine ecological effects.
•
Model sensitivity analysis and simulations revealed the importance of flow velocity.
•
Hydropower dams and water abstraction decrease ecological water quality.

Abstract

Economic growth is often based on the intensification of crop production, energy consumption and urbanization. In many cases, this leads to the degradation of aquatic ecosystems. Modelling water resources and the related identification of key drivers of change are essential to improve and protect water quality in river basins. This study evaluates the potential of Bayesian belief network models to predict the ecological water quality in a typical multifunctional and tropical river basin. Field data, expert knowledge and literature data were used to develop a set of Bayesian belief network models. The developed models were evaluated based on weighted Cohen's Kappa (κ_w), percentage of correctly classified instances (CCI) and spherical payoff. On top, a sensitivity analysis and practical simulation tests of the two most reliable models were performed. Cross-validation based on κ_w (Model 1: 0.44 ± 0.08; Model 2: 0.44 ± 0.11) and CCI (Model 1: 36.3 ± 2.3; Model 2: 41.6 ± 2.3) indicated that the performance was reliable and stable. Model 1 comprised of input variables main land use, elevation, sediment type, chlorophyll, flow velocity, dissolved oxygen, and chemical oxygen demand; whereas Model 2 did not include dissolved oxygen and chemical oxygen demand. Although the predictive performance of Model 2 was slightly higher than that of Model 1, simulation outcomes of Model 1 were more coherent. Additionally, more management options could be evaluated with Model 1. As the model's ability to simulate management outcomes is of utmost importance in model selection, Model 1 is recommended as a tool to support decision-making in river management. Model predictions and sensitivity analysis indicated that flow velocity is the major variable determining ecological water quality and suggested that construction of additional dams and water abstraction within the basin would have an adverse effect on water quality. Although a case study in a single river basin is presented, the modelling approach can be of general use on any other river basin.

Introduction

Increasing human activity in countries often leads to water quality deterioration (Holguin-Gonzalez et al., 2013, Kibena et al., 2014, Mereta et al., 2012, Yillia et al., 2008). Water resources are essential to support biodiversity and to provide social and economic benefits to humans (Bérenger and Verdier-Chouchane, 2007, Hajkowicz, 2006). Monitoring, modelling and forecasting water quality is essential to support management in maintaining a good water quality status while responding to current anthropogenic stressors (Schnoor, 2014).

Various water quality models have been developed in the past. These models range from empirical models quantifying physicochemical water quality (Burchard-Levine et al., 2014, Cuesta Cordoba et al., 2014, Lessels and Bishop, 2013, Xu and Liu, 2013), models integrating hydraulic, physicochemical and ecological water quality (Chan et al., 2013, Clarke et al., 2003, Holguin-Gonzalez et al., 2013), to complex system dynamics models (Ramin et al., 2012, Zhao et al., 2014). However, limited availability of field data frequently restricts the use of these data-driven or complex modelling techniques to support water resource management in countries.

As a result, knowledge-based models, such as, Bayesian belief networks (BBN) are increasingly being used as decision support tool to support river basin management (Adriaenssens et al., 2004, Kragt et al., 2011). Due to their graphical nature, BBNs can be easily understood by non-technical users (Ames et al., 2005, Chen and Pollino, 2012, Uusitalo, 2007). Other advantages of BBNs include the ability to deal with small and incomplete datasets, the ability to include expert knowledge during model training and the ability to take into account uncertainties without increasing calculation time. These aspects and, especially, the capability of combining knowledge-based (expert) and evidence-based (empirical) information make BBNs attractive for environmental modelling (Aguilera et al., 2011, Chen and Pollino, 2012, Landuyt et al., 2013, Pollino et al., 2007, Varis, 1997). Major limitations of BBNs include mandatory discretization of continuous variables and the inability to support feedback loops (Uusitalo, 2007).

Within the Ecuadorian Guayas River basin, various human activities (i.e. hydroelectric dams, agriculture, industrial plants) threaten the quality of the water. Poor management of the basin has resulted in biodiversity loss, unsafe potable water, eutrophication and reduced water availability (Alvarez-Mieles et al., 2013, Andres, 2009). Therefore, water quality models are needed to guide current management. In this study, we developed several BBN models to predict the water quality in the Guayas River basin as a tool to support decision-making. The developed models were evaluated based on their predictive accuracy and their ability to simulate a variety of restoration scenarios. On top, consistency of model predictions was compared. The influence of several environmental variables on the ecological water quality was explored. The paper concludes with some potential restoration opportunities to improve the ecological water quality and discusses potential application of the modelling approach on other river basins.

Section snippets

Study area

The Guayas River basin is located in central-western Ecuador and is the largest watershed in the Guayas province (Fig. 1). It occupies a land surface area of 34,000 km², 13% of the country's territory and hosts approximately 40% of the Ecuadorian population (Andres, 2009, Nguyen et al., 2015). The Guayas River, with a total length of 60 km, discharges in the Pacific Ocean. Annual rainfall and daily mean temperature vary between 300 and 4000 mm and 22 to 27 °C. The dry season falls between May and

Current water quality status

13% of the sampled sites have a good water quality status. 21%, 32%, 19% and 15% of the sampled sites are characterised by moderate, poor, bad, and very bad water quality, respectively (Fig. 3). Table 5 summarises the chemical, physical and hydromorphological water quality characteristics for which continuous data were gathered in the field.

Model performance

The model development process described in Section 2.4 resulted in two graphical layouts (Fig. 4, Fig. 5). Among all developed models (>30), the two

Model development

BBN models offer a lot of advantages. First of all, BBNs are able to deal with missing data, a frequently recurring issue in environmental research, while most classical statistical techniques are not (Gupta and Chen, 2010, Pollino et al., 2007). Also in the present dataset, missing values occurred. For instance, there were 20 missing values for the COD variable. Yet, COD could be included in the model using the other 100 measurements that were available. An additional strength of BBNs, as

Conclusion

Bayesian belief networks (BBN) were developed to model the ecological water quality based on macroinvertebrates in the Guayas River basin. Out of the developed models, two best-performing models were selected. While the predictive performance of the second model was slightly higher than that of the first, simulation outcomes of the first model were more coherent. Also more management options could be evaluated with the first model. Model performance is important to have confidence in the model.

Acknowledgements

This research was performed in the context of the VLIR Ecuador Biodiversity Network project. This project was funded by the Vlaamse Interuniversitaire Raad—Universitaire Ontwikkelingssamenwerking (VLIR-UOS), which supports partnerships between universities and university colleges in Flanders and the South. The authors would also like to thank the assistance of the Department of Chemical and Environmental Sciences (CADS-ESPOL) staff during the sampling campaign in Ecuador, Dr. Christine Vander

References (91)

V. Adriaenssens et al.
Application of Bayesian belief networks for the prediction of macroinvertebrate taxa in rivers
Ann. Limnol.
(2004)
P.A. Aguilera et al.
Bayesian networks in environmental modelling
Environ. Modell. Softw.
(2011)
J. Alba-Tercedor
Macroinvertebrados acuáticos y calidad de las aguas de los ríos
L.F. Alvarez
Metodología para la utilización de los macroinvertebrados acuáticos como indicadores de la calidad del agua
(2006)
G. Alvarez-Mieles et al.
Relationship between aquatic biotic communities and water quality in a tropical river-wetland system (Ecuador)
Environ. Sci. Policy
(2013)
D.P. Ames et al.
Using Bayesian networks to model watershed management decisions: an East Canyon Creek case study
J. Hydroinf.
(2005)
C. Andres
Sedimentation Processes at the Confluence of the Daule and Babahoyo Rivers, Guayaquil, Ecuador. El Palmar island. Manejo Ambiental de Ríos
(2009)
M.E. Arias-Hidalgo
A Decision Framework for Integrated Wetland-river Basin Management in a Tropical and Data Scarce Environment
(2012)
L. Arriaga
The Daule-peripa dam project, urban development of Guayaquil and their impact on shrimp mariculture
AUSRIVAS (Australian River Assessment System)
AUSRIVAS Physical Assessment Protocol Field Data Sheets
(1994)

N.D. Bennett et al.

Characterizing performance of environmental models

Environ. Modell. Softw.

(2013)

V. Bérenger et al.

Multidimensional measures of well-being: standard of living and quality of life across countries

World Dev.

(2007)

A. Burchard-Levine et al.

A hybrid evolutionary data driven model for river water quality early warning

J. Environ. Manage.

(2014)

J. Cain

Planning Improvements in Natural Resources Management: Guidelines for Using Bayesian Networks to Support the Planning and Management of Development Programmes in the Water Sector and Beyond

(2001)

E. Celio et al.

Modelling land use decisions with Bayesian networks: spatially explicit analysis of driving forces on land use change

Environ. Modell. Softw.

(2014)

S.N. Chan et al.

Real-time forecasting of Hong Kong beach water quality by 3D deterministic model

Water Res.

(2013)

S.H. Chen et al.

Good practice in Bayesian network modelling

Environ. Modell. Softw.

(2012)

R.T. Clarke et al.

RIVPACS models for predicting the expected macroinvertebrate fauna and assessing the ecological quality of rivers

Ecol. Modell.

(2003)

J. Cohen

Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit

Psychol. Bull.

(1968)

A.L. Collins et al.

Assessing the likelihood of catchments across England and Wales meeting ‘good ecological status’ due to sediment contributions from agricultural sources

Environ. Sci. Policy

(2008)

A.L. Collins et al.

Storage of fine grained sediment and associated contaminants within the channels of lowland permeable catchments in the UK

G.A. Cuesta Cordoba et al.

Using artificial network models to assess water quality in water distribution networks

Procedia Eng.

(2014)

I. Czerniawska-Kusza

Comparing modified biological monitoring working party score system and several biological indices based on macroinvertebrates for water-quality assessment

Limnologica

(2005)

E.J. Dawson et al.

Speciation of heavy metals on suspended sediment under high flow conditions in the River Aire, West Yorkshire, UK

Hydrol. Processes

(1998)

G. Everaert et al.

Using classification trees to analyze the impact of exotic species on the ecological assessment of polder lakes in Flanders, Belgium

Ecol. Modell.

(2011)

G. Everaert et al.

Comparison of the abiotic preferences of macroinvertebrates in tropical river basins

PLoS ONE

(2014)

E. Fleishman et al.

Modeling and predicting species occurrence using broad-scale environmental variables: an example with butterflies of the Great Basin

Conserv. Biol.

(2001)

E. Fleishman et al.

Validation tests of predictive models of butterfly occurrence based on environmental variables

Conserv. Biol.

(2002)

J.L. Fleiss et al.

The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability

Educ. Psychol. Meas.

(1973)

J. Frankforter et al.

The relative influence of nutrients and habitat on stream metabolism in agricultural streams

Environ. Monit. Assess.

(2010)

W. Gabriels et al.

Multimetric Macroinvertebrate Index Flanders (MMIF) for biological assessment of rivers and lakes in Flanders (Belgium)

Limnologica

(2010)

P.L.M. Goethals

Data driven Development of Predictive Ecological Models for Benthic Macroinvertebrates in River

(2005)

P.L.M. Goethals et al.

Application of artificial neural network predicting macroinvertebrates in freshwaters

Aquat. Ecol.

(2007)

C. Gonzalo et al.

The impact of an industrial effluent on the water quality, submersed macrophytes and benthic macroinvertebrates in a dammed river of Central Spain

Chemosphere

(2013)

A. Guisan et al.

Predictive habitat distribution models in ecology

Ecol. Modell.

(2000)

M.R. Gupta et al.

Theory and use of the EM algorithm

Found. Trends Signal Process.

(2010)

A.T. Haghighi et al.

Development of a new index to assess river regime impacts after dam construction

Global Planet. Change

(2014)

S. Hajkowicz

Multi-attributed environmental index construction

Ecol. Econ.

(2006)

D. Hering et al.

Assessment of European streams with diatoms, macrophytes, macroinvertebrates and fish: a comparative metric-based analysis of organism response to stress

Freshwater Biol.

(2006)

W.L. Hilsenhoff

Rapid field assessment of organic pollution with a family-level biotic index

J. North Am. Benthol. Soc.

(1988)

J.E. Holguin-Gonzalez et al.

Development and application of an integrated ecological modelling framework to analyze the impacts of wastewater discharges on the ecological water quality of river

Environ. Modell. Softw.

(2013)

ISU (Iowa State University) et al.

Iowa Nutrient Reduction Strategy. A Science and Technology-based Framework to Assess and Reduce Nutrients to Iowa Waters and the Gulf of Mexico

(2013)

F.V. Jensen et al.

Bayesian Networks and Decision Graphs

(2007)

D. Kay et al.

Catchment microbial dynamics: the emergence of a research agenda

Prog. Phys. Geogr.

(2007)

J. Kibena et al.

Assessing the relationship between water quality parameters and changes in landuse patterns in the Upper Manyame River, Zimbabwe

Phys. Chem. Earth. A/B/C

(2014)

Cited by (62)

Tributaries protect the water quality of central lake in an artificial spiderweb-structured water system, from the perspective of runoff pollution control
2023, Journal of Cleaner Production
Urban lakes are often disconnected to the surrounding rivers, and they are affected by rainfall runoff pollution. This study focused on an artificial lake-river system in Shanghai featuring a spiderweb-structure, it is expected to detect whether the tributaries in such a system made a protective and buffering effect on the lake under the impact of rainfall runoff. A hydrodynamic model was established using MIKE 21, one of the most widely used software which can conduct two-dimensional modeling of water quality changes in surface water, to simulate the changes of total nitrogen (TN) and total phosphorus (TP), the key indicators causing lake eutrophication, under different rainfall events. The results showed that, under various conditions, storm events almost have no first or final effect on the central lake, TN and TP in the lake were improved by 5%–18% and 1%–12% among monitoring stations. However, Obvious negative effects were displayed in the water quality of radial – circular tributaries, and the first effects in circular tributaries were more serious than those on the radial because their difference in hydrological condition. With the increase of rainfall intensity, the peak value of the pollutant concentration in circular rivers increased 63%–185% as compared with the initial. As to final effects, some circular rivers were significantly impacted, and the pollutant concentration increased by approximately 40% in the seventh day as rainfall started. It was deduced that tributaries played as protective buffer against pollutants in this spiderweb water system, in that pollutants would be degraded in such dense spiderweb-structured river systems before entering the central lake, and rainfall runoff would also accelerate the flow in rivers and lakes. Therefore, the paper hold that, the central lake could not be separated from the radial – circular tributaries, and the officially planned pumps and sluices in the river estuaries would not be recommended. This study would provide technical support for the planning, construction and ecological protection of artificial urban lake-river system in similar areas.
Cross-timescale interaction of nonstationary hydrological responses in subtropical mountainous watersheds
2023, Journal of Hydrology
Hydrological responses possess watershed systematicity and divergent features at various time scales, but how to quantitatively capture the cross-timescale interaction of nonstationary discharge and sediment concentration is unclear, thus limiting insight into hydrological responses to human alterations and stochastic hydroclimatic drivers. The present study analyzed the regimes of inter-annual, intra-annual, and event-scale hydrological responses using 40–60 years data from 15 subtropical watersheds. Bayesian networks of discharge and sediment concentration were constructed, incorporating watershed characteristics, climate effects, and three timescale hydrological indicators, to implement the nonlinear probability prediction. Broadly, annual discharge and sediment concentration followed a decreasing trend, with a key inflection in 2000. Hydrological nonstationarity was diagnosed in terms of magnitude, frequency, and time based on five temporal indicators and transient types of extreme events. In Bayesian networks, the interactions of hydrological indicators were synergistic, with intra-annual hydrological signatures as intermediate nodes between external drivers and annual trends, highly explaining the inconsistent discharge and sediment concentration. The sensitivity of marginal distribution in discharge and sediment concentration to watershed surface alterations was ranked in the terminal position. Nevertheless, the implementation of forest restoration could cause a 90.36% probability of enabling sediment concentration in a decreasing or stationary state under the restrictive scenario. These findings provide refinements in hydrological dynamic causality at different timescales for guiding watershed risk management.
Using weighted expert judgement and nonlinear data analysis to improve Bayesian belief network models for riverine ecosystem services
2022, Science of the Total Environment
Rivers are a key part of the hydrological cycle and a vital conduit of water resources, but are under increasing threat from anthropogenic pressures. Linking pressures with ecosystem services is challenging because the processes interconnecting the physico-chemical, biological and socio-economic elements are usually captured using heterogenous methods. Our objectives were, firstly, to advance an existing proof-of-principle Bayesian belief network (BBN) model for integration of ecosystem services considerations into river management. We causally linked catchment stressors with ecosystem services using weighted evidence from an expert workshop (capturing confidence among expert groups), legislation and published literature. The BBN was calibrated with analyses of national monitoring data (including non-linear relationships and ecologically meaningful breakpoints) and expert judgement. We used a novel expected index of desirability to quantify the model outputs. Secondly, we applied the BBN to three case study catchments in Ireland to demonstrate the implications of changes in stressor levels for ecosystem services in different settings. Four out of the seven significant relationships in data analyses were non-linear, highlighting that non-linearity is common in ecosystems, but rarely considered in environmental modelling. Deficiency of riparian shading was identified as a prevalent and strong influence, which should be addressed to improve a broad range of societal benefits, particularly in the catchments where riparian shading is scarce. Sediment load had a lower influence on river biology in flashy rivers where it has less potential to settle out. Sediment interacted synergistically with organic matter and phosphate where these stressors were active; tackling these stressor pairs simultaneously can yield additional societal benefits compared to the sum of their individual influences, which highlights the value of integrated management. Our BBN model can be parametrised for other Irish catchments whereas elements of our approach, including the expected index of desirability, can be adapted globally.
The role of modelling in resource management within the livelihood-conservation nexus: A socio-ecological systems approach to Sand Forest harvesting, Northern KwaZulu-Natal
2022, Ecological Informatics
Divergences between community livelihoods and conservation efforts often result in changes to the access and use of natural capital in affected areas, negatively affecting the respective livelihoods. New tools and interdisciplinary approaches are more frequently required for solving these conflicts. In this paper, the socio-ecological systems (SES) perspective along with Bayesian Belief Networks (BBNs) have been used to model the interdependencies that exist within the livelihood-conservation nexus to determine if this method can improve synergy between community livelihood requirements and conservation targets in an era of unsustainable decline of natural resources, using the livelihood-conservation nexus of informal Sand Forest harvesting in Northern KwaZulu-Natal as a case study. Results suggest BBNs have great potential for use in socio-ecological and resource management studies concerning the livelihood-conservation nexus. The results of the sensitivity analysis of the BBN showed that employment and income are the greatest socio-economic drivers in terms of Sand Forest harvesting, while preference (i.e. behaviour) for energy sources and building materials has the greatest overall influence on Sand Forest usage. The BBN scenario comparison further demonstrated the influence of preference (i.e. behaviour) on the SES. Finally, the conservation effectiveness assessment using the BBN showed the significant contribution of accessibility and availability of Sand Forest (i.e. conservation) to the system. Information provided by the BBN allowed for suitable areas for conservation to be identified given conservation targets and the utilisation needs of the communities (i.e. greater synergy), through the mapping of two livelihood management approaches (i.e. community conservation and formal conservation). The results of mapping the different management objectives have shown that community conservation is more suitable for moving the system towards synergy and should be considered for a Sand Forest resource management approach to compliment any conservation planning.
Early warning of water quality degradation: A copula-based Bayesian network model for highly efficient water quality risk assessment
2021, Journal of Environmental Management
Citation Excerpt :
BN employs the conditional probability table (CPT) to represent the probability of variables and provides many advantages in risk assessment compared with other methods. The best merit is its graphical attribute, the directed acyclic graph (DAG), which can be constructed by combining expert knowledge and empirical information, making BN attractive for environmental modeling (Forio et al., 2015). Recently, BN has been highly applied in studies of multivariate water quality analysis, such as microbial water quality prediction in Canada (Panidhapu et al., 2020), water quality and health risk assessment (Bertone et al., 2016), and deriving nutrient criteria in Ohio, U.S.A., using the BN model (Qian and Miltner, 2015).
In the context of global climate change and increasingly severe environmental pollution, drinking water quality risk assessments to provide crucial early warnings have become essential routine work. At present, traditional water quality assessment methods are commonly used without considering the correlation among different indicators and the substantial uncertainty from multiple sources, which limit their applications. To address this issue, a copula-based Bayesian network (CBN) method was proposed in this study to concretely evaluate the water quality risk with multiple environmental risk indicators in a large drinking water reservoir in Tianjin city, China. Taking rainfall and water temperature (WT) as external environmental risk indicators and pH, ammonia nitrogen (NH₃–N), total nitrogen (TN), total phosphorus (TP), and permanganate index (COD_Mn) as internal environmental risk indicators, the CBN model was constructed to investigate the interaction between the indicators and water quality state and assess the contingent risk. Our results showed that TN and NH₃–N should be considered key risk indicators. Additionally, we performed forward and backward risk analyses to assess water quality risk during different seasons and determined the distributions of key indicators under different water quality risk grades. From a time perspective, the reservoir's water quality risk is much higher in winter and spring than in other seasons affected by winter snowfall. From a spatial perspective, the water quality risk is much higher at the reservoir's entrance than at other locations affected by water diversion. Furthermore, we found that the probability of water quality risk events may be relatively high when the TN concentration is 3.6 mg/L to 6.4 mg/L at the reservoir's entrance. The results reveal that the CBN method could be an invaluable decision-support tool for reservoir managers and scientists, which could provide an early warning of water quality degradation by only inputting monitoring data.
Understanding trade-offs and synergies of ecosystem services to support the decision-making in the Beijing–Tianjin–Hebei region
2021, Land Use Policy
Understanding ecosystem service trade-offs and synergies is the foundation to achieve the efficient management of the ecosystem and improve human well-being. However, the current research involving the driving mechanism of ecosystem service relationship formation is still limited. In this paper, a semi-quantitative model named Bayesian belief networks is introduced to simulate ecological processes, which links the potential influencing factors with the ecosystem service supply. The purpose of this paper is to help understand the ecosystem service relationship and provide management decision-making reference. Taking the Beijing–Tianjin–Hebei region as a study area, four ecosystem services (habitat quality, carbon storage, water yield, and soil retention services) were quantified and mapped in 2015. Based on a created Bayesian belief network simulating the ecosystem service supply, the sensitivity analysis was used to identify the key factors affecting the ecosystem service supply. Besides, the relationship between ecosystem services was identified and the driving mechanism was analyzed through the Bayesian probabilistic inference. The main conclusions demonstrate the following. (1) The spatial heterogeneity of the ecosystem service supply in the Beijing–Tianjin–Hebei region is relatively strong. (2) The key factors affecting ecosystem services are the land use type, vegetation coverage, precipitation, slope, evapotranspiration, and population density. (3) Habitat quality, carbon storage, and soil retention services synergize one another, and there are trade-offs between water yield service and habitat quality, carbon storage, and soil retention services, respectively. (4) Among the land use type, vegetation coverage, slope, and population density, the land use type has the most important impact on ecosystem service trade-offs. As a practice of combining Bayesian belief networks and ecosystem services, this study can contribute to a research method of ecosystem service relationships and references for the management decision-making on maximizing the overall benefits of ecosystem services.

View all citing articles on Scopus

View full text

Bayesian belief network models to analyse and predict ecological water quality in rivers

Highlights

Abstract

Introduction

Section snippets

Study area

Current water quality status

Model performance

Model development

Conclusion

Acknowledgements

Application of Bayesian belief networks for the prediction of macroinvertebrate taxa in rivers

Ann. Limnol.

Bayesian networks in environmental modelling

Environ. Modell. Softw.

Macroinvertebrados acuáticos y calidad de las aguas de los ríos

Metodología para la utilización de los macroinvertebrados acuáticos como indicadores de la calidad del agua

Relationship between aquatic biotic communities and water quality in a tropical river-wetland system (Ecuador)

Environ. Sci. Policy

Using Bayesian networks to model watershed management decisions: an East Canyon Creek case study

J. Hydroinf.

Sedimentation Processes at the Confluence of the Daule and Babahoyo Rivers, Guayaquil, Ecuador. El Palmar island. Manejo Ambiental de Ríos

A Decision Framework for Integrated Wetland-river Basin Management in a Tropical and Data Scarce Environment

The Daule-peripa dam project, urban development of Guayaquil and their impact on shrimp mariculture

AUSRIVAS Physical Assessment Protocol Field Data Sheets

Characterizing performance of environmental models

Environ. Modell. Softw.

Multidimensional measures of well-being: standard of living and quality of life across countries

World Dev.

A hybrid evolutionary data driven model for river water quality early warning

J. Environ. Manage.

Planning Improvements in Natural Resources Management: Guidelines for Using Bayesian Networks to Support the Planning and Management of Development Programmes in the Water Sector and Beyond

Modelling land use decisions with Bayesian networks: spatially explicit analysis of driving forces on land use change

Environ. Modell. Softw.

Real-time forecasting of Hong Kong beach water quality by 3D deterministic model

Water Res.

Good practice in Bayesian network modelling

Environ. Modell. Softw.

RIVPACS models for predicting the expected macroinvertebrate fauna and assessing the ecological quality of rivers

Ecol. Modell.

Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit

Psychol. Bull.

Assessing the likelihood of catchments across England and Wales meeting ‘good ecological status’ due to sediment contributions from agricultural sources

Environ. Sci. Policy

Storage of fine grained sediment and associated contaminants within the channels of lowland permeable catchments in the UK

Using artificial network models to assess water quality in water distribution networks

Procedia Eng.

Comparing modified biological monitoring working party score system and several biological indices based on macroinvertebrates for water-quality assessment

Limnologica

Speciation of heavy metals on suspended sediment under high flow conditions in the River Aire, West Yorkshire, UK

Hydrol. Processes

Using classification trees to analyze the impact of exotic species on the ecological assessment of polder lakes in Flanders, Belgium

Ecol. Modell.

Comparison of the abiotic preferences of macroinvertebrates in tropical river basins

PLoS ONE

Modeling and predicting species occurrence using broad-scale environmental variables: an example with butterflies of the Great Basin

Conserv. Biol.

Validation tests of predictive models of butterfly occurrence based on environmental variables

Conserv. Biol.

The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability

Educ. Psychol. Meas.

The relative influence of nutrients and habitat on stream metabolism in agricultural streams

Environ. Monit. Assess.

Multimetric Macroinvertebrate Index Flanders (MMIF) for biological assessment of rivers and lakes in Flanders (Belgium)

Limnologica

Data driven Development of Predictive Ecological Models for Benthic Macroinvertebrates in River

Application of artificial neural network predicting macroinvertebrates in freshwaters

Aquat. Ecol.

The impact of an industrial effluent on the water quality, submersed macrophytes and benthic macroinvertebrates in a dammed river of Central Spain

Chemosphere

Predictive habitat distribution models in ecology

Ecol. Modell.

Theory and use of the EM algorithm

Found. Trends Signal Process.

Development of a new index to assess river regime impacts after dam construction

Global Planet. Change

Multi-attributed environmental index construction

Ecol. Econ.

Assessment of European streams with diatoms, macrophytes, macroinvertebrates and fish: a comparative metric-based analysis of organism response to stress

Freshwater Biol.