Regression using hybrid Bayesian networks: Modelling landscape–socioeconomy relationships

Ropero, Rosa F.; Aguilera, Pedro A.; Fernández, Antonio; Rumí, Rafael

doi:10.1016/j.envsoft.2014.02.016

Cited by 25 publications

(19 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 ii)). Natural and social subsystems are connected through causal interactions, and land use is clearly influenced by the social subsystem (Lambin et al, 2001;Foley et al, 2005;Schmitz et al, 2005;Rudel et al, 2009;Ropero et al, 2014). Furthermore, the relationship between water flows and landscape are widely described in the literature (Scanlon et al, 2005;Maes et al, 2009;Toda et al, 2010).…”

Section: Model Learning Evidence Propagation and Analysis Of Resultsmentioning

confidence: 97%

See 1 more Smart Citation

Modelling uncertainty in social–natural interactions

Ropero

Rumí

Aguilera

2016

Environmental Modelling & Software

Self Cite

View full text Add to dashboard Cite

Section: Model Learning Evidence Propagation and Analysis Of Resultsmentioning

confidence: 97%

“…In this way, hybrid BNs have been shown to provide an excellent tool for studying interactions between social and natural subsystems from an uncertainty perspective (Ropero et al, 2014).…”

Section: Model Descriptionmentioning

confidence: 99%

Modelling uncertainty in social–natural interactions

Ropero

Rumí

Aguilera

2016

Environmental Modelling & Software

Self Cite

View full text Add to dashboard Cite

“…In the future Hybrid or nonparametric BBNs, where discretisation is not needed, may avoid the need for this approach in BBN construction (e.g. Morales‐Napoles et al ., ; Ropero et al ., ).…”

Section: Discussionmentioning

confidence: 97%

How good are Bayesian belief networks for environmental management? A test with data from an agricultural river catchment

Death

Stubbington

et al. 2015

Freshwater Biology

View full text Add to dashboard Cite

SUMMARY1. The ecological health of rivers worldwide continues to decline despite increasing effort and investment in river science and management. Bayesian belief networks (BBNs) are increasingly being used as a mechanism for decision-making in river management because they provide a simple visual framework to explore different management scenarios for the multiple stressors that impact rivers. However, most applications of BBN modelling to resource management use expert knowledge and/or limited real data, and fail to accurately assess the ability of the model to make predictions.2. We developed a BBN to model ecological condition in a New Zealand river using field/GIS data (from multiple rivers), rather than expert opinion, and assessed its predictive ability on an independent dataset. The developed BBN performed moderately better than a number of other modelling techniques (e.g., artificial neural networks, classification trees, random forest, logistic regression), although model construction was more time-consuming. Thus the predictive ability of BBNs is (in this case at least) on a par with other modelling methods but the approach is distinctly better for its ability to visually present the data linkages, issues and potential outcomes of management options in real time. We have demonstrated this for a BBN of ecological condition in a New Zealand river, shown that model fit is better than that for other modelling techniques, and that improving habitat would be equally effective to reducing nutrients to improve ecological condition.

show abstract

“…The probabilistic inference is implemented based on Bayes's paradigm. As a 20 decision support system tool, a BN consists of two main components (Ropero et al, 2014): (1) a directed acyclic diagram (DAG), which is presented as a qualitative component and illustrated by directed arrows linking a set of variables or nodes with cause-effect relations; and (2) conditional probability tables (CPTs), regarded as a quantitative component. A variable or node comprises a finite set of exclusive states that describe the "values" of variable discretization.…”

Section: Bns As Decision Support System Tools For Iwrmmentioning

confidence: 99%

Development of a participatory Bayesian network model for integrating ecosystem services into catchment-scale water resources management

Xue

GUI

Lei

et al. 2016

Preprint

View full text Add to dashboard Cite

Abstract. This paper proposes an ecosystem services-based integrated water resource management (IWRM) framework within which a participatory Bayesian network (BN) model that 15assists with the integration of IWRM is developed. The framework is divided three steps: (1) identifying water-related services of ecosystems; (2) analysis of the tradeoffs and synergy among users of water; and (3) ecosystem services-based IWRM implementation using the BN model. We present the development, evaluation and application of a participatory BN model with the involvement of four participant groups (stakeholders, water manager, water management experts, 20 and research team) in Qira oasis area, Northwest China. As a typical catchment-scale region, the Qira oasis area is facing severe water competition between the demands of human activities and natural ecosystems. We demonstrate that the BN model developed provides effective integration of ecosystem services into a quantitative IWMR framework via public negotiation and feedback. The network results, sensitivity evaluation, and management scenarios are broadly accepted by the 25 participant groups. The intervention scenarios from the model conclude that any water management measure remains unable to sustain the ecosystem health in water-related ecosystem services. Greater cooperation among the stakeholders is highly necessary for dealing with such water conflicts. In particular, a proportion of the agricultural water saved through improving water-use efficiency should be transferred to natural ecosystems via water trade. The BN model 30 developed is appropriate for areas throughout the world in which there is intense competition for water between human activities and ecosystems -particularly in arid regions.

show abstract

Regression using hybrid Bayesian networks: Modelling landscape–socioeconomy relationships

Cited by 25 publications

References 49 publications

Modelling uncertainty in social–natural interactions

Modelling uncertainty in social–natural interactions

How good are Bayesian belief networks for environmental management? A test with data from an agricultural river catchment

Development of a participatory Bayesian network model for integrating ecosystem services into catchment-scale water resources management

Contact Info

Product

Resources

About