Using weighted expert judgement and nonlinear data analysis to improve Bayesian belief network models for riverine ecosystem services

Penk, Marcin R.; Bruen, Michael; Feld, Christian K.; Piggott, Jeremy J.; Christie, Michael; Bullock, Craig; Kelly‐Quinn, Mary

doi:10.1016/j.scitotenv.2022.158065

Cited by 6 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BBNs are a probabilistic graphical modelling framework that represents a set of variables and their conditional dependencies using a Directed Acyclic Graph (DAG) i.e., a network that has no cycles. BBNs are a powerful tool for modelling complex systems and have been used to integrate the disparate physicochemical, biotic/ abiotic, and socio-economic aspects (Penk et al, 2022) needed to simulate P in river catchments (Jarvie et al, 2019). BBNs show promise as decision support tools in water resource management (Phan et al, 2019) because they represent causal relationships between variables transparently and graphically, making it straightforward to understand and build BBNs with the participation of experts.…”

Section: Introductionmentioning

confidence: 99%

Bayesian network modelling of phosphorus pollution in agricultural catchments with high-resolution data

Negri,

Mellander,

Schurch

et al. 2024

Preprint

View full text Add to dashboard Cite

A Bayesian Belief Network was developed to simulate phosphorus (P) loss in an Irish agricultural catchment. Septic tanks and farmyards were included to represent all P sources and assess their effect on model performance. Bayesian priors were defined using daily discharge and turbidity, high-resolution soil P data, expert opinion, and literature. Calibration was done against seven years of daily Total Reactive P concentrations. Model performance was assessed using percentage bias, summary statistics, and visually comparing distributions. Bias was within acceptable ranges, the model predicted mean and median P concentrations within the data error, with simulated distributions wider than the observations. Considering the risk of exceeding regulatory standards, predictions showed lower P losses than observations, likely due to simulated distributions being left-skewed. We discuss model advantages and limitations, the benefits of explicitly representing uncertainty, and priorities for data collection to fill knowledge gaps present even in a highly monitored catchment.

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian network modelling of phosphorus pollution in agricultural catchments with high-resolution data

Negri,

Mellander,

Schurch

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Wageningen Environmental Research aanvaardt geen aansprakelijkheid voor eventuele schade voortvloeiend uit het gebruik van de resultaten van dit onderzoek of de toepassing van de adviezen. disciplines of betrokkenen te leren begrijpen en daarmee inzicht te krijgen in de werking van een systeem (Cormont et al, 2022;Ding, 2010;Penk et al, 2022).…”

unclassified

Methodiek formaliseren expertoordeel maatregelpakketten ten gunste van biodiversiteitsdoelstellingen

Cormont,

Berkhof

2023

View full text Add to dashboard Cite

show abstract

Emerging technologies for assessing ecosystem services: A synthesis of opportunities and challenges

Schirpke,

Ghermandi,

Sinclair

et al. 2023

Ecosystem Services

View full text Add to dashboard Cite

Using weighted expert judgement and nonlinear data analysis to improve Bayesian belief network models for riverine ecosystem services

Cited by 6 publications

References 49 publications

Bayesian network modelling of phosphorus pollution in agricultural catchments with high-resolution data

Bayesian network modelling of phosphorus pollution in agricultural catchments with high-resolution data

Methodiek formaliseren expertoordeel maatregelpakketten ten gunste van biodiversiteitsdoelstellingen

Emerging technologies for assessing ecosystem services: A synthesis of opportunities and challenges

Contact Info

Product

Resources

About