Credit: antishock – stock.adobe.com
“Not difficult, just different,” is how one author in the latest IEAM podcast describes Bayesian Network models (BNs) to researchers that are unfamiliar with—and often intimidated by—them. A recent special series aims to dispel the esoteric aura that surrounds this approach by showing how BNs have improved ecological risk assessments in the past 20 years, with the goal of encouraging more practitioners to employ BNs and continue evolving the practices of ERA and environmental management. The Guest Editors of the series are Jannicke Moe, John Carriger, and Miriam Glendell.
Guest Editor Jannicke Moe talks to us about advantages of BNs, recent developments, and highlights the research presented in the series—10 articles demonstrating the application of BNs to various environmental assessment and management scenarios involving climate change, ecological and socioeconomic endpoints, machine learning, diagnostic inference, and model evaluation.
Access the series “Applications of Bayesian Networks for Environmental Risk Assessment and Management” in the January 2021 issue of IEAM.
About the Guest
Jannicke Moe is a Senior Research Scientist at the Norwegian Institute for Water Research (NIVA), section for Ecotoxicology and Risk Assessment. She holds a PhD in biology from the University of Oslo (2001) and had a postdoctoral stay at the National Center for Ecological Analysis and Synthesis (University of California, Santa Barbara). Since her employment at NIVA in 2004 she has worked in a series of EU research projects aiming at scientific support for ecosystem-based management under the European Water Framework Directive, with responsibility for large-scale biological data management and analysis. She is a member of the European Environment Agency’s Topic Center for Inland, Coastal and Marine Waters since 2007, where she oversees the reporting and assessment of biological data from 26 countries. Her current research focuses on statistical and mechanistic modelling methods to support environmental risk assessment, including Bayesian network modelling. She is currently involved in the European Innovative Training Network ECORISK2050, leading the work package Risk & Mitigation. Since 2021 she serves as Senior Editor of IEAM, for the section Health & Ecological Risk Assessment.
Articles Referenced in this Podcast
Moe, S.J., Carriger, J.F. and Glendell, M. (2021), Increased Use of Bayesian Network Models Has Improved Environmental Risk Assessments. Integr Environ Assess Manag, 17: 53-61. https://doi.org/10.1002/ieam.4369
Kaikkonen, L., Parviainen, T., Rahikainen, M., Uusitalo, L. and Lehikoinen, A. (2021), Bayesian Networks in Environmental Risk Assessment: A Review. Integr Environ Assess Manag, 17: 62-78. https://doi.org/10.1002/ieam.4332
Landis, W.G. (2021), The Origin, Development, Application, Lessons Learned, and Future Regarding the Bayesian Network Relative Risk Model for Ecological Risk Assessment. Integr Environ Assess Manag, 17: 79-94. https://doi.org/10.1002/ieam.4351
Mitchell, C.J., Lawrence, E., Chu, V.R., Harris, M.J., Landis, W.G., von Stackelberg, K.E. and Stark, J.D. (2021), Integrating Metapopulation Dynamics into a Bayesian Network Relative Risk Model: Assessing Risk of Pesticides to Chinook Salmon (Oncorhynchus tshawytscha) in an Ecological Context. Integr Environ Assess Manag, 17: 95-109. https://doi.org/10.1002/ieam.4357
Wade, M., O’Brien, G.C., Wepener, V. and Jewitt, G. (2021), Risk Assessment of Water Quantity and Quality Stressors to Balance the Use and Protection of Vulnerable Water Resources. Integr Environ Assess Manag, 17: 110-130. https://doi.org/10.1002/ieam.4356
Cains, M.G. and Henshel, D. (2021), Parameterization Framework and Quantification Approach for Integrated Risk and Resilience Assessments. Integr Environ Assess Manag, 17: 131-146. https://doi.org/10.1002/ieam.4331
Moe, S.J., Wolf, R., Xie, L., Landis, W.G., Kotamäki, N. and Tollefsen, K.E. (2021), Quantification of an Adverse Outcome Pathway Network by Bayesian Regression and Bayesian Network Modeling. Integr Environ Assess Manag, 17: 147-164. https://doi.org/10.1002/ieam.4348
Carriger, J.F., Yee, S.H. and Fisher, W.S. (2021), Assessing Coral Reef Condition Indicators for Local and Global Stressors Using Bayesian Networks. Integr Environ Assess Manag, 17: 165-187. https://doi.org/10.1002/ieam.4368
Piffady, J., Carluer, N., Gouy, V., le Henaff, G., Tormos, T., Bougon, N., Adoir, E. and Mellac, K. (2021), ARPEGES: A Bayesian Belief Network to Assess the Risk of Pesticide Contamination for the River Network of France. Integr Environ Assess Manag, 17: 188-201. https://doi.org/10.1002/ieam.4343
Rachid, G., Alameddine, I., Najm, M.A., Qian, S. and El-Fadel, M. (2021), Dynamic Bayesian Networks to Assess Anthropogenic and Climatic Drivers of Saltwater Intrusion: A Decision Support Tool Toward Improved Management. Integr Environ Assess Manag, 17: 202-220. https://doi.org/10.1002/ieam.4355
Sahlin, U., Helle, I. and Perepolkin, D. (2021), “This Is What We Don’t Know”: Treating Epistemic Uncertainty in Bayesian Networks for Risk Assessment. Integr Environ Assess Manag, 17: 221-232. https://doi.org/10.1002/ieam.4367