Bridging groundwater models and decision support with a Bayesian network: Bayesian Network Model Emulation. Fienen, M. N., Masterson, J. P., Plant, N. G., Gutierrez, B. T., & Thieler, E. R. Water Resources Research, 49(10):6459–6473, October, 2013. ![Bridging groundwater models and decision support with a Bayesian network: Bayesian Network Model Emulation [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Resource managers need to make decisions to plan for future environmental conditions, particularly sea level rise, in the face of substantial uncertainty. Many interacting processes factor in to the decisions they face. Advances in process models and the quantification of uncertainty have made models a valuable tool for this purpose. Long-simulation runtimes and, often, numerical instability make linking process models impractical in many cases. A method for emulating the important connections between model input and forecasts, while propagating uncertainty, has the potential to provide a bridge between complicated numerical process models and the efficiency and stability needed for decision making. We explore this using a Bayesian network (BN) to emulate a groundwater flow model.We expand on previous approaches to validating a BN by calculating forecasting skill using cross validation of a groundwater model of Assateague Island in Virginia and Maryland, USA. This BN emulation was shown to capture the important groundwater-flow characteristics and uncertainty of the groundwater system because of its connection to island morphology and sea level. Forecast power metrics associated with the validation of multiple alternative BN designs guided the selection of an optimal level of BN complexity. Assateague island is an ideal test case for exploring a forecasting tool based on current conditions because the unique hydrogeomorphological variability of the island includes a range of settings indicative of past, current, and future conditions. The resulting BN is a valuable tool for exploring the response of groundwater conditions to sea level rise in decision support.
@article{fienen_bridging_2013,
title = {Bridging groundwater models and decision support with a {Bayesian} network: {Bayesian} {Network} {Model} {Emulation}},
volume = {49},
issn = {00431397},
shorttitle = {Bridging groundwater models and decision support with a {Bayesian} network},
url = {http://doi.wiley.com/10.1002/wrcr.20496},
doi = {10.1002/wrcr.20496},
abstract = {Resource managers need to make decisions to plan for future environmental conditions,
particularly sea level rise, in the face of substantial uncertainty. Many interacting processes
factor in to the decisions they face. Advances in process models and the quantification of
uncertainty have made models a valuable tool for this purpose. Long-simulation runtimes
and, often, numerical instability make linking process models impractical in many cases. A
method for emulating the important connections between model input and forecasts, while
propagating uncertainty, has the potential to provide a bridge between complicated numerical
process models and the efficiency and stability needed for decision making. We explore this
using a Bayesian network (BN) to emulate a groundwater flow model.We expand on
previous approaches to validating a BN by calculating forecasting skill using cross validation
of a groundwater model of Assateague Island in Virginia and Maryland, USA. This BN
emulation was shown to capture the important groundwater-flow characteristics and
uncertainty of the groundwater system because of its connection to island morphology and
sea level. Forecast power metrics associated with the validation of multiple alternative BN
designs guided the selection of an optimal level of BN complexity. Assateague island is an
ideal test case for exploring a forecasting tool based on current conditions because the unique
hydrogeomorphological variability of the island includes a range of settings indicative of
past, current, and future conditions. The resulting BN is a valuable tool for exploring the
response of groundwater conditions to sea level rise in decision support.},
language = {en},
number = {10},
urldate = {2015-04-06},
journal = {Water Resources Research},
author = {Fienen, Michael N. and Masterson, John P. and Plant, Nathaniel G. and Gutierrez, Benjamin T. and Thieler, E. Robert},
month = oct,
year = {2013},
pages = {6459--6473},
}
Downloads: 0
{"_id":"CYzm8wFiNP9jP4KK6","bibbaseid":"fienen-masterson-plant-gutierrez-thieler-bridginggroundwatermodelsanddecisionsupportwithabayesiannetworkbayesiannetworkmodelemulation-2013","downloads":0,"creationDate":"2016-01-10T22:58:31.285Z","title":"Bridging groundwater models and decision support with a Bayesian network: Bayesian Network Model Emulation","author_short":["Fienen, M. N.","Masterson, J. P.","Plant, N. G.","Gutierrez, B. T.","Thieler, E. R."],"year":2013,"bibtype":"article","biburl":"https://api.zotero.org/users/453099/collections/7P2A6E8Z/items?key=GHl4YpTjC2qELHX8M6OLjjNb&format=bibtex&limit=100","bibdata":{"bibtype":"article","type":"article","title":"Bridging groundwater models and decision support with a Bayesian network: Bayesian Network Model Emulation","volume":"49","issn":"00431397","shorttitle":"Bridging groundwater models and decision support with a Bayesian network","url":"http://doi.wiley.com/10.1002/wrcr.20496","doi":"10.1002/wrcr.20496","abstract":"Resource managers need to make decisions to plan for future environmental conditions, particularly sea level rise, in the face of substantial uncertainty. Many interacting processes factor in to the decisions they face. Advances in process models and the quantification of uncertainty have made models a valuable tool for this purpose. Long-simulation runtimes and, often, numerical instability make linking process models impractical in many cases. A method for emulating the important connections between model input and forecasts, while propagating uncertainty, has the potential to provide a bridge between complicated numerical process models and the efficiency and stability needed for decision making. We explore this using a Bayesian network (BN) to emulate a groundwater flow model.We expand on previous approaches to validating a BN by calculating forecasting skill using cross validation of a groundwater model of Assateague Island in Virginia and Maryland, USA. This BN emulation was shown to capture the important groundwater-flow characteristics and uncertainty of the groundwater system because of its connection to island morphology and sea level. Forecast power metrics associated with the validation of multiple alternative BN designs guided the selection of an optimal level of BN complexity. Assateague island is an ideal test case for exploring a forecasting tool based on current conditions because the unique hydrogeomorphological variability of the island includes a range of settings indicative of past, current, and future conditions. The resulting BN is a valuable tool for exploring the response of groundwater conditions to sea level rise in decision support.","language":"en","number":"10","urldate":"2015-04-06","journal":"Water Resources Research","author":[{"propositions":[],"lastnames":["Fienen"],"firstnames":["Michael","N."],"suffixes":[]},{"propositions":[],"lastnames":["Masterson"],"firstnames":["John","P."],"suffixes":[]},{"propositions":[],"lastnames":["Plant"],"firstnames":["Nathaniel","G."],"suffixes":[]},{"propositions":[],"lastnames":["Gutierrez"],"firstnames":["Benjamin","T."],"suffixes":[]},{"propositions":[],"lastnames":["Thieler"],"firstnames":["E.","Robert"],"suffixes":[]}],"month":"October","year":"2013","pages":"6459–6473","bibtex":"@article{fienen_bridging_2013,\n\ttitle = {Bridging groundwater models and decision support with a {Bayesian} network: {Bayesian} {Network} {Model} {Emulation}},\n\tvolume = {49},\n\tissn = {00431397},\n\tshorttitle = {Bridging groundwater models and decision support with a {Bayesian} network},\n\turl = {http://doi.wiley.com/10.1002/wrcr.20496},\n\tdoi = {10.1002/wrcr.20496},\n\tabstract = {Resource managers need to make decisions to plan for future environmental conditions,\nparticularly sea level rise, in the face of substantial uncertainty. Many interacting processes\nfactor in to the decisions they face. Advances in process models and the quantification of\nuncertainty have made models a valuable tool for this purpose. Long-simulation runtimes\nand, often, numerical instability make linking process models impractical in many cases. A\nmethod for emulating the important connections between model input and forecasts, while\npropagating uncertainty, has the potential to provide a bridge between complicated numerical\nprocess models and the efficiency and stability needed for decision making. We explore this\nusing a Bayesian network (BN) to emulate a groundwater flow model.We expand on\nprevious approaches to validating a BN by calculating forecasting skill using cross validation\nof a groundwater model of Assateague Island in Virginia and Maryland, USA. This BN\nemulation was shown to capture the important groundwater-flow characteristics and\nuncertainty of the groundwater system because of its connection to island morphology and\nsea level. Forecast power metrics associated with the validation of multiple alternative BN\ndesigns guided the selection of an optimal level of BN complexity. Assateague island is an\nideal test case for exploring a forecasting tool based on current conditions because the unique\nhydrogeomorphological variability of the island includes a range of settings indicative of\npast, current, and future conditions. The resulting BN is a valuable tool for exploring the\nresponse of groundwater conditions to sea level rise in decision support.},\n\tlanguage = {en},\n\tnumber = {10},\n\turldate = {2015-04-06},\n\tjournal = {Water Resources Research},\n\tauthor = {Fienen, Michael N. and Masterson, John P. and Plant, Nathaniel G. and Gutierrez, Benjamin T. and Thieler, E. Robert},\n\tmonth = oct,\n\tyear = {2013},\n\tpages = {6459--6473},\n}\n\n","author_short":["Fienen, M. N.","Masterson, J. P.","Plant, N. G.","Gutierrez, B. T.","Thieler, E. R."],"key":"fienen_bridging_2013","id":"fienen_bridging_2013","bibbaseid":"fienen-masterson-plant-gutierrez-thieler-bridginggroundwatermodelsanddecisionsupportwithabayesiannetworkbayesiannetworkmodelemulation-2013","role":"author","urls":{"Paper":"http://doi.wiley.com/10.1002/wrcr.20496"},"metadata":{"authorlinks":{}}},"search_terms":["bridging","groundwater","models","decision","support","bayesian","network","bayesian","network","model","emulation","fienen","masterson","plant","gutierrez","thieler"],"keywords":[],"authorIDs":[],"dataSources":["ezn3ueZ5o2F7ZCfmd"]}