Loading…

Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network

In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater inf...

Full description

Saved in:
Bibliographic Details
Published in:Water resources research 2021-12, Vol.57 (12), p.n/a
Main Authors: Solvik, Kylen, Bartuszevige, Anne M., Bogaerts, Meghan, Joseph, Maxwell B.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653
cites cdi_FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653
container_end_page n/a
container_issue 12
container_start_page
container_title Water resources research
container_volume 57
creator Solvik, Kylen
Bartuszevige, Anne M.
Bogaerts, Meghan
Joseph, Maxwell B.
description In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short‐term memory (LSTM) neural network to account for these complex processes, we modeled the probability of playa inundation for 71,842 playas in the Great Plains from 1984 to 2018. At the level of individual playas, the model achieved an F1‐score of 0.522 on a withheld test set, displaying the ability to predict complex inundation patterns. When simulating playa inundation over the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate. Plain Language Summary Playas are small, rain‐fed lakes typically found in the Great Plains of the US. Most of the time, they are dry, but when filled they provide important wetland habitat for migrating birds. As the water drains from the playas, they help to recharge the High Plains aquifer, which provides much of the water for agriculture in the region. We used a machine learning model to predict when individual playas are wet and when they are dry using weather, playa size, and information about the land use adjacent to each playa. Our model can accurately predict when playas fill and drain, valuable information for conservation efforts in the region. This research can be used by conservation managers and land‐owners to help protect these critical wetlands. Key Points Playas are infrequently inundated critical wetland habitats for migratory birds and a source of recharge for the High Plains aquifer Modeling playa inundation is challenging but highly valuable for conservation efforts, especially under a changing climate Using a convolutional neural network, we can accurately predict monthly inundation for 71,842 playas across the Great Plains
doi_str_mv 10.1029/2020WR029009
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2614343407</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2614343407</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653</originalsourceid><addsrcrecordid>eNp9kM9Kw0AQhxdRsFZvPkDAq9HZf8nuUYrWYtVSW3oM281GU9Ns3U0oufkIPqNP4pZ68CRz-IaZjxn4IXSO4QoDkdcECCymoQOQB6iHJWNxKlN6iHoAjMaYyvQYnXi_AsCMJ2kPPUycyUvdlPVrNKlUp6JR3da5akpbR3O_G6tobANe3qxrvj-_Zsato0eztq6LnkzrVBXQbK17P0VHhaq8OftlH83vbmeD-3j8PBwNbsaxpoyLmOmcYMyV5EYaJclSEE1ISgoNgoiCK60phSWjIJYYS60FFILIvGAyLBNO--hif3fj7EdrfJOtbOvq8DIjCWY0FKTButxb2lnvnSmyjSvXynUZhmwXV_Y3rqDTvb4tK9P962aL6WBKeAKC_gAtS2tu</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2614343407</pqid></control><display><type>article</type><title>Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network</title><source>Wiley-Blackwell AGU Digital Archive</source><creator>Solvik, Kylen ; Bartuszevige, Anne M. ; Bogaerts, Meghan ; Joseph, Maxwell B.</creator><creatorcontrib>Solvik, Kylen ; Bartuszevige, Anne M. ; Bogaerts, Meghan ; Joseph, Maxwell B.</creatorcontrib><description>In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short‐term memory (LSTM) neural network to account for these complex processes, we modeled the probability of playa inundation for 71,842 playas in the Great Plains from 1984 to 2018. At the level of individual playas, the model achieved an F1‐score of 0.522 on a withheld test set, displaying the ability to predict complex inundation patterns. When simulating playa inundation over the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate. Plain Language Summary Playas are small, rain‐fed lakes typically found in the Great Plains of the US. Most of the time, they are dry, but when filled they provide important wetland habitat for migrating birds. As the water drains from the playas, they help to recharge the High Plains aquifer, which provides much of the water for agriculture in the region. We used a machine learning model to predict when individual playas are wet and when they are dry using weather, playa size, and information about the land use adjacent to each playa. Our model can accurately predict when playas fill and drain, valuable information for conservation efforts in the region. This research can be used by conservation managers and land‐owners to help protect these critical wetlands. Key Points Playas are infrequently inundated critical wetland habitats for migratory birds and a source of recharge for the High Plains aquifer Modeling playa inundation is challenging but highly valuable for conservation efforts, especially under a changing climate Using a convolutional neural network, we can accurately predict monthly inundation for 71,842 playas across the Great Plains</description><identifier>ISSN: 0043-1397</identifier><identifier>EISSN: 1944-7973</identifier><identifier>DOI: 10.1029/2020WR029009</identifier><language>eng</language><publisher>Washington: John Wiley &amp; Sons, Inc</publisher><subject>Agriculture ; Aquatic habitats ; Aquifers ; Birds ; Climate ; Climate change ; Conservation ; Drought ; Drying ; Evaporation ; Groundwater ; Habitats ; High plains ; Hydrologic models ; Hydrology ; Lakes ; Land conservation ; Land use ; Learning algorithms ; Machine learning ; Migratory birds ; Migratory species ; Modelling ; Neural networks ; Playas ; Probability theory ; Rain ; Rainstorms ; Recharge ; Storms ; Water shortages ; Wetlands</subject><ispartof>Water resources research, 2021-12, Vol.57 (12), p.n/a</ispartof><rights>2021. American Geophysical Union. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653</citedby><cites>FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653</cites><orcidid>0000-0001-6537-1791 ; 0000-0002-7745-9990</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1029%2F2020WR029009$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1029%2F2020WR029009$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,11514,27924,27925,46468,46892</link.rule.ids></links><search><creatorcontrib>Solvik, Kylen</creatorcontrib><creatorcontrib>Bartuszevige, Anne M.</creatorcontrib><creatorcontrib>Bogaerts, Meghan</creatorcontrib><creatorcontrib>Joseph, Maxwell B.</creatorcontrib><title>Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network</title><title>Water resources research</title><description>In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short‐term memory (LSTM) neural network to account for these complex processes, we modeled the probability of playa inundation for 71,842 playas in the Great Plains from 1984 to 2018. At the level of individual playas, the model achieved an F1‐score of 0.522 on a withheld test set, displaying the ability to predict complex inundation patterns. When simulating playa inundation over the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate. Plain Language Summary Playas are small, rain‐fed lakes typically found in the Great Plains of the US. Most of the time, they are dry, but when filled they provide important wetland habitat for migrating birds. As the water drains from the playas, they help to recharge the High Plains aquifer, which provides much of the water for agriculture in the region. We used a machine learning model to predict when individual playas are wet and when they are dry using weather, playa size, and information about the land use adjacent to each playa. Our model can accurately predict when playas fill and drain, valuable information for conservation efforts in the region. This research can be used by conservation managers and land‐owners to help protect these critical wetlands. Key Points Playas are infrequently inundated critical wetland habitats for migratory birds and a source of recharge for the High Plains aquifer Modeling playa inundation is challenging but highly valuable for conservation efforts, especially under a changing climate Using a convolutional neural network, we can accurately predict monthly inundation for 71,842 playas across the Great Plains</description><subject>Agriculture</subject><subject>Aquatic habitats</subject><subject>Aquifers</subject><subject>Birds</subject><subject>Climate</subject><subject>Climate change</subject><subject>Conservation</subject><subject>Drought</subject><subject>Drying</subject><subject>Evaporation</subject><subject>Groundwater</subject><subject>Habitats</subject><subject>High plains</subject><subject>Hydrologic models</subject><subject>Hydrology</subject><subject>Lakes</subject><subject>Land conservation</subject><subject>Land use</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Migratory birds</subject><subject>Migratory species</subject><subject>Modelling</subject><subject>Neural networks</subject><subject>Playas</subject><subject>Probability theory</subject><subject>Rain</subject><subject>Rainstorms</subject><subject>Recharge</subject><subject>Storms</subject><subject>Water shortages</subject><subject>Wetlands</subject><issn>0043-1397</issn><issn>1944-7973</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kM9Kw0AQhxdRsFZvPkDAq9HZf8nuUYrWYtVSW3oM281GU9Ns3U0oufkIPqNP4pZ68CRz-IaZjxn4IXSO4QoDkdcECCymoQOQB6iHJWNxKlN6iHoAjMaYyvQYnXi_AsCMJ2kPPUycyUvdlPVrNKlUp6JR3da5akpbR3O_G6tobANe3qxrvj-_Zsato0eztq6LnkzrVBXQbK17P0VHhaq8OftlH83vbmeD-3j8PBwNbsaxpoyLmOmcYMyV5EYaJclSEE1ISgoNgoiCK60phSWjIJYYS60FFILIvGAyLBNO--hif3fj7EdrfJOtbOvq8DIjCWY0FKTButxb2lnvnSmyjSvXynUZhmwXV_Y3rqDTvb4tK9P962aL6WBKeAKC_gAtS2tu</recordid><startdate>202112</startdate><enddate>202112</enddate><creator>Solvik, Kylen</creator><creator>Bartuszevige, Anne M.</creator><creator>Bogaerts, Meghan</creator><creator>Joseph, Maxwell B.</creator><general>John Wiley &amp; Sons, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QH</scope><scope>7QL</scope><scope>7T7</scope><scope>7TG</scope><scope>7U9</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H94</scope><scope>H96</scope><scope>KL.</scope><scope>KR7</scope><scope>L.G</scope><scope>M7N</scope><scope>P64</scope><orcidid>https://orcid.org/0000-0001-6537-1791</orcidid><orcidid>https://orcid.org/0000-0002-7745-9990</orcidid></search><sort><creationdate>202112</creationdate><title>Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network</title><author>Solvik, Kylen ; Bartuszevige, Anne M. ; Bogaerts, Meghan ; Joseph, Maxwell B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Agriculture</topic><topic>Aquatic habitats</topic><topic>Aquifers</topic><topic>Birds</topic><topic>Climate</topic><topic>Climate change</topic><topic>Conservation</topic><topic>Drought</topic><topic>Drying</topic><topic>Evaporation</topic><topic>Groundwater</topic><topic>Habitats</topic><topic>High plains</topic><topic>Hydrologic models</topic><topic>Hydrology</topic><topic>Lakes</topic><topic>Land conservation</topic><topic>Land use</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Migratory birds</topic><topic>Migratory species</topic><topic>Modelling</topic><topic>Neural networks</topic><topic>Playas</topic><topic>Probability theory</topic><topic>Rain</topic><topic>Rainstorms</topic><topic>Recharge</topic><topic>Storms</topic><topic>Water shortages</topic><topic>Wetlands</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Solvik, Kylen</creatorcontrib><creatorcontrib>Bartuszevige, Anne M.</creatorcontrib><creatorcontrib>Bogaerts, Meghan</creatorcontrib><creatorcontrib>Joseph, Maxwell B.</creatorcontrib><collection>CrossRef</collection><collection>Aqualine</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Meteorological &amp; Geoastrophysical Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Water resources research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Solvik, Kylen</au><au>Bartuszevige, Anne M.</au><au>Bogaerts, Meghan</au><au>Joseph, Maxwell B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network</atitle><jtitle>Water resources research</jtitle><date>2021-12</date><risdate>2021</risdate><volume>57</volume><issue>12</issue><epage>n/a</epage><issn>0043-1397</issn><eissn>1944-7973</eissn><abstract>In the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short‐term memory (LSTM) neural network to account for these complex processes, we modeled the probability of playa inundation for 71,842 playas in the Great Plains from 1984 to 2018. At the level of individual playas, the model achieved an F1‐score of 0.522 on a withheld test set, displaying the ability to predict complex inundation patterns. When simulating playa inundation over the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate. Plain Language Summary Playas are small, rain‐fed lakes typically found in the Great Plains of the US. Most of the time, they are dry, but when filled they provide important wetland habitat for migrating birds. As the water drains from the playas, they help to recharge the High Plains aquifer, which provides much of the water for agriculture in the region. We used a machine learning model to predict when individual playas are wet and when they are dry using weather, playa size, and information about the land use adjacent to each playa. Our model can accurately predict when playas fill and drain, valuable information for conservation efforts in the region. This research can be used by conservation managers and land‐owners to help protect these critical wetlands. Key Points Playas are infrequently inundated critical wetland habitats for migratory birds and a source of recharge for the High Plains aquifer Modeling playa inundation is challenging but highly valuable for conservation efforts, especially under a changing climate Using a convolutional neural network, we can accurately predict monthly inundation for 71,842 playas across the Great Plains</abstract><cop>Washington</cop><pub>John Wiley &amp; Sons, Inc</pub><doi>10.1029/2020WR029009</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0001-6537-1791</orcidid><orcidid>https://orcid.org/0000-0002-7745-9990</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0043-1397
ispartof Water resources research, 2021-12, Vol.57 (12), p.n/a
issn 0043-1397
1944-7973
language eng
recordid cdi_proquest_journals_2614343407
source Wiley-Blackwell AGU Digital Archive
subjects Agriculture
Aquatic habitats
Aquifers
Birds
Climate
Climate change
Conservation
Drought
Drying
Evaporation
Groundwater
Habitats
High plains
Hydrologic models
Hydrology
Lakes
Land conservation
Land use
Learning algorithms
Machine learning
Migratory birds
Migratory species
Modelling
Neural networks
Playas
Probability theory
Rain
Rainstorms
Recharge
Storms
Water shortages
Wetlands
title Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T02%3A37%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20Playa%20Inundation%20Using%20a%20Long%20Short%E2%80%90Term%20Memory%20Neural%20Network&rft.jtitle=Water%20resources%20research&rft.au=Solvik,%20Kylen&rft.date=2021-12&rft.volume=57&rft.issue=12&rft.epage=n/a&rft.issn=0043-1397&rft.eissn=1944-7973&rft_id=info:doi/10.1029/2020WR029009&rft_dat=%3Cproquest_cross%3E2614343407%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c3458-4cd2115a95e9ea92b82c2272fc0828f5acc330b4308b119cc80f829df49f5a653%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2614343407&rft_id=info:pmid/&rfr_iscdi=true