{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:37:57Z","timestamp":1773247077758,"version":"3.50.1"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T00:00:00Z","timestamp":1638230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["1737633"],"award-info":[{"award-number":["1737633"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2021,12,31]]},"abstract":"<jats:p>Spatial variability is a prominent feature of various geographic phenomena such as climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all (OSFA) approach to train single deep neural network models that do not account for spatial variability. Quantification of spatial variability can be challenging due to the influence of many geophysical factors. In preliminary work, we proposed a spatial variability aware neural network (SVANN-I, formerly called<jats:italic>SVANN<\/jats:italic>) approach where weights are a function of location but the neural network architecture is location independent. In this work, we explore a more flexible SVANN-E approach where neural network architecture varies across geographic locations. In addition, we provide a taxonomy of SVANN types and a physics inspired interpretation model. Experiments with aerial imagery based wetland mapping show that SVANN-I outperforms OSFA and SVANN-E performs the best of all.<\/jats:p>","DOI":"10.1145\/3466688","type":"journal-article","created":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T16:04:49Z","timestamp":1638288289000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach"],"prefix":"10.1145","volume":"12","author":[{"given":"Jayant","family":"Gupta","sequence":"first","affiliation":[{"name":"University of Minnesota, Twin Cities, Minneapolis, MN"}]},{"given":"Carl","family":"Molnar","sequence":"additional","affiliation":[{"name":"University of Minnesota, Twin Cities, Minneapolis, MN"}]},{"given":"Yiqun","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD"}]},{"given":"Joe","family":"Knight","sequence":"additional","affiliation":[{"name":"University of Minnesota, Twin Cities, Minneapolis, MN"}]},{"given":"Shashi","family":"Shekhar","sequence":"additional","affiliation":[{"name":"University of Minnesota, Twin Cities, Minneapolis, MN"}]}],"member":"320","published-online":{"date-parts":[[2021,11,30]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"issue":"1","key":"e_1_3_3_3_2","first-page":"278","article-title":"Spatial variability of soil carbon in forested and cultivated sites: Implications for change detection","volume":"32","author":"Conant Richard T.","year":"2003","unstructured":"Richard T. Conant, Gordon R. Smith, and Keith Paustian. 2003. Spatial variability of soil carbon in forested and cultivated sites: Implications for change detection. Journal of Environmental Quality 32, 1 (2003), 278\u2013286.","journal-title":"Journal of Environmental Quality"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.5962\/bhl.title.4108"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X8800800208"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2017160130"},{"key":"e_1_3_3_8_2","volume-title":"National Wetlands Inventory: Surface Waters and Wetlands","author":"Fish U. S.","year":"2020","unstructured":"U. S. Fish and Wildlife Service. 2020. National Wetlands Inventory: Surface Waters and Wetlands. Department of the Interior, Fish and Wildlife Service, Washington, DC. https:\/\/fwsprimary.wim.usgs.gov\/wetlands\/apps\/wetlands-mapper\/."},{"key":"e_1_3_3_9_2","volume-title":"Geographically Weighted Regression: The Analysis of Spatially Varying Relationships","author":"Fotheringham A. Stewart","year":"2003","unstructured":"A. Stewart Fotheringham, Chris Brunsdon, and Martin Charlton. 2003. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. John Wiley & Sons."},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3091696.3091715"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"e_1_3_3_12_2","volume-title":"Proceedings of the Workshop on Deep Learning for Spatiotemporal Data, Applications, and Systems (DeepSpatial\u201920)","author":"Gupta Jayant","year":"2020","unstructured":"Jayant Gupta, Yiqun Xie, and Shashi Shekhar. 2020. Towards spatial variability aware deep neural networks (SVANN): A summary of results. In Proceedings of the Workshop on Deep Learning for Spatiotemporal Data, Applications, and Systems (DeepSpatial\u201920)."},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/labinvest.2014.155"},{"key":"e_1_3_3_14_2","article-title":"TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation","author":"Iglovikov Vladimir","year":"2018","unstructured":"Vladimir Iglovikov and Alexey Shvets. 2018. TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation. arXiv preprint arXiv:1801.05746 (2018).","journal-title":"arXiv preprint arXiv:1801.05746"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3337798"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511778179"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.04.014"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13157-014-0621-3"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022859003006"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_22_2","first-page":"111561J","volume-title":"Earth Resources and Environmental Remote Sensing\/GIS Applications X","author":"Lee S.","year":"2019","unstructured":"S. Lee, S. Park, S. Son, J. Han, S. Kim, and J. Kim. 2019. Land cover segmentation of aerial imagery using SegNet. In Earth Resources and Environmental Remote Sensing\/GIS Applications X, Vol. 11156. International Society for Optics and Photonics, 111561J."},{"key":"e_1_3_3_23_2","volume-title":"Oxford Research Encyclopedia of Criminology and Criminal Justice","author":"Leitner Michael","year":"2018","unstructured":"Michael Leitner, Philip Glasner, and Ourania Kounadi. 2018. Laws of geography. In Oxford Research Encyclopedia of Criminology and Criminal Justice. Oxford University Press, Oxford, UK. DOI:10.1093\/acrefore\/9780190264079.013.325"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/1394399"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018574412308"},{"key":"e_1_3_3_27_2","volume-title":"USDA Plant Hardiness Zone Map","author":"Agriculture U.S. Department of","year":"2012","unstructured":"U.S. Department of Agriculture. 2012. USDA Plant Hardiness Zone Map. USDA. https:\/\/planthardiness.ars.usda.gov\/PHZMWeb\/."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_31_2","unstructured":"Stuart Russell and Peter Norvig. 2002. Artificial Intelligence: A Modern Approach (2nd ed.). Prentice Hall."},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2657778"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2258056.2258058"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2009.03.017"},{"key":"e_1_3_3_35_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_3_36_2","unstructured":"Jan Sitterson Chris Knightes Rajbir Parmar Kurt Wolfe Brian Avant and Muluken Muche. 2018. An Overview of Rainfall-Runoff Model Types . U.S. Environmental Procection Agency Washington DC."},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/0378-1127(90)90221-V"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-24091-8_2"},{"issue":"1","key":"e_1_3_3_40_2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1080\/00031305.1982.10482778","article-title":"Simpson\u2019s paradox in real life","volume":"36","author":"Wagner Clifford H.","year":"1982","unstructured":"Clifford H. Wagner. 1982. Simpson\u2019s paradox in real life. American Statistician 36, 1 (1982), 46\u201348.","journal-title":"American Statistician"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2019.1624761"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3347146.3359066"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3466688","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3466688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:52Z","timestamp":1750195492000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3466688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,30]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,12,31]]}},"alternative-id":["10.1145\/3466688"],"URL":"https:\/\/doi.org\/10.1145\/3466688","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,30]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}