{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:07:37Z","timestamp":1755839257406,"version":"3.41.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["IIS-1850546, IIS-2008973, CNS-1951974, OAC-2152085"],"award-info":[{"award-number":["IIS-1850546, IIS-2008973, CNS-1951974, OAC-2152085"]}]},{"DOI":"10.13039\/100000192","name":"National Oceanic and Atmospheric Administration","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000192","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Microsoft AI for Earth Grant"},{"name":"Extreme Science and Engineering Discovery Environment"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2022,4,30]]},"abstract":"<jats:p>\n            Given earth imagery with spectral features on a terrain surface, this paper studies surface segmentation based on both explanatory features and surface topology. The problem is important in many spatial and spatiotemporal applications such as flood extent mapping in hydrology. The problem is uniquely challenging for several reasons: first, the size of earth imagery on a terrain surface is often much larger than the input of popular deep convolutional neural networks; second, there exists topological structure dependency between pixel classes on the surface, and such dependency can follow an unknown and non-linear distribution; third, there are often limited training labels. Existing methods for earth imagery segmentation often divide the imagery into patches and consider the elevation as an additional feature channel. These methods do not fully incorporate the spatial topological structural constraint within and across surface patches and thus often show poor results, especially when training labels are limited. Existing methods on semi-supervised and unsupervised learning for earth imagery often focus on learning representation without explicitly incorporating surface topology. In contrast, we propose a novel framework that explicitly models the topological skeleton of a terrain surface with a contour tree from computational topology, which is guided by the physical constraint (e.g., water flow direction on terrains). Our framework consists of two neural networks: a\n            <jats:bold>convolutional neural network (CNN)<\/jats:bold>\n            to learn spatial contextual features on a 2D image grid, and a\n            <jats:bold>graph neural network (GNN)<\/jats:bold>\n            to learn the statistical distribution of physics-guided spatial topological dependency on the contour tree. The two models are co-trained via variational EM. Evaluations on the real-world flood mapping datasets show that the proposed models outperform baseline methods in classification accuracy, especially when training labels are limited.\n          <\/jats:p>","DOI":"10.1145\/3481043","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T15:07:50Z","timestamp":1641395270000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Earth Imagery Segmentation on Terrain Surface with Limited Training Labels: A Semi-supervised Approach based on Physics-Guided Graph Co-Training"],"prefix":"10.1145","volume":"13","author":[{"given":"Wenchong","family":"He","sequence":"first","affiliation":[{"name":"Department of Computer &amp; Information Science &amp; Engineering, The University of Florida, Gainesville, Florida, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arpan Man","family":"Sainju","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Middle Tennessee State University, Murfreesboro, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3576-6976","authenticated-orcid":false,"given":"Zhe","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer &amp; Information Science &amp; Engineering, The University of Florida, Gainesville, Florida, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Alabama, Birmingham, AL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Auburn University, Auburn, AL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,1,5]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126550"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_38"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/1162264"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-7721(02)00093-7"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995503"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_2_9_2","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017).","journal-title":"arXiv preprint arXiv:1706.05587"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00913"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157527"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13412-016-0372-y"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22786-3_2"},{"key":"e_1_3_2_15_2","first-page":"213","volume-title":"Asian Conference on Computer Vision","author":"Hazirbas Caner","year":"2016","unstructured":"Caner Hazirbas, Lingni Ma, Csaba Domokos, and Daniel Cremers. 2016. Fusenet: Incorporating depth into semantic segmentation via fusion-based CNN architecture. In Asian Conference on Computer Vision. Springer, 213\u2013228."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3019038"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.29"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.10.005042"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454795"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2866809"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975584"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330878"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2020.1823514"},{"key":"e_1_3_2_24_2","article-title":"Spatial Big Data Science","author":"Jiang Zhe","year":"2017","unstructured":"Zhe Jiang and Shashi Shekhar. 2017. Spatial Big Data Science. Schweiz: Springer International Publishing AG.","journal-title":"Schweiz: Springer International Publishing AG"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2930518"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00536"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2016.2528038"},{"key":"e_1_3_2_28_2","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).","journal-title":"arXiv preprint arXiv:1609.02907"},{"key":"e_1_3_2_29_2","first-page":"101371M","volume-title":"Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging","author":"Lang Andrew","year":"2017","unstructured":"Andrew Lang, Aaron Carass, Ava K. Bittner, Howard S. Ying, and Jerry L. Prince. 2017. Improving graph-based OCT segmentation for severe pathology in Retinitis Pigmentosa patients. In Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging, Vol. 10137. International Society for Optics and Photonics, 101371M."},{"key":"e_1_3_2_30_2","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","author":"Li Yaguang","year":"2018","unstructured":"Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202213"},{"key":"e_1_3_2_33_2","article-title":"Image segmentation using deep learning: a survey","author":"Minaee Shervin","year":"2020","unstructured":"Shervin Minaee, Yuri Boykov, Fatih Porikli, Antonio Plaza, Nasser Kehtarnavaz, and Demetri Terzopoulos. 2020. Image segmentation using deep learning: a survey. arXiv preprint arXiv:2001.05566 (2020).","journal-title":"arXiv preprint arXiv:2001.05566"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00331"},{"key":"e_1_3_2_35_2","article-title":"Data and Imagery from NOAA\u2019s National Geodetic Survey","author":"Administration National Oceanic and Atmospheric","unstructured":"National Oceanic and Atmospheric Administration. [n.d.]. Data and Imagery from NOAA\u2019s National Geodetic Survey. https:\/\/www.ngs.noaa.gov.","journal-title":"https:\/\/www.ngs.noaa.gov"},{"key":"e_1_3_2_36_2","article-title":"National Water Model: Improving NOAA\u2019s Water Prediction Services","author":"Administration National Oceanic and Atmospheric","year":"2018","unstructured":"National Oceanic and Atmospheric Administration. 2018. National Water Model: Improving NOAA\u2019s Water Prediction Services. http:\/\/water.noaa.gov\/documents\/wrn-national-water-model.pdf.","journal-title":"http:\/\/water.noaa.gov\/documents\/wrn-national-water-model.pdf"},{"key":"e_1_3_2_37_2","article-title":"LIDAR Based Elevation Data for North Carolina","author":"Libraries NCSU","year":"2018","unstructured":"NCSU Libraries. 2018. LIDAR Based Elevation Data for North Carolina. https:\/\/www.lib.ncsu.edu\/gis\/elevation.","journal-title":"https:\/\/www.lib.ncsu.edu\/gis\/elevation"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/299068.299082"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206567"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1100.001.0001"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276449"},{"key":"e_1_3_2_44_2","article-title":"GMNN: Graph Markov neural networks","author":"Qu Meng","year":"2019","unstructured":"Meng Qu, Yoshua Bengio, and Jian Tang. 2019. GMNN: Graph Markov neural networks. arXiv preprint arXiv:1905.06214 (2019).","journal-title":"arXiv preprint arXiv:1905.06214"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3002887"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5436"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2021.707951"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi4042306"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587440"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_40"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220053"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"e_1_3_2_56_2","article-title":"Deep neural networks for surface segmentation meet conditional random fields","author":"Zhou Leixin","year":"2019","unstructured":"Leixin Zhou, Zisha Zhong, Abhay Shah, Bensheng Qiu, John Buatti, and Xiaodong Wu. 2019. Deep neural networks for surface segmentation meet conditional random fields. arXiv preprint arXiv:1906.04714 (2019).","journal-title":"arXiv preprint arXiv:1906.04714"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3481043","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3481043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:23Z","timestamp":1750191503000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3481043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,5]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4,30]]}},"alternative-id":["10.1145\/3481043"],"URL":"https:\/\/doi.org\/10.1145\/3481043","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2022,1,5]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}