Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-12

AUTHORS

Robert F. Chew, Safaa Amer, Kasey Jones, Jennifer Unangst, James Cajka, Justine Allpress, Mark Bruhn

ABSTRACT

BACKGROUND: Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country's existing administrative boundaries into area units that vary in size from 50 m × 50 m to 150 m × 150 m. To avoid sending interviewers to unoccupied areas, researchers manually classify grid cells as "residential" or "nonresidential" through visual inspection of aerial images. "Nonresidential" units are then excluded from sampling and data collection. This process of manually classifying sampling units has drawbacks since it is labor intensive, prone to human error, and creates the need for simplifying assumptions during calculation of design-based sampling weights. In this paper, we discuss the development of a deep learning classification model to predict whether aerial images are residential or nonresidential, thus reducing manual labor and eliminating the need for simplifying assumptions. RESULTS: On our test sets, the model performs comparable to a human-level baseline in both Nigeria (94.5% accuracy) and Guatemala (96.4% accuracy), and outperforms baseline machine learning models trained on crowdsourced or remote-sensed geospatial features. Additionally, our findings suggest that this approach can work well in new areas with relatively modest amounts of training data. CONCLUSIONS: Gridded population sampling methods like geosampling are becoming increasingly popular in countries with outdated or inaccurate census data because of their timeliness, flexibility, and cost. Using deep learning models directly on satellite images, we provide a novel method for sample frame construction that identifies residential gridded aerial units. In cases where manual classification of satellite images is used to (1) correct for errors in gridded population data sets or (2) classify grids where population estimates are unavailable, this methodology can help reduce annotation burden with comparable quality to human analysts. More... »

PAGES

12

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s12942-018-0132-1

DOI

http://dx.doi.org/10.1186/s12942-018-0132-1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1103904810

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/29743081


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Data Collection", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Demography", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Developing Countries", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Guatemala", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Humans", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Neural Networks (Computer)", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Nigeria", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Residence Characteristics", 
        "type": "DefinedTerm"
      }, 
      {
        "inDefinedTermSet": "https://www.nlm.nih.gov/mesh/", 
        "name": "Satellite Imagery", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Center for Data Science, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chew", 
        "givenName": "Robert F.", 
        "id": "sg:person.013501664057.86", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013501664057.86"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Division for Statistical and Data Sciences, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Amer", 
        "givenName": "Safaa", 
        "id": "sg:person.015114276136.32", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015114276136.32"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Center for Data Science, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jones", 
        "givenName": "Kasey", 
        "id": "sg:person.015711656536.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015711656536.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Division for Statistical and Data Sciences, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Unangst", 
        "givenName": "Jennifer", 
        "id": "sg:person.016507237136.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016507237136.40"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Geospatial Science and Technology Program, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Cajka", 
        "givenName": "James", 
        "id": "sg:person.0606166667.23", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606166667.23"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Geospatial Science and Technology Program, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Allpress", 
        "givenName": "Justine", 
        "id": "sg:person.01275003217.35", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01275003217.35"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "RTI International", 
          "id": "https://www.grid.ac/institutes/grid.62562.35", 
          "name": [
            "Geospatial Science and Technology Program, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bruhn", 
        "givenName": "Mark", 
        "id": "sg:person.01152070215.31", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01152070215.31"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1186/s12936-015-0831-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001546313", 
          "https://doi.org/10.1186/s12936-015-0831-z"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/rs8040329", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002913079"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1996.8.7.1341", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003549317"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.rse.2005.02.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004046220"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/219717.219748", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005662680"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.isprsjprs.2013.09.014", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006381529"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-015-0816-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009767488", 
          "https://doi.org/10.1007/s11263-015-0816-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature14539", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010020120", 
          "https://doi.org/10.1038/nature14539"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.aaf7894", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010648224"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1992.4.4.605", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013658470"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/2150704x.2016.1235299", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017631063"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10462-009-9124-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017758686", 
          "https://doi.org/10.1007/s10462-009-9124-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10462-009-9124-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017758686", 
          "https://doi.org/10.1007/s10462-009-9124-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10462-009-9124-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017758686", 
          "https://doi.org/10.1007/s10462-009-9124-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11524-016-0046-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019537003", 
          "https://doi.org/10.1007/s11524-016-0046-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11524-016-0046-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019537003", 
          "https://doi.org/10.1007/s11524-016-0046-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.isprsjprs.2009.06.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020267301"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1001/archpsyc.1985.01790300093012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021068313"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0034-4257(80)90021-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021981194"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0034-4257(80)90021-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021981194"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1476-072x-9-45", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022029214", 
          "https://doi.org/10.1186/1476-072x-9-45"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.4081/gh.2016.410", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023097789"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1869790.1869829", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025470079"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/1467-985x.00090", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026593228"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/1467-985x.00090", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026593228"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2820783.2820816", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028229296"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1471-2458-12-959", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030338225", 
          "https://doi.org/10.1186/1471-2458-12-959"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/1476-072x-11-12", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035871335", 
          "https://doi.org/10.1186/1476-072x-11-12"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pmed.1001533", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036230054"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/01431161.2011.552923", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037898439"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-77058-9_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039241015", 
          "https://doi.org/10.1007/978-3-540-77058-9_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/s16121990", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039334688"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/001316446002000104", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039619716"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/001316446002000104", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039619716"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pmed.1001007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041093395"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tkde.2009.191", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041355599"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2478/jos-2014-0013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043556035"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/ciun.1993.1024", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044516065"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.rse.2014.02.015", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044652759"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0033-2909.101.1.140", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047130153"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/rs71114680", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052528622"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/0049124114521150", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053784999"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1177/0049124114521150", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053784999"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/01621459.1958.10501465", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058299431"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1086/266043", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058576656"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/jssam/smw012", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059833580"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/poq/nfq066", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059979102"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/lgrs.2015.2499239", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061360807"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/lgrs.2015.2513443", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061360852"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mcas.2006.1688199", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061389638"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tmi.2016.2528162", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061696701"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1126/science.227.4685.369", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062529705"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/1247046", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069413181"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/2529310", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1069974986"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/3149339", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1070211959"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.2307/3150117", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1070212657"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jproc.2017.2675998", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084605162"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tgrs.2017.2685945", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085257848"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/3065386", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085642448"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/3065386", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085642448"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12942-017-0098-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090773364", 
          "https://doi.org/10.1186/s12942-017-0098-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12942-017-0098-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090773364", 
          "https://doi.org/10.1186/s12942-017-0098-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pone.0180698", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091151401"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/rs9080848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091217523"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.90", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093359587"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.308", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093497718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2014.6854661", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094421042"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icra.2017.7989417", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094478815"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2013.6638947", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095157363"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095689025"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/igarss.2016.7729192", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095775237"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mgrs.2017.2762307", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100195747"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1613/jair.614", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1105579486"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-12", 
    "datePublishedReg": "2018-12-01", 
    "description": "BACKGROUND: Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country's existing administrative boundaries into area units that vary in size from 50\u00a0m\u2009\u00d7\u200950\u00a0m to 150\u00a0m\u2009\u00d7\u2009150\u00a0m. To avoid sending interviewers to unoccupied areas, researchers manually classify grid cells as \"residential\" or \"nonresidential\" through visual inspection of aerial images. \"Nonresidential\" units are then excluded from sampling and data collection. This process of manually classifying sampling units has drawbacks since it is labor intensive, prone to human error, and creates the need for simplifying assumptions during calculation of design-based sampling weights. In this paper, we discuss the development of a deep learning classification\u00a0model to predict whether aerial images are residential or nonresidential, thus reducing manual labor and eliminating the need for simplifying assumptions.\nRESULTS: On our test sets, the model performs comparable to a human-level baseline in both Nigeria (94.5% accuracy) and Guatemala (96.4% accuracy), and outperforms baseline machine learning models trained on crowdsourced or remote-sensed geospatial features. Additionally, our findings suggest that this approach can work well in new areas with relatively modest amounts of training data.\nCONCLUSIONS: Gridded population sampling methods like geosampling are becoming increasingly popular in countries with outdated or inaccurate census data because of their timeliness, flexibility, and cost. Using deep learning models directly on satellite images, we provide a novel method for sample frame construction that identifies residential gridded aerial units. In cases where manual classification of satellite images is used to (1) correct for errors in gridded population data sets or (2) classify grids where population estimates are unavailable, this methodology can help reduce annotation burden with comparable quality to human analysts.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1186/s12942-018-0132-1", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1031277", 
        "issn": [
          "1476-072X"
        ], 
        "name": "International Journal of Health Geographics", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "17"
      }
    ], 
    "name": "Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery", 
    "pagination": "12", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "6963cdd505e703ed30bcf60a502125dc240a928e1b7726a0434e0251e5ca7d84"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "29743081"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101152198"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s12942-018-0132-1"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1103904810"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s12942-018-0132-1", 
      "https://app.dimensions.ai/details/publication/pub.1103904810"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T09:59", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000347_0000000347/records_89814_00000003.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1186%2Fs12942-018-0132-1"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s12942-018-0132-1'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s12942-018-0132-1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s12942-018-0132-1'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s12942-018-0132-1'


 

This table displays all metadata directly associated to this object as RDF triples.

350 TRIPLES      21 PREDICATES      102 URIs      30 LITERALS      18 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s12942-018-0132-1 schema:about N1c8d0ad56c67487b9fbc259dc6d0533a
2 N6206f95131314345bccb230300239d42
3 N6493cfd7ee4544d0a9749f5b02cbfbfc
4 N71b80fabe29b4cd78044c960d2b68239
5 Nb82e31dd752642d0aa379e0ea7d13007
6 Nc072c0f7fd054e278b9974c1d2199f26
7 Nd1fdadf31cda4895acbd6a2ec3ab8c90
8 Nd4cc99618b45430a86a834422b3b291f
9 Ne2f5730884a54aeb97f79f4a928c18cf
10 anzsrc-for:08
11 anzsrc-for:0801
12 schema:author Nfc2709c35496431892a5cb0ab1503a3e
13 schema:citation sg:pub.10.1007/978-3-540-77058-9_4
14 sg:pub.10.1007/s10462-009-9124-7
15 sg:pub.10.1007/s11263-015-0816-y
16 sg:pub.10.1007/s11524-016-0046-9
17 sg:pub.10.1038/nature14539
18 sg:pub.10.1186/1471-2458-12-959
19 sg:pub.10.1186/1476-072x-11-12
20 sg:pub.10.1186/1476-072x-9-45
21 sg:pub.10.1186/s12936-015-0831-z
22 sg:pub.10.1186/s12942-017-0098-4
23 https://doi.org/10.1001/archpsyc.1985.01790300093012
24 https://doi.org/10.1006/ciun.1993.1024
25 https://doi.org/10.1016/0034-4257(80)90021-8
26 https://doi.org/10.1016/j.isprsjprs.2009.06.004
27 https://doi.org/10.1016/j.isprsjprs.2013.09.014
28 https://doi.org/10.1016/j.rse.2005.02.001
29 https://doi.org/10.1016/j.rse.2014.02.015
30 https://doi.org/10.1037/0033-2909.101.1.140
31 https://doi.org/10.1080/01431161.2011.552923
32 https://doi.org/10.1080/01621459.1958.10501465
33 https://doi.org/10.1080/2150704x.2016.1235299
34 https://doi.org/10.1086/266043
35 https://doi.org/10.1093/jssam/smw012
36 https://doi.org/10.1093/poq/nfq066
37 https://doi.org/10.1109/cvpr.2009.5206848
38 https://doi.org/10.1109/cvpr.2016.308
39 https://doi.org/10.1109/cvpr.2016.90
40 https://doi.org/10.1109/icassp.2013.6638947
41 https://doi.org/10.1109/icassp.2014.6854661
42 https://doi.org/10.1109/icra.2017.7989417
43 https://doi.org/10.1109/igarss.2016.7729192
44 https://doi.org/10.1109/jproc.2017.2675998
45 https://doi.org/10.1109/lgrs.2015.2499239
46 https://doi.org/10.1109/lgrs.2015.2513443
47 https://doi.org/10.1109/mcas.2006.1688199
48 https://doi.org/10.1109/mgrs.2017.2762307
49 https://doi.org/10.1109/tgrs.2017.2685945
50 https://doi.org/10.1109/tkde.2009.191
51 https://doi.org/10.1109/tmi.2016.2528162
52 https://doi.org/10.1111/1467-985x.00090
53 https://doi.org/10.1126/science.227.4685.369
54 https://doi.org/10.1126/science.aaf7894
55 https://doi.org/10.1145/1869790.1869829
56 https://doi.org/10.1145/219717.219748
57 https://doi.org/10.1145/2820783.2820816
58 https://doi.org/10.1145/3065386
59 https://doi.org/10.1162/neco.1992.4.4.605
60 https://doi.org/10.1162/neco.1996.8.7.1341
61 https://doi.org/10.1177/001316446002000104
62 https://doi.org/10.1177/0049124114521150
63 https://doi.org/10.1371/journal.pmed.1001007
64 https://doi.org/10.1371/journal.pmed.1001533
65 https://doi.org/10.1371/journal.pone.0180698
66 https://doi.org/10.1613/jair.614
67 https://doi.org/10.2307/1247046
68 https://doi.org/10.2307/2529310
69 https://doi.org/10.2307/3149339
70 https://doi.org/10.2307/3150117
71 https://doi.org/10.2478/jos-2014-0013
72 https://doi.org/10.3390/rs71114680
73 https://doi.org/10.3390/rs8040329
74 https://doi.org/10.3390/rs9080848
75 https://doi.org/10.3390/s16121990
76 https://doi.org/10.4081/gh.2016.410
77 schema:datePublished 2018-12
78 schema:datePublishedReg 2018-12-01
79 schema:description BACKGROUND: Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country's existing administrative boundaries into area units that vary in size from 50 m × 50 m to 150 m × 150 m. To avoid sending interviewers to unoccupied areas, researchers manually classify grid cells as "residential" or "nonresidential" through visual inspection of aerial images. "Nonresidential" units are then excluded from sampling and data collection. This process of manually classifying sampling units has drawbacks since it is labor intensive, prone to human error, and creates the need for simplifying assumptions during calculation of design-based sampling weights. In this paper, we discuss the development of a deep learning classification model to predict whether aerial images are residential or nonresidential, thus reducing manual labor and eliminating the need for simplifying assumptions. RESULTS: On our test sets, the model performs comparable to a human-level baseline in both Nigeria (94.5% accuracy) and Guatemala (96.4% accuracy), and outperforms baseline machine learning models trained on crowdsourced or remote-sensed geospatial features. Additionally, our findings suggest that this approach can work well in new areas with relatively modest amounts of training data. CONCLUSIONS: Gridded population sampling methods like geosampling are becoming increasingly popular in countries with outdated or inaccurate census data because of their timeliness, flexibility, and cost. Using deep learning models directly on satellite images, we provide a novel method for sample frame construction that identifies residential gridded aerial units. In cases where manual classification of satellite images is used to (1) correct for errors in gridded population data sets or (2) classify grids where population estimates are unavailable, this methodology can help reduce annotation burden with comparable quality to human analysts.
80 schema:genre research_article
81 schema:inLanguage en
82 schema:isAccessibleForFree true
83 schema:isPartOf N4f12bfa301f3470ba9ce5f9b18ef60cc
84 Na82f1c59e1ca4590ae13bf885fe03313
85 sg:journal.1031277
86 schema:name Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery
87 schema:pagination 12
88 schema:productId N37bd03eca6f34dcc9295658713ff6387
89 N44346f649d1b40359734a26c87af0c1f
90 N7a367621931b46248350121d14f09109
91 Nb876df69ca9a416eae14a59955fab0bb
92 Nd8d1f0cc31b14b0bae002b2f2c04ea79
93 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103904810
94 https://doi.org/10.1186/s12942-018-0132-1
95 schema:sdDatePublished 2019-04-11T09:59
96 schema:sdLicense https://scigraph.springernature.com/explorer/license/
97 schema:sdPublisher N966a6ac862da4c749376f0103bc8e41e
98 schema:url https://link.springer.com/10.1186%2Fs12942-018-0132-1
99 sgo:license sg:explorer/license/
100 sgo:sdDataset articles
101 rdf:type schema:ScholarlyArticle
102 N0c711523b64141f68c2dcae3f45cb0e9 rdf:first sg:person.0606166667.23
103 rdf:rest N2375afc234fd44ba93a26f733d2e92ee
104 N1c8d0ad56c67487b9fbc259dc6d0533a schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
105 schema:name Nigeria
106 rdf:type schema:DefinedTerm
107 N2375afc234fd44ba93a26f733d2e92ee rdf:first sg:person.01275003217.35
108 rdf:rest Nf20be3a934874cb3bcd925e3a59959ce
109 N37bd03eca6f34dcc9295658713ff6387 schema:name readcube_id
110 schema:value 6963cdd505e703ed30bcf60a502125dc240a928e1b7726a0434e0251e5ca7d84
111 rdf:type schema:PropertyValue
112 N44346f649d1b40359734a26c87af0c1f schema:name pubmed_id
113 schema:value 29743081
114 rdf:type schema:PropertyValue
115 N4f12bfa301f3470ba9ce5f9b18ef60cc schema:volumeNumber 17
116 rdf:type schema:PublicationVolume
117 N54ae815473ee4c1fb17208e1b4406c5e rdf:first sg:person.015114276136.32
118 rdf:rest Nf0ac2ae6ba39420e81894bad540d0b5f
119 N6206f95131314345bccb230300239d42 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
120 schema:name Residence Characteristics
121 rdf:type schema:DefinedTerm
122 N6493cfd7ee4544d0a9749f5b02cbfbfc schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
123 schema:name Guatemala
124 rdf:type schema:DefinedTerm
125 N71b80fabe29b4cd78044c960d2b68239 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
126 schema:name Humans
127 rdf:type schema:DefinedTerm
128 N7a367621931b46248350121d14f09109 schema:name doi
129 schema:value 10.1186/s12942-018-0132-1
130 rdf:type schema:PropertyValue
131 N87944b1d9e484d0e831afaf61350ef9c rdf:first sg:person.016507237136.40
132 rdf:rest N0c711523b64141f68c2dcae3f45cb0e9
133 N966a6ac862da4c749376f0103bc8e41e schema:name Springer Nature - SN SciGraph project
134 rdf:type schema:Organization
135 Na82f1c59e1ca4590ae13bf885fe03313 schema:issueNumber 1
136 rdf:type schema:PublicationIssue
137 Nb82e31dd752642d0aa379e0ea7d13007 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
138 schema:name Demography
139 rdf:type schema:DefinedTerm
140 Nb876df69ca9a416eae14a59955fab0bb schema:name dimensions_id
141 schema:value pub.1103904810
142 rdf:type schema:PropertyValue
143 Nc072c0f7fd054e278b9974c1d2199f26 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
144 schema:name Neural Networks (Computer)
145 rdf:type schema:DefinedTerm
146 Nd1fdadf31cda4895acbd6a2ec3ab8c90 schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
147 schema:name Developing Countries
148 rdf:type schema:DefinedTerm
149 Nd4cc99618b45430a86a834422b3b291f schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
150 schema:name Data Collection
151 rdf:type schema:DefinedTerm
152 Nd8d1f0cc31b14b0bae002b2f2c04ea79 schema:name nlm_unique_id
153 schema:value 101152198
154 rdf:type schema:PropertyValue
155 Ne2f5730884a54aeb97f79f4a928c18cf schema:inDefinedTermSet https://www.nlm.nih.gov/mesh/
156 schema:name Satellite Imagery
157 rdf:type schema:DefinedTerm
158 Nf0ac2ae6ba39420e81894bad540d0b5f rdf:first sg:person.015711656536.82
159 rdf:rest N87944b1d9e484d0e831afaf61350ef9c
160 Nf20be3a934874cb3bcd925e3a59959ce rdf:first sg:person.01152070215.31
161 rdf:rest rdf:nil
162 Nfc2709c35496431892a5cb0ab1503a3e rdf:first sg:person.013501664057.86
163 rdf:rest N54ae815473ee4c1fb17208e1b4406c5e
164 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
165 schema:name Information and Computing Sciences
166 rdf:type schema:DefinedTerm
167 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
168 schema:name Artificial Intelligence and Image Processing
169 rdf:type schema:DefinedTerm
170 sg:journal.1031277 schema:issn 1476-072X
171 schema:name International Journal of Health Geographics
172 rdf:type schema:Periodical
173 sg:person.01152070215.31 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
174 schema:familyName Bruhn
175 schema:givenName Mark
176 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01152070215.31
177 rdf:type schema:Person
178 sg:person.01275003217.35 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
179 schema:familyName Allpress
180 schema:givenName Justine
181 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01275003217.35
182 rdf:type schema:Person
183 sg:person.013501664057.86 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
184 schema:familyName Chew
185 schema:givenName Robert F.
186 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013501664057.86
187 rdf:type schema:Person
188 sg:person.015114276136.32 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
189 schema:familyName Amer
190 schema:givenName Safaa
191 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015114276136.32
192 rdf:type schema:Person
193 sg:person.015711656536.82 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
194 schema:familyName Jones
195 schema:givenName Kasey
196 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015711656536.82
197 rdf:type schema:Person
198 sg:person.016507237136.40 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
199 schema:familyName Unangst
200 schema:givenName Jennifer
201 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016507237136.40
202 rdf:type schema:Person
203 sg:person.0606166667.23 schema:affiliation https://www.grid.ac/institutes/grid.62562.35
204 schema:familyName Cajka
205 schema:givenName James
206 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606166667.23
207 rdf:type schema:Person
208 sg:pub.10.1007/978-3-540-77058-9_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039241015
209 https://doi.org/10.1007/978-3-540-77058-9_4
210 rdf:type schema:CreativeWork
211 sg:pub.10.1007/s10462-009-9124-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017758686
212 https://doi.org/10.1007/s10462-009-9124-7
213 rdf:type schema:CreativeWork
214 sg:pub.10.1007/s11263-015-0816-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1009767488
215 https://doi.org/10.1007/s11263-015-0816-y
216 rdf:type schema:CreativeWork
217 sg:pub.10.1007/s11524-016-0046-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019537003
218 https://doi.org/10.1007/s11524-016-0046-9
219 rdf:type schema:CreativeWork
220 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
221 https://doi.org/10.1038/nature14539
222 rdf:type schema:CreativeWork
223 sg:pub.10.1186/1471-2458-12-959 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030338225
224 https://doi.org/10.1186/1471-2458-12-959
225 rdf:type schema:CreativeWork
226 sg:pub.10.1186/1476-072x-11-12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035871335
227 https://doi.org/10.1186/1476-072x-11-12
228 rdf:type schema:CreativeWork
229 sg:pub.10.1186/1476-072x-9-45 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022029214
230 https://doi.org/10.1186/1476-072x-9-45
231 rdf:type schema:CreativeWork
232 sg:pub.10.1186/s12936-015-0831-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1001546313
233 https://doi.org/10.1186/s12936-015-0831-z
234 rdf:type schema:CreativeWork
235 sg:pub.10.1186/s12942-017-0098-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090773364
236 https://doi.org/10.1186/s12942-017-0098-4
237 rdf:type schema:CreativeWork
238 https://doi.org/10.1001/archpsyc.1985.01790300093012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021068313
239 rdf:type schema:CreativeWork
240 https://doi.org/10.1006/ciun.1993.1024 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044516065
241 rdf:type schema:CreativeWork
242 https://doi.org/10.1016/0034-4257(80)90021-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021981194
243 rdf:type schema:CreativeWork
244 https://doi.org/10.1016/j.isprsjprs.2009.06.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020267301
245 rdf:type schema:CreativeWork
246 https://doi.org/10.1016/j.isprsjprs.2013.09.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006381529
247 rdf:type schema:CreativeWork
248 https://doi.org/10.1016/j.rse.2005.02.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004046220
249 rdf:type schema:CreativeWork
250 https://doi.org/10.1016/j.rse.2014.02.015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044652759
251 rdf:type schema:CreativeWork
252 https://doi.org/10.1037/0033-2909.101.1.140 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047130153
253 rdf:type schema:CreativeWork
254 https://doi.org/10.1080/01431161.2011.552923 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037898439
255 rdf:type schema:CreativeWork
256 https://doi.org/10.1080/01621459.1958.10501465 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058299431
257 rdf:type schema:CreativeWork
258 https://doi.org/10.1080/2150704x.2016.1235299 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017631063
259 rdf:type schema:CreativeWork
260 https://doi.org/10.1086/266043 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058576656
261 rdf:type schema:CreativeWork
262 https://doi.org/10.1093/jssam/smw012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059833580
263 rdf:type schema:CreativeWork
264 https://doi.org/10.1093/poq/nfq066 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059979102
265 rdf:type schema:CreativeWork
266 https://doi.org/10.1109/cvpr.2009.5206848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095689025
267 rdf:type schema:CreativeWork
268 https://doi.org/10.1109/cvpr.2016.308 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093497718
269 rdf:type schema:CreativeWork
270 https://doi.org/10.1109/cvpr.2016.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359587
271 rdf:type schema:CreativeWork
272 https://doi.org/10.1109/icassp.2013.6638947 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095157363
273 rdf:type schema:CreativeWork
274 https://doi.org/10.1109/icassp.2014.6854661 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094421042
275 rdf:type schema:CreativeWork
276 https://doi.org/10.1109/icra.2017.7989417 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094478815
277 rdf:type schema:CreativeWork
278 https://doi.org/10.1109/igarss.2016.7729192 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095775237
279 rdf:type schema:CreativeWork
280 https://doi.org/10.1109/jproc.2017.2675998 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084605162
281 rdf:type schema:CreativeWork
282 https://doi.org/10.1109/lgrs.2015.2499239 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061360807
283 rdf:type schema:CreativeWork
284 https://doi.org/10.1109/lgrs.2015.2513443 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061360852
285 rdf:type schema:CreativeWork
286 https://doi.org/10.1109/mcas.2006.1688199 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061389638
287 rdf:type schema:CreativeWork
288 https://doi.org/10.1109/mgrs.2017.2762307 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100195747
289 rdf:type schema:CreativeWork
290 https://doi.org/10.1109/tgrs.2017.2685945 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085257848
291 rdf:type schema:CreativeWork
292 https://doi.org/10.1109/tkde.2009.191 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041355599
293 rdf:type schema:CreativeWork
294 https://doi.org/10.1109/tmi.2016.2528162 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061696701
295 rdf:type schema:CreativeWork
296 https://doi.org/10.1111/1467-985x.00090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026593228
297 rdf:type schema:CreativeWork
298 https://doi.org/10.1126/science.227.4685.369 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062529705
299 rdf:type schema:CreativeWork
300 https://doi.org/10.1126/science.aaf7894 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010648224
301 rdf:type schema:CreativeWork
302 https://doi.org/10.1145/1869790.1869829 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025470079
303 rdf:type schema:CreativeWork
304 https://doi.org/10.1145/219717.219748 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005662680
305 rdf:type schema:CreativeWork
306 https://doi.org/10.1145/2820783.2820816 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028229296
307 rdf:type schema:CreativeWork
308 https://doi.org/10.1145/3065386 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085642448
309 rdf:type schema:CreativeWork
310 https://doi.org/10.1162/neco.1992.4.4.605 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013658470
311 rdf:type schema:CreativeWork
312 https://doi.org/10.1162/neco.1996.8.7.1341 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003549317
313 rdf:type schema:CreativeWork
314 https://doi.org/10.1177/001316446002000104 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039619716
315 rdf:type schema:CreativeWork
316 https://doi.org/10.1177/0049124114521150 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053784999
317 rdf:type schema:CreativeWork
318 https://doi.org/10.1371/journal.pmed.1001007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041093395
319 rdf:type schema:CreativeWork
320 https://doi.org/10.1371/journal.pmed.1001533 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036230054
321 rdf:type schema:CreativeWork
322 https://doi.org/10.1371/journal.pone.0180698 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091151401
323 rdf:type schema:CreativeWork
324 https://doi.org/10.1613/jair.614 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105579486
325 rdf:type schema:CreativeWork
326 https://doi.org/10.2307/1247046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069413181
327 rdf:type schema:CreativeWork
328 https://doi.org/10.2307/2529310 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069974986
329 rdf:type schema:CreativeWork
330 https://doi.org/10.2307/3149339 schema:sameAs https://app.dimensions.ai/details/publication/pub.1070211959
331 rdf:type schema:CreativeWork
332 https://doi.org/10.2307/3150117 schema:sameAs https://app.dimensions.ai/details/publication/pub.1070212657
333 rdf:type schema:CreativeWork
334 https://doi.org/10.2478/jos-2014-0013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043556035
335 rdf:type schema:CreativeWork
336 https://doi.org/10.3390/rs71114680 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052528622
337 rdf:type schema:CreativeWork
338 https://doi.org/10.3390/rs8040329 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002913079
339 rdf:type schema:CreativeWork
340 https://doi.org/10.3390/rs9080848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091217523
341 rdf:type schema:CreativeWork
342 https://doi.org/10.3390/s16121990 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039334688
343 rdf:type schema:CreativeWork
344 https://doi.org/10.4081/gh.2016.410 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023097789
345 rdf:type schema:CreativeWork
346 https://www.grid.ac/institutes/grid.62562.35 schema:alternateName RTI International
347 schema:name Center for Data Science, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA
348 Division for Statistical and Data Sciences, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA
349 Geospatial Science and Technology Program, RTI International, 3040 East Cornwallis Road, Research Triangle Park, NC, USA
350 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...