Wildland Fire Spread Modeling Using Convolutional Neural Networks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-27

AUTHORS

Jonathan L. Hodges, Brian Y. Lattimer

ABSTRACT

The computational cost of predicting wildland fire spread across large, diverse landscapes is significant using current models, which limits the ability to use simulations to develop mitigation strategies or perform forecasting. This paper presents a machine learning approach to estimate the time-resolved spatial evolution of a wildland fire front using a deep convolutional inverse graphics network (DCIGN). The DCIGN was trained and tested for wildland fire spread across simple homogeneous landscapes as well as heterogeneous landscapes having complex terrain. Data sets for training, validation, and testing were created using computational models. The model for homogeneous landscapes was based on a rate of spread from the model of Rothermel, while heterogeneous spread was modeled using FARSITE. Over 10,000 model predictions were made to determine burn maps in 6 h increments up to 24 h after ignition. Overall the predicted burn maps from the DCIGN-based approach agreed with simulation results, with mean precision, sensitivity, F-measure, and Chan–Vese similarity of 0.97, 0.92, 0.93, and 0.93, respectively. Noise in the input parameters was found to not significantly impact the DCIGN-based predictions. The computational cost of the method was found to be significantly better than the computational model for heterogeneous spatial conditions where a reduction in simulation time of 102-105 was observed. In addition, the DCIGN-based approach was shown to be capable of predicting burn maps further in the future by recursively using previous predictions as inputs to the DCIGN. The machine learning DCIGN approach was able to provide fire spread predictions at a computational cost three orders of magnitude less than current models. More... »

PAGES

1-28

References to SciGraph publications

  • 2016. Wildland Fires in SFPE HANDBOOK OF FIRE PROTECTION ENGINEERING
  • 2017-06. Wildfire Susceptibility Assessment in Southern China: A Comparison of Multiple Methods in INTERNATIONAL JOURNAL OF DISASTER RISK SCIENCE
  • 2015-04. Predicting Burned Areas of Forest Fires: an Artificial Intelligence Approach in FIRE ECOLOGY
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10694-019-00846-4

    DOI

    http://dx.doi.org/10.1007/s10694-019-00846-4

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1113042317


    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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "name": [
                "Jensen Hughes, 2020 Kraft Drive, Suite 3020, 24060, Blacksburg, VA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hodges", 
            "givenName": "Jonathan L.", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Jensen Hughes, 2020 Kraft Drive, Suite 3020, 24060, Blacksburg, VA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lattimer", 
            "givenName": "Brian Y.", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1071/wf02031", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000366156"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1071/wf06002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000929519"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5558/tfc45103-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003269555"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4939-2565-0_87", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1006585632", 
              "https://doi.org/10.1007/978-1-4939-2565-0_87"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5194/nhess-14-2951-2014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007041451"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/neco.1989.1.4.541", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008345178"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.proci.2012.06.090", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009839432"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.procs.2012.04.119", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019386206"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1071/wf08088", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022499406"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2379810.2379816", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037021569"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0304-3800(83)90030-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037223108"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0304-3800(83)90030-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037223108"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1071/wf16031", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038263206"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5194/nhess-15-1721-2015", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040018451"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.firesaf.2013.08.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043663425"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1071/wf12202", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046070241"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0360-1285(91)90003-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049203482"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/83.902291", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061240267"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpds.2015.2405912", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061754829"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.12988/ams.2013.13025", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1064851810"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3801/iafss.fss.11-1443", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1071435505"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.4996/fireecology.1101106", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1072532988", 
              "https://doi.org/10.4996/fireecology.1101106"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.firesaf.2017.03.057", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084757099"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13753-017-0129-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086120279", 
              "https://doi.org/10.1007/s13753-017-0129-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s13753-017-0129-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1086120279", 
              "https://doi.org/10.1007/s13753-017-0129-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2015.123", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093828312"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ijcnn.2016.7727265", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094811940"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.244", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060220"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.310", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060294"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2737/rmrs-gtr-266", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103736524"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2737/rmrs-gtr-153", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1103747408"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.proci.2018.07.112", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1106610453"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-03-27", 
        "datePublishedReg": "2019-03-27", 
        "description": "The computational cost of predicting wildland fire spread across large, diverse landscapes is significant using current models, which limits the ability to use simulations to develop mitigation strategies or perform forecasting. This paper presents a machine learning approach to estimate the time-resolved spatial evolution of a wildland fire front using a deep convolutional inverse graphics network (DCIGN). The DCIGN was trained and tested for wildland fire spread across simple homogeneous landscapes as well as heterogeneous landscapes having complex terrain. Data sets for training, validation, and testing were created using computational models. The model for homogeneous landscapes was based on a rate of spread from the model of Rothermel, while heterogeneous spread was modeled using FARSITE. Over 10,000 model predictions were made to determine burn maps in 6 h increments up to 24 h after ignition. Overall the predicted burn maps from the DCIGN-based approach agreed with simulation results, with mean precision, sensitivity, F-measure, and Chan\u2013Vese similarity of 0.97, 0.92, 0.93, and 0.93, respectively. Noise in the input parameters was found to not significantly impact the DCIGN-based predictions. The computational cost of the method was found to be significantly better than the computational model for heterogeneous spatial conditions where a reduction in simulation time of 102-105 was observed. In addition, the DCIGN-based approach was shown to be capable of predicting burn maps further in the future by recursively using previous predictions as inputs to the DCIGN. The machine learning DCIGN approach was able to provide fire spread predictions at a computational cost three orders of magnitude less than current models.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s10694-019-00846-4", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1122008", 
            "issn": [
              "0015-2684", 
              "1572-8099"
            ], 
            "name": "Fire Technology", 
            "type": "Periodical"
          }
        ], 
        "name": "Wildland Fire Spread Modeling Using Convolutional Neural Networks", 
        "pagination": "1-28", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "2a2bd7c4c03eecddf2f609c230148707e0aff977817c82998d0a7083e6894beb"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10694-019-00846-4"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1113042317"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10694-019-00846-4", 
          "https://app.dimensions.ai/details/publication/pub.1113042317"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T13:18", 
        "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/v90/0000000368_0000000368/records_78941_00000001.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs10694-019-00846-4"
      }
    ]
     

    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.10.1007/s10694-019-00846-4'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s10694-019-00846-4'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10694-019-00846-4'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10694-019-00846-4'


     

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

    154 TRIPLES      21 PREDICATES      54 URIs      16 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10694-019-00846-4 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nab3022024eac467494c362ffbeed39cf
    4 schema:citation sg:pub.10.1007/978-1-4939-2565-0_87
    5 sg:pub.10.1007/s13753-017-0129-6
    6 sg:pub.10.4996/fireecology.1101106
    7 https://doi.org/10.1016/0304-3800(83)90030-3
    8 https://doi.org/10.1016/0360-1285(91)90003-6
    9 https://doi.org/10.1016/j.firesaf.2013.08.014
    10 https://doi.org/10.1016/j.firesaf.2017.03.057
    11 https://doi.org/10.1016/j.proci.2012.06.090
    12 https://doi.org/10.1016/j.proci.2018.07.112
    13 https://doi.org/10.1016/j.procs.2012.04.119
    14 https://doi.org/10.1071/wf02031
    15 https://doi.org/10.1071/wf06002
    16 https://doi.org/10.1071/wf08088
    17 https://doi.org/10.1071/wf12202
    18 https://doi.org/10.1071/wf16031
    19 https://doi.org/10.1109/83.902291
    20 https://doi.org/10.1109/iccv.2015.123
    21 https://doi.org/10.1109/iccv.2017.244
    22 https://doi.org/10.1109/iccv.2017.310
    23 https://doi.org/10.1109/ijcnn.2016.7727265
    24 https://doi.org/10.1109/tpds.2015.2405912
    25 https://doi.org/10.1145/2379810.2379816
    26 https://doi.org/10.1162/neco.1989.1.4.541
    27 https://doi.org/10.12988/ams.2013.13025
    28 https://doi.org/10.2737/rmrs-gtr-153
    29 https://doi.org/10.2737/rmrs-gtr-266
    30 https://doi.org/10.3801/iafss.fss.11-1443
    31 https://doi.org/10.5194/nhess-14-2951-2014
    32 https://doi.org/10.5194/nhess-15-1721-2015
    33 https://doi.org/10.5558/tfc45103-2
    34 schema:datePublished 2019-03-27
    35 schema:datePublishedReg 2019-03-27
    36 schema:description The computational cost of predicting wildland fire spread across large, diverse landscapes is significant using current models, which limits the ability to use simulations to develop mitigation strategies or perform forecasting. This paper presents a machine learning approach to estimate the time-resolved spatial evolution of a wildland fire front using a deep convolutional inverse graphics network (DCIGN). The DCIGN was trained and tested for wildland fire spread across simple homogeneous landscapes as well as heterogeneous landscapes having complex terrain. Data sets for training, validation, and testing were created using computational models. The model for homogeneous landscapes was based on a rate of spread from the model of Rothermel, while heterogeneous spread was modeled using FARSITE. Over 10,000 model predictions were made to determine burn maps in 6 h increments up to 24 h after ignition. Overall the predicted burn maps from the DCIGN-based approach agreed with simulation results, with mean precision, sensitivity, F-measure, and Chan–Vese similarity of 0.97, 0.92, 0.93, and 0.93, respectively. Noise in the input parameters was found to not significantly impact the DCIGN-based predictions. The computational cost of the method was found to be significantly better than the computational model for heterogeneous spatial conditions where a reduction in simulation time of 102-105 was observed. In addition, the DCIGN-based approach was shown to be capable of predicting burn maps further in the future by recursively using previous predictions as inputs to the DCIGN. The machine learning DCIGN approach was able to provide fire spread predictions at a computational cost three orders of magnitude less than current models.
    37 schema:genre research_article
    38 schema:inLanguage en
    39 schema:isAccessibleForFree false
    40 schema:isPartOf sg:journal.1122008
    41 schema:name Wildland Fire Spread Modeling Using Convolutional Neural Networks
    42 schema:pagination 1-28
    43 schema:productId N1446b6a1e1dd404098a8fc3a15dc4ae7
    44 N77c9edd513814ddf9423fa51c57f59ae
    45 Nc580f3ee7c9a4a90b21b39c9fe3d1609
    46 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113042317
    47 https://doi.org/10.1007/s10694-019-00846-4
    48 schema:sdDatePublished 2019-04-11T13:18
    49 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    50 schema:sdPublisher Ne4a4c27fca9842c99fdf2ac132c4fdd2
    51 schema:url https://link.springer.com/10.1007%2Fs10694-019-00846-4
    52 sgo:license sg:explorer/license/
    53 sgo:sdDataset articles
    54 rdf:type schema:ScholarlyArticle
    55 N1446b6a1e1dd404098a8fc3a15dc4ae7 schema:name dimensions_id
    56 schema:value pub.1113042317
    57 rdf:type schema:PropertyValue
    58 N1e7b47bdf4404b08b8ac37402c8f6619 rdf:first Nb328522aadf54c82bc6d376498100e7f
    59 rdf:rest rdf:nil
    60 N77c9edd513814ddf9423fa51c57f59ae schema:name readcube_id
    61 schema:value 2a2bd7c4c03eecddf2f609c230148707e0aff977817c82998d0a7083e6894beb
    62 rdf:type schema:PropertyValue
    63 N93de1370b938414687e9d83d96a05b89 schema:name Jensen Hughes, 2020 Kraft Drive, Suite 3020, 24060, Blacksburg, VA, USA
    64 rdf:type schema:Organization
    65 Naaa4d92f5e1b4f839ec8ebb60e644675 schema:name Jensen Hughes, 2020 Kraft Drive, Suite 3020, 24060, Blacksburg, VA, USA
    66 rdf:type schema:Organization
    67 Nab3022024eac467494c362ffbeed39cf rdf:first Nabada58fc16a4be1b61ff778253fe7ad
    68 rdf:rest N1e7b47bdf4404b08b8ac37402c8f6619
    69 Nabada58fc16a4be1b61ff778253fe7ad schema:affiliation Naaa4d92f5e1b4f839ec8ebb60e644675
    70 schema:familyName Hodges
    71 schema:givenName Jonathan L.
    72 rdf:type schema:Person
    73 Nb328522aadf54c82bc6d376498100e7f schema:affiliation N93de1370b938414687e9d83d96a05b89
    74 schema:familyName Lattimer
    75 schema:givenName Brian Y.
    76 rdf:type schema:Person
    77 Nc580f3ee7c9a4a90b21b39c9fe3d1609 schema:name doi
    78 schema:value 10.1007/s10694-019-00846-4
    79 rdf:type schema:PropertyValue
    80 Ne4a4c27fca9842c99fdf2ac132c4fdd2 schema:name Springer Nature - SN SciGraph project
    81 rdf:type schema:Organization
    82 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    83 schema:name Information and Computing Sciences
    84 rdf:type schema:DefinedTerm
    85 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    86 schema:name Artificial Intelligence and Image Processing
    87 rdf:type schema:DefinedTerm
    88 sg:journal.1122008 schema:issn 0015-2684
    89 1572-8099
    90 schema:name Fire Technology
    91 rdf:type schema:Periodical
    92 sg:pub.10.1007/978-1-4939-2565-0_87 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006585632
    93 https://doi.org/10.1007/978-1-4939-2565-0_87
    94 rdf:type schema:CreativeWork
    95 sg:pub.10.1007/s13753-017-0129-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086120279
    96 https://doi.org/10.1007/s13753-017-0129-6
    97 rdf:type schema:CreativeWork
    98 sg:pub.10.4996/fireecology.1101106 schema:sameAs https://app.dimensions.ai/details/publication/pub.1072532988
    99 https://doi.org/10.4996/fireecology.1101106
    100 rdf:type schema:CreativeWork
    101 https://doi.org/10.1016/0304-3800(83)90030-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037223108
    102 rdf:type schema:CreativeWork
    103 https://doi.org/10.1016/0360-1285(91)90003-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049203482
    104 rdf:type schema:CreativeWork
    105 https://doi.org/10.1016/j.firesaf.2013.08.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043663425
    106 rdf:type schema:CreativeWork
    107 https://doi.org/10.1016/j.firesaf.2017.03.057 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084757099
    108 rdf:type schema:CreativeWork
    109 https://doi.org/10.1016/j.proci.2012.06.090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009839432
    110 rdf:type schema:CreativeWork
    111 https://doi.org/10.1016/j.proci.2018.07.112 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106610453
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.1016/j.procs.2012.04.119 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019386206
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1071/wf02031 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000366156
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1071/wf06002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000929519
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1071/wf08088 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022499406
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1071/wf12202 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046070241
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1071/wf16031 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038263206
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1109/83.902291 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061240267
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/iccv.2015.123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093828312
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/iccv.2017.244 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060220
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/iccv.2017.310 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060294
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/ijcnn.2016.7727265 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094811940
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/tpds.2015.2405912 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061754829
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1145/2379810.2379816 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037021569
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1162/neco.1989.1.4.541 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008345178
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.12988/ams.2013.13025 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064851810
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.2737/rmrs-gtr-153 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103747408
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.2737/rmrs-gtr-266 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103736524
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.3801/iafss.fss.11-1443 schema:sameAs https://app.dimensions.ai/details/publication/pub.1071435505
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.5194/nhess-14-2951-2014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007041451
    150 rdf:type schema:CreativeWork
    151 https://doi.org/10.5194/nhess-15-1721-2015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040018451
    152 rdf:type schema:CreativeWork
    153 https://doi.org/10.5558/tfc45103-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003269555
    154 rdf:type schema:CreativeWork
     




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


    ...