{"id":"https://openalex.org/W7165552182","doi":"https://doi.org/10.5194/ems2026-297","title":"Explainable Flood Mapping from Sentinel-1 Imagery using CNNs and Vision Transformers","display_name":"Explainable Flood Mapping from Sentinel-1 Imagery using CNNs and Vision Transformers","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165552182","doi":"https://doi.org/10.5194/ems2026-297"},"language":null,"primary_location":{"id":"doi:10.5194/ems2026-297","doi":"https://doi.org/10.5194/ems2026-297","is_oa":true,"landing_page_url":"https://doi.org/10.5194/ems2026-297","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5194/ems2026-297","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049108271","display_name":"Arundhuti Banerjee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arundhuti Banerjee","raw_affiliation_strings":["UNU EHS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNU EHS","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036444086","display_name":"David Daou","orcid":"https://orcid.org/0000-0001-8729-7115","observed_orcids":["https://orcid.org/0000-0001-8729-7115"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Daou","raw_affiliation_strings":["UNU EHS"],"raw_orcid":"https://orcid.org/0000-0001-8729-7115","affiliations":[{"raw_affiliation_string":"UNU EHS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5036444086"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10930","display_name":"Flood Risk Assessment and Management","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10930","display_name":"Flood Risk Assessment and Management","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.023000000044703484,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11490","display_name":"Hydrological Forecasting Using AI","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flood-mapping","display_name":"flood mapping","score":0.996999979019165},{"id":"https://openalex.org/keywords/sentinel-1","display_name":"Sentinel-1","score":0.8690000176429749},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"synthetic aperture radar","score":0.9700000286102295},{"id":"https://openalex.org/keywords/flood-segmentation","display_name":"flood segmentation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/explainable-deep-learning","display_name":"explainable deep learning","score":0.7689999938011169},{"id":"https://openalex.org/keywords/grad-cam","display_name":"Grad-CAM","score":0.8740000128746033},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.8069999814033508},{"id":"https://openalex.org/keywords/segformer","display_name":"SegFormer","score":0.8550000190734863},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.9829999804496765},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.8640000224113464},{"id":"https://openalex.org/keywords/cross-dataset-generalization","display_name":"cross-dataset generalization","score":0.8320000171661377},{"id":"https://openalex.org/keywords/radar-backscatter","display_name":"radar backscatter","score":0.6790000200271606},{"id":"https://openalex.org/keywords/disaster-response","display_name":"disaster response","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042999863624573},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C74256435","wikidata":"https://www.wikidata.org/wiki/Q134052","display_name":"Flood myth","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5958999991416931},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38100001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C10929652","wikidata":"https://www.wikidata.org/wiki/Q7279985","display_name":"Radar imaging","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5194/ems2026-297","doi":"https://doi.org/10.5194/ems2026-297","is_oa":true,"landing_page_url":"https://doi.org/10.5194/ems2026-297","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.5194/ems2026-297","doi":"https://doi.org/10.5194/ems2026-297","is_oa":true,"landing_page_url":"https://doi.org/10.5194/ems2026-297","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.5351999998092651,"id":"https://metadata.un.org/sdg/13"}],"sustainable_development_goals_aurora":[{"display_name":"Climate action","score":0.7323474287986755,"id":"https://metadata.un.org/sdg/13"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reliable":[0],"and":[1,11,41,58,66,94,117,128,157,165,227],"efficient":[2],"flood":[3,31,60,75,111,147,178,225],"mapping":[4,226],"techniques":[5],"are":[6],"critical":[7],"for":[8,223,237],"disaster":[9,64],"response":[10],"risk":[12],"assessment.":[13],"Satellite-based":[14],"Earth":[15,81],"observation,":[16,82],"particularly":[17],"Synthetic":[18],"Aperture":[19],"Radar":[20],"(SAR)":[21],"data":[22],"from":[23,114],"Sentinel-1,":[24],"provides":[25],"an":[26],"effective":[27],"means":[28],"of":[29,38,56,220,232],"monitoring":[30],"events":[32],"over":[33],"large":[34],"spatial":[35],"scales,":[36],"independent":[37],"cloud":[39],"cover":[40],"daylight":[42],"conditions.":[43],"When":[44],"combined":[45],"with":[46,90],"advanced":[47],"deep":[48,137],"learning":[49,138],"algorithms,":[50],"SAR":[51,146],"imagery":[52],"enables":[53],"the":[54,121,218,229],"generation":[55],"accurate":[57],"timely":[59],"maps":[61],"that":[62,171],"support":[63],"mitigation":[65],"emergency":[67],"response.":[68],"In":[69,185],"this":[70],"study,":[71],"we":[72,134,150],"benchmark":[73],"multiple":[74],"segmentation":[76,103,132,213],"architectures":[77,97,173],"commonly":[78],"used":[79],"in":[80,211,234],"including":[83],"convolutional":[84],"neural":[85],"network":[86],"(CNN)-based":[87],"U-Net":[88,199],"models":[89,144,200],"different":[91],"encoder":[92],"backbones":[93],"transformer-based":[95,172],"vision":[96],"such":[98],"as":[99],"SegFormer.":[100],"A":[101],"multiclass":[102],"model":[104,129,163],"is":[105],"initially":[106],"trained":[107],"on":[108,120,204],"a":[109],"Sentinel-1":[110],"dataset":[112,123],"derived":[113],"NASA":[115],"observations":[116],"subsequently":[118],"fine-tuned":[119],"Sen1Floods11":[122],"to":[124,140,161,181,202],"evaluate":[125],"cross-dataset":[126],"generalization":[127],"robustness.":[130],"Beyond":[131],"accuracy,":[133],"investigate":[135],"explainable":[136],"approaches":[139],"better":[141],"understand":[142],"how":[143],"interpret":[145],"signatures.":[148],"Specifically,":[149],"employ":[151],"Gradient-weighted":[152],"Class":[153],"Activation":[154],"Mapping":[155],"(Grad-CAM)":[156],"entropy-based":[158],"uncertainty":[159],"estimation":[160],"analyze":[162],"attention":[164],"prediction":[166],"confidence.":[167],"Our":[168],"results":[169],"indicate":[170],"produce":[174],"more":[175,195],"spatially":[176],"coherent":[177],"predictions":[179],"compared":[180],"traditional":[182],"CNN":[183],"models.":[184],"several":[186],"test":[187],"scenes,":[188],"SegFormer":[189],"captures":[190],"large,":[191],"continuous":[192],"inundated":[193],"regions":[194],"effectively,":[196],"whereas":[197],"CNN-based":[198],"tend":[201],"rely":[203],"localized":[205],"radar":[206],"backscatter":[207],"patterns,":[208],"often":[209],"resulting":[210],"fragmented":[212],"outputs.":[214],"These":[215],"findings":[216],"underline":[217],"importance":[219],"architectural":[221],"choice":[222],"robust":[224],"demonstrate":[228],"added":[230],"value":[231],"explainability":[233],"building":[235],"trust":[236],"operational":[238],"deployment.":[239]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-06-23T00:00:00"}