{"id":"https://openalex.org/W7117166895","doi":"https://doi.org/10.48550/arxiv.2512.19504","title":"FusionNet: Physics-Aware Representation Learning for Multi-Spectral and Thermal Data via Trainable Signal-Processing Priors","display_name":"FusionNet: Physics-Aware Representation Learning for Multi-Spectral and Thermal Data via Trainable Signal-Processing Priors","publication_year":2025,"publication_date":"2025-12-22","ids":{"openalex":"https://openalex.org/W7117166895","doi":"https://doi.org/10.48550/arxiv.2512.19504"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.19504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.19504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102842983","display_name":"Georgios Voulgaris","orcid":"https://orcid.org/0000-0003-4597-7352"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Voulgaris, Georgios","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102842983"],"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.13809999823570251,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.13809999823570251,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.1324000060558319,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11225","display_name":"Geothermal Energy Systems and Applications","score":0.1177000030875206,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6843000054359436},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6834999918937683},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6543999910354614},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6514999866485596},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5013999938964844},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48260000348091125},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.47279998660087585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4034999907016754}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7153000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089999914169312},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6843000054359436},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6834999918937683},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6543999910354614},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6514999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4034999907016754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2984335091","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Thermal infrared","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C204530211","wikidata":"https://www.wikidata.org/wiki/Q752823","display_name":"Thermal","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.19504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.19504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19504","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.46425947546958923,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"deep":[1,194],"learning":[2,61,161,195,210],"models":[3],"operating":[4],"on":[5,11,145,181],"multi-modal":[6],"visual":[7],"signals":[8],"often":[9],"rely":[10],"inductive":[12],"biases":[13],"that":[14,37,63,132,165,187],"are":[15],"poorly":[16],"aligned":[17],"with":[18,90,140,192],"the":[19,146,172,184],"physical":[20,73],"processes":[21],"governing":[22],"signal":[23,205],"formation,":[24],"leading":[25],"to":[26,43,67,84,123,137],"brittle":[27],"performance":[28,138],"under":[29,211],"cross-spectral":[30,178],"and":[31,118,149,199],"real-world":[32,182],"conditions.":[33,213],"In":[34],"particular,":[35],"approaches":[36],"prioritise":[38],"direct":[39],"thermal":[40],"cues":[41],"struggle":[42],"capture":[44],"indirect":[45],"yet":[46],"persistent":[47],"environmental":[48],"alterations":[49],"induced":[50],"by":[51],"sustained":[52],"heat":[53],"emissions.":[54],"This":[55],"work":[56],"introduces":[57],"a":[58,76],"physics-aware":[59,189],"representation":[60],"framework":[62],"leverages":[64],"multi-spectral":[65,209],"information":[66],"model":[68],"stable":[69],"signatures":[70],"of":[71,174],"long-term":[72],"processes.":[74],"Specifically,":[75],"geological":[77],"Short":[78],"Wave":[79],"Infrared":[80,92],"(SWIR)":[81],"ratio":[82,148],"sensitive":[83],"soil":[85],"property":[86],"changes":[87],"is":[88],"integrated":[89],"Thermal":[91],"(TIR)":[93],"data":[94],"through":[95],"an":[96],"intermediate":[97],"fusion":[98],"architecture,":[99],"instantiated":[100],"as":[101],"FusionNet.":[102],"The":[103],"proposed":[104],"backbone":[105],"embeds":[106],"trainable":[107],"differential":[108],"signal-processing":[109],"priors":[110],"within":[111],"convolutional":[112],"layers,":[113],"combines":[114],"mixed":[115],"pooling":[116],"strategies,":[117],"employs":[119],"wider":[120],"receptive":[121],"fields":[122],"enhance":[124],"robustness":[125],"across":[126,156],"spectral":[127,158],"modalities.":[128],"Systematic":[129],"ablations":[130],"show":[131,164],"each":[133],"architectural":[134],"component":[135],"contributes":[136],"gains,":[139],"DGCNN":[141],"achieving":[142],"88.7%":[143],"accuracy":[144],"SWIR":[147],"FusionNet":[150],"reaching":[151],"90.6%,":[152],"outperforming":[153],"state-of-the-art":[154],"baselines":[155],"five":[157],"configurations.":[159],"Transfer":[160],"experiments":[162],"further":[163],"ImageNet":[166],"pretraining":[167],"degrades":[168],"TIR":[169],"performance,":[170],"highlighting":[171],"importance":[173],"modality-aware":[175],"training":[176],"for":[177],"learning.":[179],"Evaluated":[180],"data,":[183],"results":[185],"demonstrate":[186],"combining":[188],"feature":[190],"selection":[191],"principled":[193],"architectures":[196],"yields":[197],"robust":[198],"generalisable":[200],"representations,":[201],"illustrating":[202],"how":[203],"first-principles":[204],"modelling":[206],"can":[207],"improve":[208],"challenging":[212]},"counts_by_year":[],"updated_date":"2025-12-24T23:14:05.333182","created_date":"2025-12-24T00:00:00"}