{"id":"W2956786564","doi":"10.1007/s00521-019-04349-9","title":"A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery","year":2019,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":101,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Computer science; Land cover; Deep learning; Artificial intelligence; Satellite imagery; Context (archaeology); Satellite; Remote sensing; Pixel; Pattern recognition (psychology); Field (mathematics); Contextual image classification; Convolutional neural network; Scale (ratio); Land use; Image (mathematics); Cartography; Geography; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001060284,0.0001445017,0.0002125547,0.0001450986,0.0002113868,0.0002088027,0.00005422121,0.00007736863,0.000001919822],"category_scores_gemma":[0.00003592437,0.0001528187,0.00006672793,0.0003944746,0.00003287592,0.0001175878,0.00002908109,0.0002290418,0.00000605186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000296491,"about_ca_system_score_gemma":0.000003640882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000156418,"about_ca_topic_score_gemma":0.000001959677,"domain_scores_codex":[0.9991665,0.00002429011,0.0002122305,0.0002975802,0.00007284215,0.0002264816],"domain_scores_gemma":[0.9992056,0.0004314268,0.0000712356,0.0001858658,0.00004558155,0.00006021414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007826923,0.00001409713,0.1973219,0.0001719503,0.0001832714,8.112834e-7,0.0005366124,0.6641498,0.02705503,0.0002288449,0.000005920115,0.1103239],"study_design_scores_gemma":[0.0001313474,0.000006651364,0.07793391,0.00002622636,0.00008786942,0.000008800399,0.00003282066,0.9205688,0.0001697548,0.00009273289,0.0007816321,0.0001594688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4948622,0.0002256226,0.5044544,0.00002096014,0.00002980604,0.0002097454,0.000002133141,0.0001569052,0.00003815895],"genre_scores_gemma":[0.9082605,0.00005480805,0.09144955,0.00002883337,0.0001105041,0.00000548765,0.00003456766,0.00002878489,0.00002693069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4133983,"threshold_uncertainty_score":0.6231765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02146645467919889,"score_gpt":0.2638803138753766,"score_spread":0.2424138591961777,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}