{"id":"W3217586766","doi":"10.3390/s21238083","title":"Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Contextual image classification; Land cover; Remote sensing; Residual; Pattern recognition (psychology); Machine learning; Clipping (morphology); Artificial neural network; Land use; Image (mathematics); Geography; Algorithm; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002432704,0.0009830615,0.0007233025,0.001683283,0.0003053609,0.0007737188,0.0009358886,0.0009380226,0.001892975],"category_scores_gemma":[0.003136906,0.0001650401,0.0006071606,0.001545181,0.0003706414,0.001662381,0.0008541486,0.0008148169,0.0007194226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009817072,"about_ca_system_score_gemma":0.0006697729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01179151,"about_ca_topic_score_gemma":0.007104295,"domain_scores_codex":[0.9992241,0.0002094388,0.00004970833,0.0001526776,0.0002541451,0.0001099344],"domain_scores_gemma":[0.998863,0.0005210164,0.00006291343,0.000156824,0.0003302816,0.00006597504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001095189,0.000819441,0.01810538,0.0005463271,0.0004436282,0.0001705663,0.0001219591,0.2383061,0.004934061,0.002050141,0.008392648,0.7250146],"study_design_scores_gemma":[0.00003141776,0.000301203,0.01206979,0.00003629792,0.00008360166,0.00006279678,0.0001297317,0.9783277,0.004634641,0.001491967,0.002808588,0.0000222561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8346177,0.01841429,0.1219685,0.001101761,0.0004596817,0.0002500947,0.001617221,0.002855753,0.0187151],"genre_scores_gemma":[0.9676737,0.001778735,0.02373264,0.0001015143,0.00008020184,0.00005993621,0.002446235,0.00009216643,0.004035083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01179151,"threshold_uncertainty_score":0.02344573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06235099648868551,"score_gpt":0.2757454833334606,"score_spread":0.2133944868447751,"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."}}