{"id":"W4376137947","doi":"10.3390/su15107854","title":"A Comparison of Deep Transfer Learning Methods for Land Use and Land Cover Classification","year":2023,"lang":"en","type":"article","venue":"Sustainability","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transfer of learning; Pace; Artificial intelligence; Deep learning; Land cover; Computer science; Machine learning; Class (philosophy); Test set; Land use; Set (abstract data type); Geography; Engineering; Civil engineering","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":[0.000737279,0.000103105,0.0002198794,0.00009459198,0.00006492515,0.00004326503,0.00004812654,0.00009204416,0.000003168032],"category_scores_gemma":[0.001608563,0.0001044742,0.0000461052,0.0002600351,0.00008187359,0.0001620746,0.0000116814,0.0001298159,0.000001620834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001697544,"about_ca_system_score_gemma":0.00002910081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248607,"about_ca_topic_score_gemma":0.00001277894,"domain_scores_codex":[0.9991289,0.0001428165,0.000264539,0.0001972935,0.0000760768,0.0001903236],"domain_scores_gemma":[0.9986772,0.0006940762,0.00002741435,0.0002163379,0.0003411988,0.00004380355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000113374,0.00005629162,0.677344,0.001983168,0.000055147,7.763442e-7,0.003718967,0.1076283,0.03406375,0.0004624253,0.0001486383,0.1744251],"study_design_scores_gemma":[0.000232478,0.00002909439,0.3374273,0.000005604656,0.00002075962,4.471835e-7,0.0003178178,0.6555143,0.002931843,0.0007300721,0.002706488,0.00008375931],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6316774,0.00004996467,0.3675231,0.0001205854,0.00004701392,0.0003557087,0.000003080494,0.0001860435,0.0000370534],"genre_scores_gemma":[0.9916078,0.0000144985,0.00819147,0.000002405525,0.00001681642,0.00001915179,0.00003739742,0.00002491647,0.00008548117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.547886,"threshold_uncertainty_score":0.4260334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05583714975142652,"score_gpt":0.3742336261795202,"score_spread":0.3183964764280937,"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."}}