{"id":"W4413306939","doi":"10.1080/07038992.2025.2532528","title":"Self-Supervised Deep Learning for Urban Land Cover Classification from Very High Resolution Imagery","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada; Institut National de la Recherche Scientifique","funders":"","keywords":"Land cover; Geography; Satellite imagery; Remote sensing; Aerial imagery; Cartography; Cover (algebra); High resolution; Deep learning; Land use; Artificial intelligence; Physical geography; Computer science; Ecology; Engineering; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.0006177491,0.0005841901,0.0004156627,0.0006239586,0.0002517973,0.0005275581,0.001049961,0.0006320631,0.001423114],"category_scores_gemma":[0.001060173,0.0003056868,0.0006291176,0.0006679763,0.0004225308,0.0009674412,0.0006823689,0.001159306,0.0005602153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007339214,"about_ca_system_score_gemma":0.000821376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009934988,"about_ca_topic_score_gemma":0.02024547,"domain_scores_codex":[0.9997315,0.00004684904,0.00001195346,0.00008484399,0.00006098693,0.00006389761],"domain_scores_gemma":[0.9996489,0.0001048975,0.00003982715,0.00007652478,0.0001085685,0.0000212468],"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":[0.00030038,0.000434657,0.005818046,0.0001424061,0.0001497646,0.0001938164,0.0001792685,0.4803685,0.02947882,0.002442556,0.008281371,0.4722104],"study_design_scores_gemma":[0.000004042347,0.00001691352,0.0008810994,0.000003840775,0.000005431288,0.00001168249,0.00001954953,0.9936372,0.004226029,0.0008393353,0.000350319,0.000004520432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3535856,0.0007142971,0.63111,0.0005479344,0.00009294274,0.0001378492,0.001266911,0.007573066,0.004971436],"genre_scores_gemma":[0.823292,0.0002071934,0.1680451,0.0002124121,0.00003223593,0.00009373717,0.003606822,0.0001501619,0.004360344],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009934988,"threshold_uncertainty_score":0.01975435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0125221850229363,"score_gpt":0.2083055235858787,"score_spread":0.1957833385629424,"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."}}