{"id":"W4407722895","doi":"10.1080/07038992.2024.2439835","title":"Urban green space extraction from BJ-2 remote sensing image based SegFormer semantic segmentation model","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"State Key Laboratory of Remote Sensing Science","keywords":"Segmentation; Geography; Space (punctuation); Artificial intelligence; Urban green space; Extraction (chemistry); Image (mathematics); Computer science; Image segmentation; Computer vision; Cartography; Remote sensing; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003497658,0.0001801309,0.0002494693,0.0002192949,0.0003105583,0.0001390753,0.0001229244,0.0001067991,0.0000892404],"category_scores_gemma":[0.00003308972,0.0001680039,0.0001113853,0.0002923587,0.00003060365,0.0005062061,0.00001738875,0.0002461965,0.000053558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006519515,"about_ca_system_score_gemma":0.0002751448,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1768538,"about_ca_topic_score_gemma":0.3075665,"domain_scores_codex":[0.9986688,0.00008247553,0.0004123782,0.0002245023,0.0002462042,0.0003656252],"domain_scores_gemma":[0.9990001,0.00005600579,0.0003168793,0.000218958,0.00005796295,0.0003500636],"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":[0.00008791815,0.000007420998,0.002370408,0.0001057821,0.0001281038,0.000852122,0.001990825,0.02538271,0.103523,0.00000151429,0.005238456,0.8603117],"study_design_scores_gemma":[0.0004352078,0.00001870023,0.001450962,0.0004644284,0.0001091786,0.00009576861,0.0003385812,0.9831752,0.01084476,0.0006609062,0.002218538,0.0001877803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6678756,0.00007341171,0.3277363,0.001583034,0.0004095495,0.000100622,0.000006846531,0.00001172917,0.002202871],"genre_scores_gemma":[0.8313813,0.000009578721,0.1675408,0.0007005271,0.0001373822,2.659139e-9,0.000009259913,0.00002004801,0.0002010685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9577925,"threshold_uncertainty_score":0.8286276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0103083506437616,"score_gpt":0.2240165272469636,"score_spread":0.213708176603202,"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."}}