{"id":"W4387676577","doi":"10.1080/07038992.2023.2259504","title":"Object-Based Image Analysis (OBIA) and Machine Learning (ML) Applied to Tropical Forest Mapping Using Sentinel-2","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universidade Federal do Paraná","keywords":"Land cover; Random forest; Scale (ratio); Remote sensing; Geography; Object based; Vegetation (pathology); Pixel; Contextual image classification; Computer science; Artificial intelligence; Land use; Cartography; Image (mathematics); Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005700214,0.0005112523,0.0002589918,0.001224664,0.000212465,0.0005188109,0.00039568,0.0002644733,0.001191699],"category_scores_gemma":[0.0008303358,0.0001877328,0.0005115136,0.0009751641,0.0002019929,0.0005004746,0.0005135209,0.0002419238,0.0004695012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003565868,"about_ca_system_score_gemma":0.0006424102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03210636,"about_ca_topic_score_gemma":0.03623138,"domain_scores_codex":[0.9997509,0.00003948557,0.00001742678,0.00006780799,0.00008209957,0.00004224391],"domain_scores_gemma":[0.9997852,0.00004347242,0.00002260772,0.00005960034,0.00007243934,0.00001660566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005542716,0.0006638687,0.1249628,0.0008390334,0.0003193096,0.0005770223,0.0007206065,0.1029524,0.07107641,0.003031335,0.01108776,0.6832151],"study_design_scores_gemma":[0.00007274916,0.0002515905,0.1643381,0.0001312529,0.000174405,0.0005483155,0.0007204743,0.7623321,0.05250605,0.002940683,0.0158904,0.00009381923],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8403571,0.0006124175,0.1340177,0.0002355945,0.0001251396,0.0005014247,0.01053613,0.004884562,0.008730075],"genre_scores_gemma":[0.8135386,0.0003582793,0.173154,0.00007597953,0.00002616032,0.0002336864,0.01044247,0.0001950113,0.001975803],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03210636,"threshold_uncertainty_score":0.06383896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01514757598592054,"score_gpt":0.2131841736463694,"score_spread":0.1980365976604488,"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."}}