{"id":"W4407998460","doi":"10.1017/eds.2024.53","title":"OpenForest: a data catalog for machine learning in forest monitoring","year":2025,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Computer science; Data science; Forestry; Artificial intelligence; Machine learning; Geography","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":[0.001080246,0.0001391613,0.0001228533,0.00008459633,0.0005111798,0.0001095754,0.003274333,0.00003710606,0.00005617109],"category_scores_gemma":[0.000192375,0.0001353334,0.00001403537,0.0005356279,0.0008038715,0.001486562,0.004857577,0.000183133,0.0001740397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002653693,"about_ca_system_score_gemma":0.00003681404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001521218,"about_ca_topic_score_gemma":0.0008008701,"domain_scores_codex":[0.9979575,0.0000222113,0.0002351096,0.001035758,0.0003432552,0.0004062046],"domain_scores_gemma":[0.9976479,0.00009476161,0.00006277983,0.002102673,0.0000011197,0.00009070189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002000698,0.0001725155,0.864271,0.000009270905,0.000005499972,0.000004386287,0.0001774068,0.005368114,0.04039706,0.000178582,0.001624449,0.0877717],"study_design_scores_gemma":[0.0004349313,0.00002783148,0.6222515,0.00003242747,0.00001384611,0.000006996486,0.0002088839,0.2559857,0.001767545,0.0002661103,0.1187619,0.0002422615],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9717398,0.0002690212,0.01274085,0.0009205618,0.0004214277,0.001291231,0.001337245,0.00009768471,0.01118223],"genre_scores_gemma":[0.9854185,0.00007281638,0.01209309,0.00006959161,0.00002519859,0.000009650813,0.00145054,0.00001041013,0.0008502271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2506176,"threshold_uncertainty_score":0.6084581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03437498071578052,"score_gpt":0.3017214673339243,"score_spread":0.2673464866181438,"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."}}