{"id":"W3203611529","doi":"10.14288/1.0402360","title":"Detailed land cover mapping in a seasonally dry tropical forest landscape using multiple sensor types","year":2021,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Land cover; Cover (algebra); Tropical and subtropical dry broadleaf forests; Tropical forest; Forest cover; Geography; Remote sensing; Environmental science; Dry land; Tropics; Forestry; Land use; Ecology; Biology; Agronomy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.000290603,0.0002985086,0.0001772084,0.0009334236,0.0001866175,0.0005521814,0.0002288012,0.0002026727,0.0008949434],"category_scores_gemma":[0.0003402306,0.000179622,0.0002780114,0.001153037,0.0001237465,0.0007464507,0.0004278914,0.0002175867,0.0002847022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000219929,"about_ca_system_score_gemma":0.0001853374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005509651,"about_ca_topic_score_gemma":0.01845361,"domain_scores_codex":[0.9998398,0.00002261238,0.000008007772,0.00004746143,0.00004174021,0.000040454],"domain_scores_gemma":[0.9998674,0.00002258441,0.00003643077,0.00002078582,0.00003938689,0.00001339072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00025794,0.000230918,0.5159957,0.0003561263,0.0002819019,0.0007212218,0.001233906,0.02624309,0.1003943,0.00123326,0.004205538,0.348846],"study_design_scores_gemma":[0.00001832256,0.0001669113,0.88198,0.0001077186,0.000109707,0.0004691883,0.002092745,0.09482883,0.01110044,0.001278403,0.007788234,0.00005950248],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811487,0.0003842176,0.01159361,0.0001309182,0.00002792094,0.00005204056,0.002086119,0.0001978326,0.004378618],"genre_scores_gemma":[0.97219,0.0003233436,0.02465516,0.00005922119,0.00001928376,0.00003581931,0.001774746,0.00001704638,0.0009255443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005509651,"threshold_uncertainty_score":0.01095515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01187652550259999,"score_gpt":0.1633173086014187,"score_spread":0.1514407830988188,"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."}}