{"id":"W4392588171","doi":"10.5194/egusphere-egu24-2092","title":"Identifying direct deforestation drivers in Cameroon using deep learning and optical satellite data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Oil Palm Production and Sustainability","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"International Institute for Sustainable Development","funders":"","keywords":"Deforestation (computer science); Satellite; Remote sensing; Geography; Computer science; Astronomy; Physics","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":[0.0004839746,0.0009780308,0.0002020275,0.001281773,0.0003335486,0.0005105949,0.0003117696,0.0003777213,0.001293361],"category_scores_gemma":[0.0008126128,0.0001439608,0.0003414778,0.0009050174,0.0002469525,0.0005244371,0.0004867876,0.0005649388,0.0003174661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287196,"about_ca_system_score_gemma":0.0008347955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1509219,"about_ca_topic_score_gemma":0.1574912,"domain_scores_codex":[0.999833,0.00003920565,0.000007514036,0.00004249342,0.00001931047,0.00005851996],"domain_scores_gemma":[0.9997706,0.0000673935,0.00003960733,0.0000196047,0.00006519356,0.0000376476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009821814,0.0004407252,0.6494334,0.0002444512,0.0001978814,0.001321606,0.0003012581,0.1283275,0.0108316,0.001169615,0.02133988,0.1854099],"study_design_scores_gemma":[0.00007836618,0.0001264438,0.3152421,0.0001935066,0.00009878264,0.0001708193,0.001193477,0.6669871,0.007508231,0.0007432008,0.007609698,0.00004832294],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883592,0.0009839515,0.002538239,0.0008235284,0.00008391887,0.00004144819,0.005041049,0.0003410442,0.001787566],"genre_scores_gemma":[0.9857455,0.0004682321,0.003841626,0.0001107331,0.00003042749,0.00002846429,0.008594885,0.00001648746,0.001163568],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1509219,"threshold_uncertainty_score":0.300087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0371388408596194,"score_gpt":0.3193415341100325,"score_spread":0.2822026932504131,"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."}}