{"id":"W4206363618","doi":"10.1002/essoar.10510081.1","title":"Co-Production of a 10-m Cropland Extent Map for Continental Africa using Sentinel-2, Cloud Computing, and the Open-Data-Cube","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth","funders":"","keywords":"Geospatial analysis; Earth observation; Remote sensing; Geography; Scale (ratio); Land cover; Random forest; Cartography; Environmental science; Land use; Computer science; Physical geography; Satellite; Artificial intelligence","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":[0.0007463835,0.000605929,0.0002539936,0.002182876,0.0003125741,0.0009417034,0.0005512019,0.0003054273,0.005142787],"category_scores_gemma":[0.002226427,0.0002621353,0.0005938709,0.003346068,0.0001751495,0.001263614,0.0009561213,0.0005883185,0.003042709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005203712,"about_ca_system_score_gemma":0.001264523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02366561,"about_ca_topic_score_gemma":0.03021967,"domain_scores_codex":[0.999642,0.00003671071,0.00002622061,0.00007834517,0.0001717268,0.00004503204],"domain_scores_gemma":[0.9985816,0.0002038025,0.0001136029,0.0002858901,0.000698585,0.0001165669],"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":[0.0005476227,0.0003087848,0.07162956,0.0008980073,0.0003118525,0.001790377,0.001798594,0.109033,0.05146867,0.009449772,0.2451477,0.507616],"study_design_scores_gemma":[0.0001509098,0.000112456,0.131123,0.0004051947,0.0001233552,0.0005695858,0.002013074,0.2974983,0.06005064,0.008468633,0.4992327,0.0002522557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2146976,0.0006139713,0.3084189,0.002692035,0.0009627983,0.001251593,0.3629186,0.05121189,0.05723274],"genre_scores_gemma":[0.3498324,0.0005863686,0.4420777,0.0002013753,0.00008812614,0.0006021218,0.1958476,0.004337295,0.006427078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02366561,"threshold_uncertainty_score":0.04705572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04531442639573173,"score_gpt":0.2987866593162262,"score_spread":0.2534722329204945,"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."}}