{"id":"W4402825119","doi":"10.1007/s40003-024-00785-9","title":"The Comparison of Machine Learning Techniques for Agricultural Land Use Classifications in the Prairies: A Case Study in Saskatchewan, Canada","year":2024,"lang":"en","type":"article","venue":"Agricultural Research","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Ministry of Agriculture - Saskatchewan","keywords":"Agriculture; Plant ecology; Plant biochemistry; Geography; Land use; Biodiversity; Agroforestry; Environmental resource management; Forestry; Ecology; Environmental science; Archaeology; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001643281,0.0001673061,0.0001908894,0.00004468855,0.0005555148,0.0003133183,0.0004674321,0.00007674617,0.000005914466],"category_scores_gemma":[0.000535556,0.00006172474,0.00005389512,0.001648838,0.0002174793,0.0002245537,0.0001696372,0.001008478,0.000004741756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005858985,"about_ca_system_score_gemma":0.00008776646,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7542788,"about_ca_topic_score_gemma":0.9954202,"domain_scores_codex":[0.9971247,0.000744109,0.0004142106,0.0003635803,0.0008776247,0.0004757923],"domain_scores_gemma":[0.9967289,0.002828285,0.00006471868,0.0002283847,0.00009369529,0.0000560172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000993893,0.001017356,0.6928262,0.0001274248,0.0001059337,0.001077008,0.09633767,0.003047743,0.03770861,0.0002717566,0.1310118,0.03636913],"study_design_scores_gemma":[0.0001789782,0.0002657183,0.6613341,0.00007190563,0.0000130033,0.0003016442,0.3123896,0.001647301,0.000918284,0.00002502253,0.02267332,0.0001811208],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938848,0.0002225953,0.000004583208,0.003494732,0.00005401332,0.001895151,0.00001339739,0.00003106354,0.0003996699],"genre_scores_gemma":[0.9974914,0.00001580374,0.0001879504,0.0000113151,0.00004697605,0.0001168148,0.00002785003,0.000007433762,0.002094485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2411414,"threshold_uncertainty_score":0.4381392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07093418443491921,"score_gpt":0.3664766643970378,"score_spread":0.2955424799621186,"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."}}