{"id":"W4411698206","doi":"10.1016/j.compag.2025.110670","title":"Generating crop type labels from historical annual crop inventory data with an ensemble learning method","year":2025,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Crop; Ensemble learning; Agricultural engineering; Type (biology); Artificial intelligence; Computer science; Mathematics; Machine learning; Geography; Engineering; Forestry; Ecology; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002656652,0.0002437587,0.0002670964,0.00003217281,0.000244838,0.0001137808,0.0004607306,0.000190403,0.00001595386],"category_scores_gemma":[0.00003331792,0.0001573664,0.00002113662,0.0005796847,0.0000476492,0.0002967719,0.000436882,0.0007327985,0.000007282885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007239688,"about_ca_system_score_gemma":0.00003525822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001136713,"about_ca_topic_score_gemma":0.002158668,"domain_scores_codex":[0.99817,0.0002194364,0.0002158118,0.0007553824,0.0002309119,0.0004084639],"domain_scores_gemma":[0.9993455,0.00006848689,0.00009204233,0.0003625674,0.00002991687,0.0001014646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000178705,0.0004464824,0.01868474,0.00004271943,0.000181475,0.0001317294,0.005084095,0.2607865,0.1565042,0.0004891884,0.4107521,0.146718],"study_design_scores_gemma":[0.001273763,0.000756644,0.01771264,0.0001946014,0.0001097328,0.0000899946,0.0004090878,0.2545383,0.001484031,0.0006217466,0.7217818,0.001027637],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9692212,0.004003227,0.02344976,0.0008233115,0.0004645343,0.0002834488,0.000007754075,0.0001347987,0.001611948],"genre_scores_gemma":[0.4731208,0.0009405595,0.5068009,0.002548434,0.0009287483,0.000006268932,0.001153369,0.00007321343,0.01442767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4961004,"threshold_uncertainty_score":0.6417216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01123822061531646,"score_gpt":0.2447275864635457,"score_spread":0.2334893658482292,"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."}}