{"id":"W4308570689","doi":"10.1016/j.isprsjprs.2022.10.017","title":"In-season crop type identification using optimal feature knowledge graph","year":2022,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Identification (biology); Thresholding; Crop; Ground truth; Crop yield; Graph; Feature (linguistics); Computer science; Growing season; Segmentation; Mathematics; Pattern recognition (psychology); Artificial intelligence; Remote sensing; Geography; Agronomy; Ecology","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":[0.0008481292,0.0001824374,0.0002657171,0.0002206301,0.0003788561,0.0000884261,0.0001683576,0.0001005533,0.00005449087],"category_scores_gemma":[0.00008657461,0.000153714,0.0001188182,0.001363918,0.0001473016,0.0002338052,0.0001890224,0.0007963512,0.000005123082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003087377,"about_ca_system_score_gemma":0.00002814526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004735978,"about_ca_topic_score_gemma":0.0001014719,"domain_scores_codex":[0.9983335,0.0002680426,0.0003976944,0.000264094,0.0004327453,0.000303913],"domain_scores_gemma":[0.9991783,0.00005873822,0.0004046843,0.0001670129,0.00005734984,0.0001338588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001970878,0.0001084067,0.0008063503,0.00002462153,0.00004414934,0.0005014163,0.002132382,0.02429016,0.7346905,0.000002463021,0.002589828,0.2346126],"study_design_scores_gemma":[0.004639019,0.001298372,0.05374594,0.0007233591,0.0005413718,0.04282735,0.009253486,0.6383014,0.1196276,0.00233055,0.1243513,0.002360344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921149,0.0008571966,0.004982126,0.0002272258,0.001196741,0.000135075,0.000001270815,0.00001188448,0.000473598],"genre_scores_gemma":[0.9708124,0.00008823248,0.02851156,0.0001259285,0.0001539194,6.91891e-9,0.000001971589,0.00002099777,0.0002850032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.615063,"threshold_uncertainty_score":0.6268274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01264819266975658,"score_gpt":0.2593396880408614,"score_spread":0.2466914953711048,"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."}}