{"id":"W2604308675","doi":"10.1016/j.isprsjprs.2017.03.019","title":"Using spectrotemporal indices to improve the fruit-tree crop classification accuracy","year":2017,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Geological Survey","keywords":"Linear discriminant analysis; Feature (linguistics); Context (archaeology); Pattern recognition (psychology); Artificial intelligence; Computer science; Tree (set theory); Mathematics; Random forest; Statistics; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008952619,0.0002242938,0.0002835198,0.00008266632,0.001122511,0.000605288,0.0004583828,0.000136345,0.00001401213],"category_scores_gemma":[0.0005975306,0.0001330348,0.000144534,0.0002154697,0.0003966076,0.0004451461,0.0002420778,0.0005558565,0.00001337266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001527016,"about_ca_system_score_gemma":0.00002581909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002852292,"about_ca_topic_score_gemma":0.0006683852,"domain_scores_codex":[0.9982532,0.0001287335,0.0004643532,0.0002857531,0.0005072875,0.0003606502],"domain_scores_gemma":[0.9979594,0.0001212538,0.001115181,0.0005127211,0.00006603874,0.0002254416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004589518,0.00001258655,0.0009000851,0.000005741575,0.00002673154,0.00005930539,0.0004863387,0.00009964873,0.479289,0.000002218123,0.0002079661,0.5188645],"study_design_scores_gemma":[0.002591245,0.0008383135,0.4226212,0.001006307,0.0005199147,0.007503402,0.004292398,0.1546218,0.3625103,0.004422572,0.03746075,0.001611829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760699,0.00008611033,0.01820349,0.001737945,0.0007663022,0.0002711486,0.000001213039,0.00001327718,0.002850632],"genre_scores_gemma":[0.9448751,0.00004833563,0.05422067,0.0002908789,0.0004650648,7.58953e-9,4.224883e-7,0.0000184551,0.0000810581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5172527,"threshold_uncertainty_score":0.8633557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03343954117160347,"score_gpt":0.3020362080005523,"score_spread":0.2685966668289488,"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."}}