{"id":"W2774571784","doi":"10.1109/jstars.2017.2774807","title":"Image Classification Using RapidEye Data: Integration of Spectral and Textual Features in a Random Forest Classifier","year":2017,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"China Scholarship Council; Agriculture and Agri-Food Canada; National Natural Science Foundation of China","keywords":"Multispectral image; Random forest; Remote sensing; Principal component analysis; Red edge; Contextual image classification; Linear discriminant analysis; Spectral bands; Normalized Difference Vegetation Index; Pattern recognition (psychology); Artificial intelligence; Multispectral pattern recognition; Reflectivity; Classifier (UML); Support vector machine; Statistical classification; Computer science; Mathematics; Geology; Hyperspectral imaging","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":[0.0005454707,0.0001342941,0.0002824988,0.0001138631,0.0001903955,0.0001298844,0.0001683563,0.0001358868,0.000001892017],"category_scores_gemma":[0.0002853053,0.0001058607,0.00002330958,0.0002599,0.00023913,0.0003953726,0.00006402875,0.0004316204,2.052267e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007791255,"about_ca_system_score_gemma":0.0000522985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006968102,"about_ca_topic_score_gemma":0.008221406,"domain_scores_codex":[0.9987755,0.00006281539,0.0005131199,0.0002195336,0.0002597199,0.000169278],"domain_scores_gemma":[0.9989044,0.00007980159,0.0005828964,0.0002965465,0.00008564768,0.00005071557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001165492,0.00003338897,0.008992312,0.00001982085,0.00001794402,0.00001732516,0.0005815274,0.001330808,0.8577997,0.0001032794,0.0001234659,0.1308639],"study_design_scores_gemma":[0.001064075,0.00002937409,0.8021777,0.0001625125,0.00002412608,0.0001089893,0.0002449373,0.1914543,0.003772479,0.0007050275,0.0001394651,0.0001170114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9876408,0.00003778215,0.01060938,0.0004859928,0.0001184529,0.0001960981,0.000003714332,0.000004486599,0.0009033178],"genre_scores_gemma":[0.8228952,0.0001599903,0.176744,0.00002146511,0.0001326123,1.36967e-8,0.000006963136,0.00000771207,0.00003203051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8540272,"threshold_uncertainty_score":0.4587737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04892699195225098,"score_gpt":0.2748302703267093,"score_spread":0.2259032783744583,"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."}}