{"id":"W2082081125","doi":"10.1016/j.rse.2011.11.020","title":"A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery","year":2011,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":973,"is_retracted":false,"has_abstract":false,"ca_institutions":"Total (Canada); Trent University; University of Saskatchewan","funders":"","keywords":"Support vector machine; Artificial intelligence; Land cover; Pixel; Computer science; Random forest; Decision tree; Statistical classification; Pattern recognition (psychology); Object (grammar); Contextual image classification; Machine learning; Algorithm; Image (mathematics); Land use","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002365367,0.0004943994,0.0005439674,0.001869619,0.0002927082,0.001140762,0.0006309776,0.0007543593,0.001398298],"category_scores_gemma":[0.003128491,0.0001800841,0.0005256197,0.001216416,0.0002910263,0.001259776,0.0003273249,0.0003020876,0.0004778807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004252385,"about_ca_system_score_gemma":0.000386669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00469502,"about_ca_topic_score_gemma":0.006644048,"domain_scores_codex":[0.9993047,0.0002234481,0.00005151765,0.0001001389,0.0002745597,0.00004576244],"domain_scores_gemma":[0.997559,0.001398275,0.00009858391,0.0001079021,0.0007907273,0.00004558071],"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":[0.005871685,0.0007710534,0.05387056,0.000630556,0.0009868931,0.0001820631,0.0002873913,0.04917061,0.1020243,0.001399062,0.003174345,0.7816315],"study_design_scores_gemma":[0.0001572608,0.0008081697,0.1255817,0.00003236896,0.0005052451,0.0002449967,0.0002990255,0.8348054,0.03443818,0.0009561505,0.002103461,0.00006808214],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8189996,0.001818506,0.1725872,0.0002626894,0.0001289733,0.000126646,0.0006122728,0.00123028,0.004233851],"genre_scores_gemma":[0.8780985,0.0005750661,0.1183204,0.0001077129,0.0000485559,0.00005883973,0.0008778384,0.0001882602,0.001724877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00469502,"threshold_uncertainty_score":0.01250941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02497637550135123,"score_gpt":0.2432161822838509,"score_spread":0.2182398067824997,"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."}}