{"id":"W2132099602","doi":"10.1080/01431160902755346","title":"The impact of imperfect ground reference data on the accuracy of land cover change estimation","year":2009,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Forest Service","keywords":"Change detection; Land cover; Ground truth; Reference data; Data set; Remote sensing; Computer science; Estimation; Cover (algebra); Set (abstract data type); Environmental science; Land use; Statistics; Data mining; Mathematics; Geography; Artificial intelligence; Ecology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0340075,0.0007683925,0.0009566206,0.00161228,0.0009022244,0.00206631,0.001111116,0.001149671,0.0008995476],"category_scores_gemma":[0.2215779,0.0006954753,0.00067121,0.003292735,0.002205911,0.002300238,0.001834357,0.0007986549,0.0004927698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002445935,"about_ca_system_score_gemma":0.001103852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03315834,"about_ca_topic_score_gemma":0.02158197,"domain_scores_codex":[0.9607012,0.02091406,0.002966589,0.003450773,0.01076302,0.001204206],"domain_scores_gemma":[0.7543334,0.1919125,0.01431924,0.02076595,0.01820707,0.0004617378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001513921,0.0001471484,0.5161225,0.001301371,0.000800014,0.0006363522,0.001975904,0.2611074,0.01191058,0.007122781,0.002648794,0.1947133],"study_design_scores_gemma":[0.0001022386,0.0006987234,0.7660467,0.0004911636,0.0004755981,0.001353457,0.001178742,0.1657632,0.0389092,0.01149101,0.01322093,0.000269111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7800555,0.006914632,0.1919948,0.00230979,0.0003414783,0.0003118397,0.00295998,0.0007674895,0.0143445],"genre_scores_gemma":[0.9745286,0.0005709809,0.02301813,0.0002326558,0.00003542093,0.00005108304,0.0009593794,0.00009571259,0.0005080309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0340075,"threshold_uncertainty_score":0.179851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04958561424397102,"score_gpt":0.3291342431927547,"score_spread":0.2795486289487837,"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."}}