{"id":"W2051440202","doi":"10.1080/01431161.2014.978035","title":"Land-use and land-cover classification in semi-arid regions using independent component analysis (ICA) and expert classification","year":2014,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Land cover; Thematic Mapper; Thematic map; Watershed; Remote sensing; Cohen's kappa; Vegetation (pathology); Land use; Arid; Arable land; Preprocessor; Environmental science; Cartography; Geography; Computer science; Satellite imagery; Artificial intelligence; Statistics; Mathematics; Geology; Agriculture","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":[0.0009790605,0.0004059774,0.0002896655,0.001886435,0.0002980789,0.0006658498,0.0003084865,0.0002812149,0.0006810452],"category_scores_gemma":[0.001706053,0.0001210316,0.0003589135,0.001071766,0.0002779075,0.0005546504,0.0003430129,0.0002605099,0.0002447853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004016696,"about_ca_system_score_gemma":0.0005828414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009520696,"about_ca_topic_score_gemma":0.01549749,"domain_scores_codex":[0.9994808,0.0001876861,0.0000363335,0.0001136156,0.000133192,0.00004841878],"domain_scores_gemma":[0.9995584,0.0001656198,0.00004036847,0.00004130919,0.0001732944,0.00002098351],"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":[0.0001874286,0.0003253238,0.0634846,0.0001621643,0.0001647017,0.0001730153,0.0004635636,0.05403109,0.01814172,0.003214662,0.00257723,0.8570745],"study_design_scores_gemma":[0.00001955935,0.00008533401,0.1256452,0.00002855806,0.00006727038,0.0001149085,0.0004714945,0.8585383,0.009099646,0.003236318,0.002638535,0.0000548317],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4797978,0.0002904719,0.513435,0.0001420134,0.00005252619,0.0002376845,0.0003368513,0.0009132306,0.004794415],"genre_scores_gemma":[0.7798248,0.0001468364,0.2181482,0.00003197099,0.00002387769,0.0001083607,0.0005194318,0.00003694178,0.001159606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009520696,"threshold_uncertainty_score":0.01893061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04407450553201075,"score_gpt":0.279244702526776,"score_spread":0.2351701969947652,"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."}}