{"id":"W2152334070","doi":"10.1080/01431160903571791","title":"Comparison of pixel- and object-based classification in land cover change mapping","year":2011,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":230,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Vlaamse regering","keywords":"Thematic Mapper; Thematic map; Land cover; Change detection; Cartography; Remote sensing; Pixel; Object (grammar); Land use; Geography; Computer science; Data mining; Artificial intelligence; Satellite imagery; Ecology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002251902,0.00004880388,0.0001215064,0.00009206652,0.00001422235,0.00001239244,0.00009192078,0.00003019944,0.00005433707],"category_scores_gemma":[0.00001408343,0.0000396468,0.00002615045,0.00006017832,0.0000134319,0.0001771256,0.00002837915,0.00006748827,0.000008186224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005891596,"about_ca_system_score_gemma":0.000006330688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007406776,"about_ca_topic_score_gemma":0.0005652542,"domain_scores_codex":[0.9993308,0.0000288998,0.0002884931,0.00006565397,0.0002219395,0.00006423475],"domain_scores_gemma":[0.9995465,0.00002833229,0.0003170955,0.0000446586,0.00003485848,0.00002858485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001187396,0.00005190414,0.8791658,0.00001960267,0.00002844469,0.00002978904,0.003731142,0.0002700129,0.01267393,0.000003589109,0.00002139328,0.1038856],"study_design_scores_gemma":[0.0006325651,0.00005636507,0.7618076,0.0003358581,0.000009460869,0.00006298078,0.0002852704,0.2309463,0.004631076,0.0001680485,0.0009851491,0.00007932717],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99555,0.00005246435,0.002696683,0.0001574607,0.0002073608,0.00003563057,9.277628e-7,0.000002232105,0.001297257],"genre_scores_gemma":[0.9935783,0.00001992932,0.006258378,0.00007701937,0.00005920678,1.288711e-8,0.00000102092,0.000003648591,0.000002461297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2306762,"threshold_uncertainty_score":0.161675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0803817342266771,"score_gpt":0.2913954218955067,"score_spread":0.2110136876688296,"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."}}