{"id":"W3044295292","doi":"10.1080/13658816.2020.1796131","title":"Land cover harmonization using Latent Dirichlet Allocation","year":2020,"lang":"en","type":"article","venue":"International Journal of Geographical Information Systems","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Natural Resources Canada; Agriculture and Agri-Food Canada; Canadian Forest Service","funders":"Canadian Space Agency; Natural Environment Research Council; Sight Research UK","keywords":"Harmonization; Latent Dirichlet allocation; Land cover; Benchmark (surveying); Cover (algebra); Class (philosophy); Data mining; Computer science; Dirichlet distribution; Geography; Artificial intelligence; Topic model; Land use; Mathematics; Cartography; Ecology; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002646696,0.0001011732,0.0001403793,0.00009970245,0.0000492084,0.0002237009,0.0002872095,0.0000850155,0.0001049056],"category_scores_gemma":[0.0001308168,0.00007587752,0.00009516683,0.0003438698,0.00004960458,0.001535446,0.00006809609,0.0001750196,0.0001886741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267925,"about_ca_system_score_gemma":0.00001469778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009382602,"about_ca_topic_score_gemma":0.000001219582,"domain_scores_codex":[0.99809,0.00005748023,0.0006928376,0.00007395796,0.0009816332,0.0001040439],"domain_scores_gemma":[0.9988011,0.00002891527,0.0006526433,0.00005913908,0.0003242475,0.0001339465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001366351,0.00005417301,0.2332164,0.00002007337,0.000173901,0.00001556188,0.001167009,0.7478389,0.005349799,0.0002978602,0.008305117,0.003424541],"study_design_scores_gemma":[0.001841242,0.000211766,0.1613235,0.0001787658,0.00007358129,0.0007605228,0.0002725858,0.6664248,0.0007917364,0.0000879775,0.1676065,0.0004269432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8494375,0.00006886516,0.1396111,0.005634209,0.002256732,0.0002965362,0.00001955698,0.00005050583,0.002625018],"genre_scores_gemma":[0.9976537,0.00003672108,0.001052038,0.0009122984,0.0003006303,3.638016e-7,0.00002889152,0.000004846853,0.00001053523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1593014,"threshold_uncertainty_score":0.3094195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01497938368627917,"score_gpt":0.2283728486471961,"score_spread":0.2133934649609169,"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."}}