{"id":"W3015176885","doi":"10.3808/jeil.202000023","title":"Multi-Layer Perceptron Neural Network and Markov Chain Based Geospatial Analysis of Land Use and Land Cover Change","year":2020,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Ministry of Forests; University of Northern British Columbia","funders":"","keywords":"Thematic Mapper; Land cover; Land use; Watershed; Environmental science; Artificial neural network; Remote sensing; Geospatial analysis; Multilayer perceptron; Agricultural land; Markov chain; Change analysis; Computer science; Geography; Satellite imagery; Artificial intelligence; Physical geography; Machine learning; 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":[0.0001986886,0.0001483396,0.0003408697,0.00005928964,0.00006288756,0.00005295621,0.0001150531,0.00005028668,0.0004557362],"category_scores_gemma":[0.000005833012,0.0001108566,0.00009630748,0.0001235772,0.00005228291,0.0008156662,0.0001271853,0.00012792,0.00000855542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000412053,"about_ca_system_score_gemma":0.000001597031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072751,"about_ca_topic_score_gemma":0.00009278152,"domain_scores_codex":[0.9988788,0.00004442429,0.0005089089,0.00008448811,0.0002945875,0.0001888109],"domain_scores_gemma":[0.9992305,0.00005724679,0.0004461811,0.00009117941,0.000002065356,0.0001727944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008206091,0.00002941421,0.9370755,0.00003761397,0.0001547524,0.000008164078,0.001879227,0.05808975,0.002048941,3.151154e-8,0.0001592229,0.0004353291],"study_design_scores_gemma":[0.0006793282,0.0001022773,0.6310998,0.00001302345,0.0002483622,0.000007123489,0.00008670883,0.3673405,0.00002664872,1.159157e-7,0.0003010317,0.00009511292],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987534,0.00005298251,0.0003863118,0.000573879,0.00004405039,0.0001184462,0.00006031349,0.000003199593,0.000007441035],"genre_scores_gemma":[0.9926748,0.0001157348,0.002318333,0.004789988,0.00007279473,0.00000144647,0.00001719192,0.000008294208,0.000001390172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3092508,"threshold_uncertainty_score":0.4989991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02067577469173217,"score_gpt":0.203026627048819,"score_spread":0.1823508523570868,"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."}}