{"id":"W3201715788","doi":"10.3390/w13192622","title":"Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques","year":2021,"lang":"en","type":"article","venue":"Water","topic":"Groundwater and Watershed Analysis","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; McGill University","funders":"University of Tabriz","keywords":"Multiple-criteria decision analysis; Hazard; Computer science; Vulnerability (computing); Receiver operating characteristic; Support vector machine; Data mining; Realization (probability); Artificial intelligence; Machine learning; Risk analysis (engineering); Operations research; Statistics; Engineering; Mathematics; Computer security; Business","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005000503,0.0002105825,0.0002372782,0.00008643461,0.0003339282,0.0003767698,0.0002009976,0.00007006753,0.0003197344],"category_scores_gemma":[0.00005344522,0.0001619153,0.00005236625,0.000244083,0.00005679317,0.000353434,0.0004719065,0.0001560787,0.0001308973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009844873,"about_ca_system_score_gemma":0.00001139977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00112835,"about_ca_topic_score_gemma":0.0008483054,"domain_scores_codex":[0.9982052,0.00008804262,0.0004135226,0.0005797627,0.0002553638,0.0004581197],"domain_scores_gemma":[0.9995447,0.00005652526,0.00003938575,0.0002201143,0.00003034995,0.0001088701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008346418,0.0001502723,0.114581,0.00005693606,0.0001192921,0.0003054863,0.01900857,0.0412234,0.4757171,0.00007442692,0.0001476285,0.3485324],"study_design_scores_gemma":[0.0002439751,0.00006955548,0.003941215,0.000630879,0.00007120564,0.0000887066,0.003844111,0.5589337,0.3971709,0.03341686,0.0002475104,0.001341344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5303583,0.00001874596,0.4693404,0.00009357845,0.0000356741,0.00006410674,0.000005212288,0.00003415452,0.00004976605],"genre_scores_gemma":[0.8817596,0.00003481996,0.1178759,0.0001932211,0.00002659069,0.00001530929,0.00001368583,0.00001876437,0.00006205246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5177104,"threshold_uncertainty_score":0.6602715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05237208147169949,"score_gpt":0.3091670511324739,"score_spread":0.2567949696607745,"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."}}