{"id":"W4392450031","doi":"10.1109/jstars.2024.3373029","title":"LCFSTE: Landslide Conditioning Factors and Swin Transformer Ensemble for Landslide Susceptibility Assessment","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Landslides and related hazards","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chengdu University; State Key Laboratory of Remote Sensing Science; State Key Laboratory of Geohazard Prevention and Geoenvironment Protection; Chengdu University of Technology; National Geographic Society; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Landslide; Computer science; Data mining; Machine learning; Reliability engineering; Artificial intelligence; Geology; Engineering; Geotechnical engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004460185,0.0001352501,0.0002289299,0.00009090731,0.000177146,0.0001109935,0.00004291923,0.0001231527,0.00001904141],"category_scores_gemma":[0.00002783424,0.00009725169,0.00004977159,0.0003129775,0.00006291505,0.0001438623,0.00001034269,0.0003573862,4.735604e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008369247,"about_ca_system_score_gemma":0.00006552182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009109611,"about_ca_topic_score_gemma":0.0006703245,"domain_scores_codex":[0.9989563,0.00002673831,0.0004080154,0.0001955654,0.0002040261,0.0002093977],"domain_scores_gemma":[0.9995406,0.0001651722,0.00009216358,0.0000719923,0.00004893536,0.00008119621],"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":[0.0001779647,0.0001040395,0.08194898,0.0004210371,0.0003483271,0.00008748838,0.004910017,0.008471076,0.3363081,0.001212604,0.001037045,0.5649734],"study_design_scores_gemma":[0.004187155,0.0005817209,0.7041665,0.001001487,0.0004335392,0.000459594,0.001234682,0.1710898,0.02962656,0.01621933,0.06998371,0.00101595],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9448922,0.0001196985,0.05318042,0.0005494326,0.0002309606,0.0002042359,0.000008137717,0.0000184664,0.0007964718],"genre_scores_gemma":[0.9485447,0.0002636302,0.05083918,0.00005962886,0.0001209054,1.660683e-7,0.00001089349,0.00001364554,0.0001472705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6222175,"threshold_uncertainty_score":0.3965809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.018583785422048,"score_gpt":0.2562655252923245,"score_spread":0.2376817398702765,"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."}}