{"id":"W4408426859","doi":"10.5194/egusphere-egu25-10685","title":"Leveraging modern geospatial data science techniques for multi-hazard exposure analysis in British Columbia, Canada","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth; BGC Engineering (Canada)","funders":"","keywords":"Geospatial analysis; Hazard; Data science; Geography; Geomatics; Computer science; Remote sensing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001846871,0.0005359269,0.0003634527,0.00432676,0.003355959,0.00500204,0.001363773,0.0003754123,0.004476087],"category_scores_gemma":[0.006942286,0.0005750993,0.0005490454,0.009315142,0.001230775,0.001099524,0.00216158,0.0008498269,0.0007729922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04978226,"about_ca_system_score_gemma":0.1008264,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9980844,"about_ca_topic_score_gemma":0.9987878,"domain_scores_codex":[0.9982052,0.0001969509,0.0001435492,0.0003001186,0.0008900799,0.0002641651],"domain_scores_gemma":[0.9947116,0.0006743053,0.0001725279,0.0003691243,0.003602026,0.0004703555],"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":[0.0002159462,0.000216499,0.1982566,0.0008375226,0.0002609614,0.001171606,0.006278413,0.06593128,0.005112861,0.02361449,0.1057111,0.5923927],"study_design_scores_gemma":[0.0000776215,0.00006246439,0.3901429,0.001030936,0.0001912453,0.0002233197,0.01886935,0.1928136,0.005539202,0.0138079,0.3768517,0.0003898581],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4837833,0.008030467,0.1775347,0.02260097,0.0004199223,0.002574271,0.08892554,0.009058928,0.207072],"genre_scores_gemma":[0.726644,0.005342269,0.1966871,0.001074794,0.00003056213,0.0004391674,0.02225494,0.001007953,0.0465192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04978226,"threshold_uncertainty_score":0.3611973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04213762643359533,"score_gpt":0.3212531562661186,"score_spread":0.2791155298325233,"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."}}