{"id":"W4411161761","doi":"10.5194/hess-29-2393-2025","title":"Skilful probabilistic predictions of UK flood risk months ahead using a large-sample machine learning model trained on multimodel ensemble climate forecasts","year":2025,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ouranos","funders":"U.S. Army Corps of Engineers; National Oceanic and Atmospheric Administration; UK Research and Innovation; Natural Environment Research Council; U.S. Army; University of Oxford; University of Alabama","keywords":"Probabilistic logic; Flood myth; Sample (material); Ensemble forecasting; Ensemble learning; Climate change; Environmental science; Computer science; Climatology; Machine learning; Artificial intelligence; Meteorology; Geology; Geography; Oceanography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000752694,0.0003287318,0.0003304667,0.0002397339,0.0001689652,0.0004395761,0.0003132859,0.0003606562,0.001423519],"category_scores_gemma":[0.002434315,0.0002356741,0.0004024198,0.0002035346,0.0001406812,0.0006368321,0.0003767783,0.0006443061,0.0003013679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000457142,"about_ca_system_score_gemma":0.0004533624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02374143,"about_ca_topic_score_gemma":0.02847528,"domain_scores_codex":[0.9998659,0.00004713752,0.000008719008,0.00003856561,0.00002070637,0.00001894709],"domain_scores_gemma":[0.9991121,0.0005288932,0.00009487734,0.00009732079,0.0001208265,0.0000460329],"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":[0.00007331109,0.00002791469,0.01647581,0.00001193736,0.00004814989,0.0000349942,0.00002584835,0.9673431,0.0006298869,0.0002460284,0.0007315531,0.01435143],"study_design_scores_gemma":[0.000003507618,0.000009982691,0.003092207,0.000002170378,0.000004235549,0.000003836175,0.000003610141,0.9964741,0.0001840715,0.0001393797,0.00007951176,0.000003345764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9491883,0.00009494017,0.04728624,0.0003239921,0.00005122332,0.00001460768,0.0009056383,0.00050076,0.001634306],"genre_scores_gemma":[0.9945516,0.00002163512,0.004318763,0.00001984663,0.00001229039,0.000007075651,0.0004930498,0.00001560615,0.0005600977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02374143,"threshold_uncertainty_score":0.04720646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0171962514135775,"score_gpt":0.2414918201868626,"score_spread":0.2242955687732851,"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."}}