{"id":"W3198578454","doi":"10.5194/hess-25-4611-2021","title":"Combining split-sample testing and hidden Markov modelling to assess the robustness of hydrological models","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Climate change; Environmental science; Hidden Markov model; Hydrological modelling; Climate model; Climatology; Hydrology (agriculture); Computer science; Geology; Artificial intelligence; Oceanography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02131381,0.001069973,0.001089587,0.003077139,0.0005228845,0.001053809,0.001206778,0.001127255,0.001020675],"category_scores_gemma":[0.06467556,0.0003910765,0.001311316,0.00105516,0.001660772,0.002394739,0.001862048,0.00107812,0.0001289202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000908385,"about_ca_system_score_gemma":0.0008635836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003934702,"about_ca_topic_score_gemma":0.003177774,"domain_scores_codex":[0.991604,0.006576689,0.0003037162,0.0006548928,0.000608512,0.0002521541],"domain_scores_gemma":[0.8391988,0.1515278,0.003186891,0.003244941,0.001930974,0.0009106215],"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":[0.001187784,0.0003099116,0.09453076,0.0001171616,0.0008643104,0.0002339531,0.0002594301,0.8486435,0.002152638,0.004939136,0.0003051041,0.04645621],"study_design_scores_gemma":[0.000009037542,0.0001177338,0.002725363,0.000003378184,0.00001694575,0.00001410697,0.00002449967,0.994688,0.0005337062,0.001835046,0.00002422963,0.000007895294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7905375,0.0001843343,0.2079102,0.0001588293,0.00003511429,0.00005384296,0.000163021,0.0003481276,0.0006090426],"genre_scores_gemma":[0.9855864,0.00002281773,0.0140841,0.00001745033,0.00001090527,0.00002518611,0.0001650417,0.00001967869,0.00006830251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02131381,"threshold_uncertainty_score":0.1127196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07653943524195118,"score_gpt":0.2469956993026507,"score_spread":0.1704562640606995,"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."}}