{"id":"W3195031531","doi":"10.1016/j.jhydrol.2021.126782","title":"Assessing the new Natural Resources Conservation Service water supply forecast model for the American West: A challenging test of explainable, automated, ensemble artificial intelligence","year":2021,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ensemble forecasting; Service (business); Natural resource; Computer science; Test (biology); Water supply; Water resources; Water conservation; Operations research; Artificial intelligence; Environmental science; Engineering; Business; Ecology; Environmental engineering","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":[0.0007530489,0.0001200664,0.0002564812,0.00004541264,0.0003849757,0.00003793168,0.0003157519,0.0000406412,0.00004371129],"category_scores_gemma":[0.0001349938,0.00006253363,0.00008621545,0.000179305,0.0003050266,0.0002633285,0.0002162406,0.0002139683,0.00000794978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003730518,"about_ca_system_score_gemma":0.00002154486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001819656,"about_ca_topic_score_gemma":0.0006947328,"domain_scores_codex":[0.9988385,0.0001037355,0.0004275418,0.0001521696,0.000172032,0.0003059738],"domain_scores_gemma":[0.9987523,0.0006265102,0.0003707858,0.0001582404,0.00005939073,0.00003280566],"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":[0.0003360143,0.0001772466,0.01202278,0.00004772693,0.0003004151,0.00007446841,0.01539428,0.9089377,0.04435676,0.0003492299,0.0035675,0.01443586],"study_design_scores_gemma":[0.0001419337,0.0001671052,0.004008598,0.00001563423,0.0001119247,0.0001379046,0.002422444,0.9758024,0.009500244,0.005987647,0.001615718,0.00008845696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9012252,0.0001899741,0.02661529,0.0715525,0.0001534092,0.0001325789,0.000001093788,0.00001511288,0.0001148375],"genre_scores_gemma":[0.9955174,0.00008787752,0.001648669,0.002536076,0.00008232241,0.000007402461,0.000001709763,0.000009351726,0.0001091404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09429225,"threshold_uncertainty_score":0.2960961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03149519499297227,"score_gpt":0.2820105990887551,"score_spread":0.2505154040957828,"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."}}