{"id":"W4306925940","doi":"10.3390/hydrology9100186","title":"Development of a Machine Learning Framework to Aid Climate Model Assessment and Improvement: Case Study of Surface Soil Moisture","year":2022,"lang":"en","type":"article","venue":"Hydrology","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Space Agency","keywords":"Climate model; Random forest; Climate change; Environmental science; Snowmelt; Emulation; Climatology; Meteorology; Relative humidity; Mean squared error; Snow; Water content; Downscaling; Range (aeronautics); Computer science; Machine learning; Statistics; Mathematics; Precipitation; Geography; Geology; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004327318,0.0001278133,0.0002469315,0.00003855796,0.0003075007,0.000004401882,0.0001046967,0.00004977052,0.00004979701],"category_scores_gemma":[0.000009269303,0.0001175295,0.00002312148,0.0001632145,0.000053238,0.00002488822,0.0008529742,0.0003250406,0.000001906957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056506,"about_ca_system_score_gemma":0.00001975955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001958351,"about_ca_topic_score_gemma":0.004614696,"domain_scores_codex":[0.9987652,0.0001083765,0.0003092248,0.0003163743,0.0002578528,0.0002429724],"domain_scores_gemma":[0.9995475,0.00004843931,0.0001468706,0.0001842991,0.000006306687,0.00006662503],"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":[0.00007259322,0.0004721212,0.1537448,0.00001855731,0.00004906251,0.000222738,0.02314488,0.7776658,0.02897325,0.00001545978,0.00001122051,0.01560956],"study_design_scores_gemma":[0.003081554,0.004775427,0.08215329,0.00002473613,0.0001784896,0.001039845,0.02744753,0.8751324,0.003544564,0.0004978857,0.001335896,0.000788321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977939,0.00003254411,0.0008962766,0.0000900305,0.00006233827,0.0002891975,0.000002276244,0.00001555377,0.0008178502],"genre_scores_gemma":[0.9819649,0.000004327746,0.01777764,0.0001869829,0.000005383584,0.000004988491,0.000002990222,0.00001387288,0.00003891762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09746668,"threshold_uncertainty_score":0.4792713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01256802905866953,"score_gpt":0.2655223267511311,"score_spread":0.2529542976924616,"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."}}