{"id":"W4322208747","doi":"10.5194/egusphere-egu23-15968","title":"Differentiable modeling to unify machine learning and physical models and advance Geosciences","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Differentiable function; Leverage (statistics); Consistency (knowledge bases); Deep learning; Data science; Artificial neural network; Mathematics","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":[0.0002498802,0.0002659559,0.0003114113,0.00004996069,0.0002703965,0.0001418271,0.0002616238,0.0001182627,0.00009284489],"category_scores_gemma":[0.0001074181,0.0002074287,0.00003720927,0.000173656,0.0002078796,0.000135394,0.003509638,0.0005663459,0.0000749969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005104538,"about_ca_system_score_gemma":0.00000614916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00192642,"about_ca_topic_score_gemma":0.0001811108,"domain_scores_codex":[0.9980348,0.00005874652,0.0001840267,0.0009630961,0.0003500615,0.0004093175],"domain_scores_gemma":[0.9994355,0.0000837517,0.00005710555,0.0001903616,0.000006554671,0.0002267664],"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":[0.000005366218,0.00001978894,0.002963103,0.00001756313,0.000003628749,0.00000277235,0.0003353478,0.9935092,0.0004933833,0.0001239319,0.00001507732,0.00251082],"study_design_scores_gemma":[0.00005941454,0.00005987539,0.0003422511,0.00004902094,0.00001164335,0.000002507998,0.00001888357,0.9583917,0.00003198935,0.0406737,0.0001028857,0.0002561012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9428115,0.00004446039,0.05444506,0.0004306928,0.00008697378,0.0001983309,0.000006832919,0.0002438275,0.001732319],"genre_scores_gemma":[0.9854499,0.0000872313,0.01066189,0.0001025151,0.0000325226,0.00001993579,0.000007616185,0.00002443283,0.003613937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04378317,"threshold_uncertainty_score":0.8458697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0497047783015673,"score_gpt":0.2844941740250474,"score_spread":0.2347893957234801,"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."}}