{"id":"W4388532585","doi":"10.5194/hess-2023-258","title":"When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"U.S. Department of Energy; National Oceanic and Atmospheric Administration; National Science Foundation","keywords":"Automatic differentiation; Discretization; Differentiable function; Interpretability; Computer science; Applied mathematics; Artificial neural network; Maxima and minima; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics; Computation","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":[0.0009773239,0.0005110233,0.0004664121,0.0003329821,0.0004059236,0.001459463,0.0007576925,0.001227644,0.002513591],"category_scores_gemma":[0.005683433,0.0003394158,0.0004527696,0.0002825691,0.001388222,0.0021143,0.001356753,0.00203636,0.0003444906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008155319,"about_ca_system_score_gemma":0.0008522045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004420262,"about_ca_topic_score_gemma":0.004189222,"domain_scores_codex":[0.9997959,0.00007890765,0.00001184615,0.00003992066,0.00004894149,0.00002456176],"domain_scores_gemma":[0.9991482,0.000452818,0.00009388079,0.0001162482,0.000126348,0.00006248074],"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":[0.00007058333,0.00003966078,0.002759416,0.0000818077,0.0000272231,0.0001866091,0.0001636607,0.8487127,0.004333179,0.1167084,0.001687038,0.02522985],"study_design_scores_gemma":[0.00000310074,0.000004998476,0.00008202481,0.000005383313,0.000001603259,0.000009276143,0.00001027777,0.9859035,0.0004545029,0.01309551,0.0004261235,0.000003839796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1181447,0.0003348795,0.8714985,0.002074488,0.0001810855,0.000037869,0.00009352068,0.0005752638,0.007059686],"genre_scores_gemma":[0.8967457,0.0001354018,0.09988926,0.0003249165,0.00004585119,0.00004858575,0.00008103569,0.0001931766,0.002535968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004420262,"threshold_uncertainty_score":0.008789062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06157307140959203,"score_gpt":0.2944952785277758,"score_spread":0.2329222071181838,"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."}}