{"id":"W4400662624","doi":"10.5194/hess-28-3051-2024","title":"When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling","year":2024,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":28,"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; Computer science; Differentiable function; Discretization; Interpretability; Artificial neural network; Applied mathematics; 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":[0.001014876,0.0005038931,0.0004716864,0.0003319872,0.000432821,0.001454235,0.0007665419,0.001268212,0.002622137],"category_scores_gemma":[0.006030726,0.0003503179,0.0004331706,0.0002828381,0.001500501,0.002329074,0.00150148,0.002157467,0.0003309718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007871861,"about_ca_system_score_gemma":0.0008185296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004210727,"about_ca_topic_score_gemma":0.003866602,"domain_scores_codex":[0.9997916,0.00008174789,0.00001220557,0.00003947038,0.00004987002,0.00002522618],"domain_scores_gemma":[0.9991661,0.0004367827,0.00009570638,0.000117372,0.000121195,0.00006268059],"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":[0.00007282051,0.00004343926,0.002985172,0.00008948298,0.00002913288,0.0002108538,0.0001945257,0.7945496,0.005048355,0.1666602,0.00204179,0.02807465],"study_design_scores_gemma":[0.000003564054,0.000005137527,0.00009974161,0.00000577869,0.000001628788,0.00001067813,0.00001181341,0.981891,0.0004937652,0.01695603,0.0005165208,0.000004336699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1161495,0.0003083901,0.8730356,0.002429097,0.0001935185,0.00003875095,0.00008771339,0.0005290367,0.007228344],"genre_scores_gemma":[0.8938606,0.0001296402,0.1027564,0.0003550894,0.00004941029,0.00005196611,0.00007396073,0.0001938755,0.002529171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004210727,"threshold_uncertainty_score":0.008771896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02059565344104644,"score_gpt":0.2380365877345579,"score_spread":0.2174409342935114,"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."}}