{"id":"W4383955976","doi":"10.1038/s43017-023-00450-9","title":"Differentiable modelling to unify machine learning and physical models for geosciences","year":2023,"lang":"en","type":"review","venue":"Nature Reviews Earth & Environment","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":394,"is_retracted":false,"has_abstract":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Institute for Computational and Data Sciences, Pennsylvania State University; Office of Science; Pennsylvania State University; Division of Chemical, Bioengineering, Environmental, and Transport Systems; University of Pennsylvania; U.S. Geological Survey; U.S. Department of Energy; National Science Foundation","keywords":"Interpretability; Machine learning; Differentiable function; Artificial intelligence; Computer science; Leverage (statistics); Extrapolation; Artificial neural network; Consistency (knowledge bases); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006079447,0.0005409051,0.001686791,0.0001933857,0.0001116928,0.00006995214,0.0002211959,0.0003640366,0.00001142867],"category_scores_gemma":[0.00005285143,0.0004149279,0.0003947451,0.0002667503,0.00002084618,0.00008786182,0.00009891406,0.001042448,0.00005879573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005684054,"about_ca_system_score_gemma":0.000009549896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000157736,"about_ca_topic_score_gemma":5.655057e-7,"domain_scores_codex":[0.9980679,0.0001385361,0.0005431602,0.0005470473,0.0002803497,0.0004230455],"domain_scores_gemma":[0.9990569,0.0003061882,0.00009666303,0.0003322245,0.000006914084,0.000201122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[4.907048e-7,0.000005331914,1.490149e-7,0.007500185,0.00002916349,4.815292e-7,0.00002665255,0.7325099,9.85466e-7,0.00007849273,0.00002843597,0.2598197],"study_design_scores_gemma":[0.00004322646,0.00001410383,1.459858e-7,0.001799521,0.0001088357,9.358101e-7,8.12567e-7,0.4800138,8.263771e-7,0.00006696601,0.5177342,0.0002166095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002191655,0.7032851,0.2952274,0.000004135999,0.0001167484,0.001146892,0.00002538729,0.0001341232,0.00003822658],"genre_scores_gemma":[0.00001661332,0.9663296,0.03153215,0.000006059676,0.0001920431,0.000371589,0.00009598609,0.0001233585,0.00133255],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5177057,"threshold_uncertainty_score":0.9998302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06341500714554814,"score_gpt":0.3296476525477977,"score_spread":0.2662326454022496,"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."}}