{"id":"W4390669434","doi":"10.1038/s41467-023-43860-5","title":"Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Climate change impacts on agriculture","field":"Agricultural and Biological Sciences","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Environment and Protected Areas; University of Alberta","funders":"National Institute of Food and Agriculture; Nuclear Safety and Security Commission; Advanced Research Projects Agency - Energy; U.S. Department of Agriculture; National Aeronautics and Space Administration; U.S. Department of Energy; Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Testbed; Carbon cycle; Biogeochemical cycle; Process (computing); Machine learning; Remote sensing; Ecosystem; Ecology","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":[0.0004138091,0.0001672855,0.0001754296,0.00005106118,0.0002157936,0.0001754362,0.0007601071,0.0003305425,0.00003283042],"category_scores_gemma":[0.000197178,0.00006905698,0.00007769318,0.001094841,0.00004249164,0.0001063461,0.0002106645,0.001299163,0.00003878628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001770918,"about_ca_system_score_gemma":0.00001748009,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001702761,"about_ca_topic_score_gemma":0.1197514,"domain_scores_codex":[0.9987606,0.0002477232,0.0002954201,0.0003007225,0.0001402846,0.0002552722],"domain_scores_gemma":[0.9989821,0.0004378938,0.00007755504,0.0003026687,0.0001139547,0.00008581574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000116042,0.00045089,0.01318336,0.0001077103,0.00005253078,0.000007881856,0.002725974,0.00006762495,0.9041087,0.006432307,0.003726919,0.06912449],"study_design_scores_gemma":[0.0004286703,0.0002381761,0.1530342,0.0007043169,0.00008611478,0.00007316969,0.002380348,0.1423895,0.007439776,0.0006910531,0.6913611,0.001173562],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9284548,0.03622388,4.113598e-7,0.02316448,0.0005441764,0.0005418065,0.0001926759,0.0004398867,0.0104379],"genre_scores_gemma":[0.9967319,0.00132503,0.00004158069,0.00007869931,0.0001774566,0.00007419847,0.00102114,0.000003137436,0.0005468382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8966689,"threshold_uncertainty_score":0.8963108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05349434908630368,"score_gpt":0.3183279181358475,"score_spread":0.2648335690495438,"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."}}