{"id":"W4353047559","doi":"10.1016/j.ecoinf.2023.102079","title":"Development of a sensitivity analysis framework for aquatic biogeochemical models using machine learning","year":2023,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Clean Air Regulatory Agenda; China Scholarship Council; Department of the Environment, Australian Government; Mitacs; Government of Canada","keywords":"Machine learning; Equifinality; Computer science; Sensitivity (control systems); Biogeochemical cycle; Ecology; Artificial intelligence; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001307496,0.0001549604,0.0003824184,0.0001034843,0.0002353868,0.00002202596,0.0001480645,0.0002085731,0.0002230397],"category_scores_gemma":[0.001185601,0.000119989,0.0001562943,0.001279662,0.0001693346,0.0001313059,0.0003712504,0.0002374685,0.00009754475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001426316,"about_ca_system_score_gemma":0.00001571462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002118903,"about_ca_topic_score_gemma":0.00003255131,"domain_scores_codex":[0.998421,0.00006142657,0.0006556516,0.0001558108,0.0002971795,0.0004089173],"domain_scores_gemma":[0.9986541,0.0008030597,0.0002725778,0.0001500542,0.00001312787,0.0001070739],"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":[0.00001493071,0.00007877464,0.01477064,0.00002413216,0.00008851597,0.000002429278,0.001420812,0.980663,0.001325562,0.0002104206,0.00001741191,0.001383369],"study_design_scores_gemma":[0.0001041375,0.00005687851,0.001565337,0.00001042836,0.00009083878,0.000002012854,0.00007684951,0.9887146,0.001039281,0.008000685,0.0001833684,0.0001555324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.739108,0.000001067876,0.260381,0.00002945056,0.00002317583,0.0001529616,0.000009912647,0.0001060053,0.000188525],"genre_scores_gemma":[0.6342651,0.000001026082,0.365579,0.00007723614,0.000006090212,0.00000858815,0.00004874087,0.000004716609,0.000009487435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1051981,"threshold_uncertainty_score":0.4893009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07157095124181152,"score_gpt":0.2920708098434655,"score_spread":0.220499858601654,"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."}}