{"id":"W3036873236","doi":"10.1016/j.scitotenv.2020.140338","title":"Machine learning for predicting greenhouse gas emissions from agricultural soils","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":283,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Agriculture and Agri-Food Canada","keywords":"Greenhouse gas; Soil water; Agriculture; Environmental science; Natural resource economics; Earth science; Soil science; Economics; Geology; Geography; Archaeology; Oceanography","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":[0.0003331564,0.0001186426,0.0001098686,0.000006650311,0.000727363,0.00003132232,0.0006930884,0.00002144872,0.0003385092],"category_scores_gemma":[0.0002426136,0.0000606859,0.00007892864,0.0001841775,0.000780453,0.0001168318,0.0009001051,0.0001542842,0.00005363156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008370949,"about_ca_system_score_gemma":0.00001081249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004265135,"about_ca_topic_score_gemma":0.00000291963,"domain_scores_codex":[0.9986355,0.00003940776,0.0001940779,0.0003019682,0.0005431352,0.0002859437],"domain_scores_gemma":[0.9993417,0.0001178778,0.0001601395,0.0002455786,0.000002996609,0.0001317505],"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":[0.00002177698,0.00005447683,0.002213987,0.000005222892,0.00001568843,4.939382e-7,0.003587921,0.5551241,0.4318709,0.0001309276,0.0004364263,0.006538095],"study_design_scores_gemma":[0.000759321,0.0003471694,0.2657621,0.00004869112,0.00009721277,0.000008785403,0.001955491,0.6758393,0.05022958,0.002057875,0.002473254,0.0004212739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938836,0.00004350457,0.0007131099,0.003543484,0.0001039057,0.0003335646,0.00003624966,0.00002184809,0.001320778],"genre_scores_gemma":[0.9980518,0.00002552995,0.001353545,0.0000699402,0.00005367622,0.00001452507,0.000003311059,0.000008201248,0.0004195101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3816413,"threshold_uncertainty_score":0.5594362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01326013409874458,"score_gpt":0.2036675925635267,"score_spread":0.1904074584647821,"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."}}