{"id":"W4205366521","doi":"10.1016/j.jenvman.2022.114515","title":"Improving litterfall production prediction in China under variable environmental conditions using machine learning algorithms","year":2022,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Natural Resources and Forestry; Ontario Forest Research Institute; University of British Columbia","funders":"","keywords":"Random forest; Plant litter; Primary production; Abiotic component; Environmental science; Production (economics); Ecosystem; Ecology; Machine learning; Computer science; Biology","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001163998,0.0002466781,0.0002619523,0.000240291,0.0004663109,0.00003727231,0.000302795,0.00004469057,0.005164039],"category_scores_gemma":[0.000008127791,0.0002656602,0.0001059431,0.0002420583,0.0000985979,0.0006574877,0.0006976535,0.0006349753,0.00006326444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003425192,"about_ca_system_score_gemma":0.000006025625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002787986,"about_ca_topic_score_gemma":0.000008738225,"domain_scores_codex":[0.9972199,0.0003454353,0.0007048235,0.0004163439,0.0009319893,0.0003814596],"domain_scores_gemma":[0.9990343,0.00002319806,0.0005972177,0.0002357395,8.09702e-7,0.0001087522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00009954502,0.001329461,0.1553936,0.00003818942,0.0001175264,0.0001504334,0.0004326071,0.6191871,0.215796,0.00001252931,0.0002536672,0.007189362],"study_design_scores_gemma":[0.002932742,0.001287312,0.7623967,0.0000803334,0.0002579916,0.001138147,0.002628426,0.2168036,0.001843746,0.0003361828,0.009606728,0.0006881469],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959686,0.0002025008,0.001678062,0.00009842432,0.0008703422,0.0006166577,0.00005725574,0.00002101346,0.0004871778],"genre_scores_gemma":[0.9954137,0.00005305974,0.002818227,0.00007323894,0.0001116078,0.00004062756,0.00004129998,0.0000450803,0.001403139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6070031,"threshold_uncertainty_score":0.9999796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004774922561420528,"score_gpt":0.1849169422098116,"score_spread":0.1801420196483911,"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."}}