{"id":"W4206710461","doi":"10.1071/wf21061","title":"Modelling chamise fuel moisture content across California: a machine learning approach","year":2021,"lang":"en","type":"article","venue":"International Journal of Wildland Fire","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Environmental science; Water content; Moisture; Sampling (signal processing); Meteorology; Boreal; Mean squared error; Mediterranean climate; Atmospheric sciences; Climatology; Physical geography; Geography; Statistics; Mathematics; Computer science; Engineering; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006003186,0.0006246816,0.0004311035,0.0007682545,0.0003840883,0.0008118539,0.0008492116,0.0006619801,0.0006509232],"category_scores_gemma":[0.001314576,0.0004049435,0.0004703117,0.0006364329,0.0002509187,0.0005987852,0.0002786198,0.0006635234,0.0001455526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001210583,"about_ca_system_score_gemma":0.0008433729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1810529,"about_ca_topic_score_gemma":0.1838347,"domain_scores_codex":[0.9998509,0.0000200776,0.000006904788,0.00008352519,0.00001991863,0.00001865104],"domain_scores_gemma":[0.9994778,0.0002884707,0.0000830163,0.00003755892,0.00008925105,0.00002391968],"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":[0.00002853213,0.00004001843,0.01866362,0.00001136613,0.00002944339,0.00002064756,0.00001903853,0.9701291,0.0003319804,0.0001370339,0.0003278756,0.01026149],"study_design_scores_gemma":[0.000002633062,0.000005120886,0.003975818,0.000001744841,0.000003568544,0.000002820255,0.000008940094,0.9957228,0.00008960978,0.0001052334,0.00007858476,0.000003258065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.929597,0.0002536293,0.06533338,0.000256479,0.00001782772,0.00005082173,0.001444533,0.000740828,0.002305468],"genre_scores_gemma":[0.9852405,0.00009174161,0.01274833,0.00001929896,0.00001137942,0.00003369576,0.001083964,0.00002600273,0.0007450624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1810529,"threshold_uncertainty_score":0.359998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01852111761274406,"score_gpt":0.2345115545813082,"score_spread":0.2159904369685642,"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."}}