{"id":"W4400177915","doi":"10.1186/s40068-024-00352-9","title":"Random forest and spatial cross-validation performance in predicting species abundance distributions","year":2024,"lang":"en","type":"article","venue":"ENVIRONMENTAL SYSTEMS RESEARCH","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutscher Akademischer Austauschdienst; International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Statistics; Spatial analysis; Random forest; Mathematics; Autocorrelation; Algorithm; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001169933,0.0001408404,0.0001440247,0.00007770319,0.0003937791,0.0003773381,0.0001743198,0.00008736886,0.007643627],"category_scores_gemma":[0.0000489079,0.0001304212,0.00003595352,0.0003104377,0.0006790489,0.0004301921,0.0003255269,0.0003400501,0.001447353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635018,"about_ca_system_score_gemma":0.000008928309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001197948,"about_ca_topic_score_gemma":0.000391816,"domain_scores_codex":[0.9978309,0.0001567828,0.000303806,0.0004488322,0.0007612357,0.0004984933],"domain_scores_gemma":[0.9995052,0.0001439061,0.00003009677,0.0001947436,0.000003588281,0.0001225319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003743999,0.00005756762,0.9915596,0.00006741281,0.000005678479,0.00001639768,0.0002856374,0.000619015,0.005477121,0.0002022683,0.0004795183,0.0011924],"study_design_scores_gemma":[0.000497676,0.00006502266,0.943401,0.00007853135,0.000002735602,0.00002567914,0.001046899,0.01507315,0.0008081235,0.00001411473,0.03884911,0.0001379448],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881247,0.0006759579,0.0002615994,0.0001180809,0.0002522733,0.000532911,0.0002631407,0.00004924221,0.009722079],"genre_scores_gemma":[0.9962071,0.0005929287,0.000003947475,0.000003330979,0.000100175,0.0001601848,0.0002241779,0.00001633189,0.002691804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04815853,"threshold_uncertainty_score":0.9993302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04409507595534297,"score_gpt":0.3147594149579463,"score_spread":0.2706643390026034,"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."}}