{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02576387,0.001580539,0.00107662,0.002412124,0.0005254471,0.0008597194,0.00107427,0.001059421,0.0008112055],"category_scores_gemma":[0.0334544,0.0003279502,0.001603985,0.001182262,0.0006243093,0.001294881,0.0008628523,0.0009772028,0.0003821937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006146611,"about_ca_system_score_gemma":0.001134294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008802014,"about_ca_topic_score_gemma":0.004873516,"domain_scores_codex":[0.992527,0.004950128,0.0004813299,0.001164206,0.0006133408,0.000263938],"domain_scores_gemma":[0.963474,0.02834301,0.001365956,0.002066314,0.004370773,0.0003799048],"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":[0.00103192,0.0002695888,0.06137382,0.0002051262,0.0007819657,0.00009367122,0.0000882555,0.8461483,0.002865965,0.001180515,0.001392733,0.08456809],"study_design_scores_gemma":[0.00001385569,0.00008549035,0.003216497,0.00002257294,0.00003148432,0.00002490627,0.00001188848,0.994879,0.001093163,0.0004602072,0.0001474987,0.00001349191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6009516,0.002888411,0.3907362,0.0002211344,0.000175485,0.0001560028,0.0008576246,0.00232271,0.001690828],"genre_scores_gemma":[0.9389717,0.0001567137,0.05915618,0.00008353902,0.00002547578,0.000117724,0.001066938,0.00009139127,0.0003301504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02576387,"threshold_uncertainty_score":0.136254,"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."}}