{"id":"W4399576043","doi":"10.1007/s40808-024-02055-7","title":"Predicting species abundance using machine learning approach: a comparative assessment of random forest spatial variants and performance metrics","year":2024,"lang":"en","type":"article","venue":"Modeling Earth Systems and Environment","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Deutscher Akademischer Austauschdienst; International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Abundance (ecology); Random forest; Relative abundance distribution; Spatial analysis; Statistics; Autocorrelation; Mathematics; Ecology; Computer science; Relative species abundance; Machine learning; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004584236,0.0001661623,0.0002780958,0.00004986149,0.0002170338,0.00009997187,0.00005980158,0.00005139264,0.0003068662],"category_scores_gemma":[0.000005562787,0.0001400792,0.00003495503,0.0001061516,0.000102642,0.0001702523,0.0001521113,0.0001605477,0.000007092103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001454999,"about_ca_system_score_gemma":0.000005878963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001155549,"about_ca_topic_score_gemma":0.00004929236,"domain_scores_codex":[0.9987208,0.00006192379,0.0003155386,0.0003363804,0.0003530718,0.0002122999],"domain_scores_gemma":[0.9996815,0.00003778849,0.00008960033,0.00010769,0.000004042294,0.00007934581],"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":[0.00001979523,0.000039975,0.290674,0.0001841146,0.00003050833,0.00000194988,0.0007349333,0.7059093,0.00188139,0.0001195762,0.000002891474,0.0004016403],"study_design_scores_gemma":[0.0003907912,0.00008210792,0.06606171,0.00008171815,0.00003112081,0.00001786832,0.0008118875,0.9317812,0.00002835444,0.000002479509,0.0005789099,0.0001318553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8863494,0.001441314,0.1101836,0.000009636102,0.00009764614,0.0002499349,0.0000339793,0.00002559393,0.001608839],"genre_scores_gemma":[0.9978289,0.001081292,0.0008507299,0.000004163817,0.00003529899,0.0000160719,0.00002341015,0.0000120581,0.0001480735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2258719,"threshold_uncertainty_score":0.5712262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07001004285392892,"score_gpt":0.2575218916826686,"score_spread":0.1875118488287397,"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."}}