{"id":"W4414530414","doi":"10.1007/s40808-025-02633-3","title":"Modeling drought intensity in the hyrcanian forest using machine learning and environmental variables","year":2025,"lang":"en","type":"article","venue":"Modeling Earth Systems and Environment","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Sari Agricultural Sciences and Natural Resources University","keywords":"Random forest; Basal area; Abiotic component; Mean squared error; Support vector machine; Linear regression; Sample (material); Regression; Set (abstract data type); Predictive modelling","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":[],"consensus_categories":[],"category_scores_codex":[0.0007701829,0.0002139361,0.0002843202,0.00006879102,0.000431351,0.00006299615,0.0001246891,0.0001019135,0.00004621661],"category_scores_gemma":[0.000007326705,0.0001650825,0.0000443731,0.00009628418,0.0001339116,0.0001442039,0.0002545162,0.0002973632,0.000009741048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008019312,"about_ca_system_score_gemma":0.000003995088,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007165696,"about_ca_topic_score_gemma":0.0007037771,"domain_scores_codex":[0.9985106,0.000136617,0.0003464991,0.0004675262,0.0002202906,0.0003184552],"domain_scores_gemma":[0.9996467,0.00002618086,0.00004946197,0.0002152673,9.840368e-7,0.00006141709],"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":[0.00001368499,0.00003151731,0.1702093,0.00001102828,0.00001891661,0.000007727774,0.0004514831,0.8285077,0.0005005761,0.00004001005,0.000001199557,0.0002068703],"study_design_scores_gemma":[0.0002837975,0.00002455546,0.00124251,0.00003826041,0.00006062385,0.00002927428,0.0008900279,0.9964882,0.000006725207,0.0002244346,0.0005477638,0.0001637967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419649,0.001694167,0.05559258,0.0001322435,0.00004682644,0.0002109051,0.000003386743,0.00001353933,0.0003414236],"genre_scores_gemma":[0.9983772,0.0006019237,0.0005938328,0.0001519345,0.00002185233,0.0000158629,0.00001221322,0.00001143302,0.0002137452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1689668,"threshold_uncertainty_score":0.9994457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01181136938572627,"score_gpt":0.2017500164635287,"score_spread":0.1899386470778024,"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."}}