{"id":"W4409449923","doi":"10.4000/13raq","title":"Évaluation comparative des algorithmes d'apprentissage automatique pour la classification des types de sols à partir de caractéristiques physico-chimiques : application de Random Forest, XGBoost, SVM et KNN","year":2025,"lang":"fr","type":"article","venue":"VertigO","topic":"Soil and Land Suitability Analysis","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Random forest; Support vector machine; Computer science; Artificial intelligence; Forestry; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001568225,0.0002810929,0.0003867194,0.00008148343,0.0004531124,0.0002372635,0.000266988,0.0002370358,0.0001844343],"category_scores_gemma":[0.0003283708,0.0002743814,0.0002001209,0.0004305791,0.0009070771,0.0005166198,0.0000801762,0.0002520993,0.00008354666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008375313,"about_ca_system_score_gemma":0.0002928931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005411578,"about_ca_topic_score_gemma":0.007571066,"domain_scores_codex":[0.9967419,0.00163007,0.00043386,0.0004652303,0.0002388215,0.0004901009],"domain_scores_gemma":[0.9983777,0.0008609426,0.0001778974,0.0003387725,0.00009773675,0.0001468909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001635987,0.0007411847,0.6568518,0.0002432725,0.0002561596,0.000003316507,0.02395527,0.01185399,0.02914919,0.00858537,0.002545775,0.265651],"study_design_scores_gemma":[0.0004068103,0.00002742644,0.5373543,0.0001225979,0.0002361109,0.000003659475,0.0008481065,0.3887215,0.01672807,0.05444624,0.0009390139,0.0001662052],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6266322,0.001045657,0.3665164,0.001361243,0.00002806564,0.0003250322,0.00002512604,0.00008805365,0.00397829],"genre_scores_gemma":[0.972789,0.001064956,0.0241473,0.0002269382,0.00006232924,0.0003577103,0.00007900397,0.00001658372,0.001256188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3768675,"threshold_uncertainty_score":0.9999709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03120061627788215,"score_gpt":0.3102955914255297,"score_spread":0.2790949751476475,"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."}}