{"id":"W4409324757","doi":"10.1007/s10661-025-13972-0","title":"Variability analysis of soil organic carbon content across land use types and its digital mapping using machine learning and deep learning algorithms","year":2025,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières; Innovation and Economic Development Trois Rivières","funders":"","keywords":"Soil carbon; Digital soil mapping; Algorithm; Total organic carbon; Land use; Environmental science; Ecotoxicology; Carbon fibers; Computer science; Artificial intelligence; Machine learning; Soil science; Soil classification; Environmental chemistry; Chemistry; Soil water; Ecology; Biology","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":[0.000316737,0.0001844678,0.0002967438,0.00006416492,0.0002933356,0.0001295615,0.00004450164,0.00005880393,0.00001948445],"category_scores_gemma":[0.00005553899,0.0001816465,0.00003518881,0.0001959145,0.0001366406,0.0001768027,0.00047586,0.0002342974,4.59333e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001699401,"about_ca_system_score_gemma":0.000004865463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007030879,"about_ca_topic_score_gemma":0.00002906426,"domain_scores_codex":[0.9987951,0.00007521373,0.0002645278,0.0004119592,0.0002054641,0.0002477406],"domain_scores_gemma":[0.9994946,0.0001929074,0.0001241913,0.00009334034,0.000003968948,0.00009100418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005927446,0.00004397428,0.9614831,0.00002162308,0.0002047064,0.000004220247,0.0004040608,0.002668749,0.02248223,0.000004597041,2.918226e-8,0.01267682],"study_design_scores_gemma":[0.0002795107,0.00003931142,0.7859874,0.00003431769,0.0001788745,0.00000291653,0.000871241,0.2116829,0.0006768457,0.00001563089,0.00008544049,0.0001455935],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976644,0.000534298,0.00145742,0.00001194823,0.00008360387,0.000112443,0.00002302743,0.00001783775,0.00009503924],"genre_scores_gemma":[0.9978571,0.0005754885,0.001324598,0.00000338916,0.00001641987,0.00000518183,0.0000205374,0.00001165079,0.0001856209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2090141,"threshold_uncertainty_score":0.740733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01816350387728679,"score_gpt":0.267671127503592,"score_spread":0.2495076236263052,"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."}}