{"id":"W4391043080","doi":"10.1016/j.pedsph.2024.01.002","title":"Prediction of lead in agricultural soils: An integrated approach using machine learning, terrain attributes and reflectance spectra","year":2024,"lang":"en","type":"article","venue":"Pedosphere","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; Memorial University of Newfoundland","funders":"Česká Zemědělská Univerzita v Praze","keywords":"VNIR; Mean squared error; Support vector machine; Correlation coefficient; Coefficient of determination; Terrain; Artificial intelligence; Soil water; Mean absolute error; Mathematics; Machine learning; Soil science; Remote sensing; Environmental science; Hyperspectral imaging; Computer science; Statistics; Geology; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003854228,0.0006580763,0.0008042794,0.00133041,0.0002317768,0.0009091088,0.0004530462,0.0006495051,0.0004079999],"category_scores_gemma":[0.0006903526,0.0003085336,0.0006918395,0.001189973,0.0001776159,0.0007271846,0.0003435538,0.000398173,0.0002205877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004327453,"about_ca_system_score_gemma":0.000548652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01556357,"about_ca_topic_score_gemma":0.0170886,"domain_scores_codex":[0.9998624,0.00002740754,0.000008621402,0.00004693121,0.00003566383,0.00001896402],"domain_scores_gemma":[0.9996997,0.0001341566,0.00004083966,0.00001702476,0.00008572406,0.00002255518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0006145121,0.00052985,0.09208554,0.000136091,0.0003603792,0.0001469143,0.00005442313,0.7362047,0.02601249,0.0002803367,0.0005912515,0.1429835],"study_design_scores_gemma":[0.000009726935,0.00003282092,0.008559782,0.000002713569,0.00003799546,0.00001575393,0.00001768285,0.9893451,0.00160461,0.0002923359,0.00007461746,0.000006745186],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8606317,0.0006071447,0.1361693,0.0001457826,0.0000240637,0.00003375351,0.0007088185,0.0007633493,0.0009160348],"genre_scores_gemma":[0.9816641,0.0001950109,0.01715848,0.00001524913,0.00001633842,0.00001222201,0.0004390195,0.00002163734,0.0004779158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01556357,"threshold_uncertainty_score":0.03094596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02716710789227439,"score_gpt":0.249294612343837,"score_spread":0.2221275044515627,"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."}}