{"id":"W3190751509","doi":"10.3390/agronomy11081550","title":"Artificial Intelligence-Based Prediction of Key Textural Properties from LUCAS and ICRAF Spectral Libraries","year":2021,"lang":"en","type":"article","venue":"Agronomy","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Boosting (machine learning); Soil texture; Silt; Random forest; Categorical variable; Gradient boosting; Environmental science; Soil science; Artificial intelligence; Computer science; Machine learning; Mathematics; Geology; Soil water","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003870629,0.00006949413,0.00008736084,0.00001147764,0.00006278345,0.0000486875,0.0000517221,0.00002788579,0.001021597],"category_scores_gemma":[0.00002678907,0.00006069946,0.00002147039,0.0000698626,0.0001930877,0.0001475694,0.00007024182,0.0000497123,0.00003504258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002097973,"about_ca_system_score_gemma":0.00002638161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000756568,"about_ca_topic_score_gemma":0.0001279188,"domain_scores_codex":[0.9994467,0.00002055749,0.0001557787,0.0001730315,0.00009159854,0.0001122847],"domain_scores_gemma":[0.9997764,0.00003929972,0.00003970634,0.00009746852,0.000006411727,0.00004071054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001625847,0.0003350478,0.4476414,0.00006142932,0.0001134736,0.00004641206,0.009543776,0.003924515,0.07806993,0.01757334,0.003837256,0.4386908],"study_design_scores_gemma":[0.0001364908,0.0001079176,0.5745047,0.00007287358,0.00004633859,0.00000428277,0.002227342,0.01893123,0.3647646,0.03376097,0.005176186,0.0002670186],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9880041,0.0002193751,0.008203066,0.0003800695,0.0001061131,0.00007762314,0.00003024542,0.00001884913,0.002960504],"genre_scores_gemma":[0.9920323,0.000009195801,0.007685643,0.00005271263,0.00005091944,0.000004164087,0.0000323652,0.000004656892,0.0001280329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4384238,"threshold_uncertainty_score":0.9998916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02847315895753972,"score_gpt":0.1968756315065924,"score_spread":0.1684024725490527,"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."}}