{"id":"W4416332491","doi":"10.1038/s41598-025-24236-9","title":"Enhancing soil organic carbon estimation with generative AI and Nix color sensor","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Indian Institute of Technology Kharagpur","keywords":"Mean squared error; Random forest; Calibration; Soil carbon; Artificial neural network; Boosting (machine learning); Partial least squares regression; Data set; Regression; Soil test","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":[0.0005382475,0.0005224912,0.0002888027,0.0003089089,0.0001314181,0.0003291439,0.0005822376,0.0003159955,0.0004197587],"category_scores_gemma":[0.0009085762,0.000213142,0.0004226318,0.0003097417,0.0002162981,0.0004073165,0.000397169,0.0004590682,0.000224377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003129441,"about_ca_system_score_gemma":0.0002739909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003392649,"about_ca_topic_score_gemma":0.003655771,"domain_scores_codex":[0.999843,0.00003802877,0.00000474549,0.00004824404,0.00004699864,0.00001900834],"domain_scores_gemma":[0.9997404,0.0001057569,0.00003427969,0.00003515957,0.0000730904,0.00001122676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002527976,0.0002273351,0.01552843,0.00009991881,0.00008999518,0.0001219002,0.0001360448,0.7151386,0.07795024,0.001461029,0.0008556133,0.1881382],"study_design_scores_gemma":[0.000002141658,0.00002473799,0.001894657,0.000001955349,0.000006179346,0.00001841181,0.000007028375,0.9894227,0.008212041,0.0001979571,0.0002052892,0.000006842756],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3435937,0.0002381635,0.651485,0.0001443071,0.00007139933,0.00005167957,0.0001986289,0.001371087,0.002846099],"genre_scores_gemma":[0.9239663,0.00007099457,0.07460811,0.00006578473,0.00001229452,0.00003154201,0.0001644197,0.00002508927,0.001055433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003392649,"threshold_uncertainty_score":0.006745756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004886922566827325,"score_gpt":0.2186571633630497,"score_spread":0.2137702407962224,"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."}}