{"id":"W4220757256","doi":"10.1016/j.geodrs.2022.e00495","title":"Incorporating spatial uncertainty maps into soil sampling improves digital soil mapping classification accuracy in Ontario, Canada","year":2022,"lang":"en","type":"article","venue":"Geoderma Regional","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; Natural Resources Canada; Canadian Forest Service","funders":"Canadian Forest Service","keywords":"Digital soil mapping; Soil map; Environmental science; Sampling (signal processing); Topographic Wetness Index; Soil texture; Soil science; Spatial variability; Water content; Soil water; Hydrology (agriculture); Remote sensing; Statistics; Digital elevation model; Computer science; Mathematics; Geography; Geology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002429443,0.0001882377,0.0001683927,0.00006436498,0.000576927,0.00009568365,0.0003082107,0.00004032939,0.0004196646],"category_scores_gemma":[0.0001000268,0.000215336,0.00004411073,0.0002450319,0.0001016607,0.000269128,0.0005269996,0.0004239949,0.00001329677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002524381,"about_ca_system_score_gemma":0.0007590395,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9844839,"about_ca_topic_score_gemma":0.9933489,"domain_scores_codex":[0.9980105,0.00004966287,0.0004110682,0.0004697172,0.0006649546,0.0003940601],"domain_scores_gemma":[0.9992012,0.0001932484,0.0002554682,0.0002219149,0.00001652699,0.0001116244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000104054,0.0001906265,0.478651,0.00003926226,0.00003804518,0.0001248876,0.004478544,0.3763033,0.007466705,0.001454307,0.01589036,0.1152589],"study_design_scores_gemma":[0.0008575091,0.00004585379,0.7226715,0.0000323773,0.000008225345,0.00006187344,0.004120957,0.162678,0.00002783018,0.01294914,0.09588007,0.0006666595],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917035,0.00001600129,0.003587302,0.001471527,0.0003255795,0.0002235447,0.00004840263,0.00003117701,0.002592959],"genre_scores_gemma":[0.997282,0.000001205422,0.0009112839,0.0006979574,0.0000605751,0.00009015857,0.0006055378,0.00001699238,0.0003343182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2440205,"threshold_uncertainty_score":0.8781149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02723772449586692,"score_gpt":0.2205783969271931,"score_spread":0.1933406724313262,"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."}}