{"id":"W3047226873","doi":"10.1016/j.geoderma.2020.114630","title":"Pairing soil sampling with very-high resolution UAV imagery: An examination of drivers of soil and nutrient movement and agricultural productivity in southern Ontario","year":2020,"lang":"en","type":"article","venue":"Geoderma","topic":"Soil erosion and sediment transport","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Mitacs; Ontario Ministry of Agriculture, Food and Rural Affairs; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Environmental science; Landform; Normalized Difference Vegetation Index; Soil water; Soil science; Spatial variability; Hydrology (agriculture); Erosion; Soil map; Geology; Agronomy; Leaf area index; Geomorphology","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":[0.0001473078,0.0000893068,0.0001447351,0.00001059415,0.00005560308,0.00001266647,0.00004574984,0.00003762365,0.00001373707],"category_scores_gemma":[0.000006300651,0.00003774627,0.00001740695,0.0001304242,0.00006076255,0.0001533544,0.00002367853,0.00006979347,2.485779e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002422265,"about_ca_system_score_gemma":0.000007540991,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01397943,"about_ca_topic_score_gemma":0.0515846,"domain_scores_codex":[0.9992795,0.00003793698,0.0001563527,0.000231995,0.0001763844,0.0001178183],"domain_scores_gemma":[0.9997652,0.00002046804,0.00008140533,0.00002735671,0.00004542785,0.00006020855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001883806,0.0002252636,0.5691341,0.00005965224,0.00001440676,0.000002825532,0.01585781,0.000865582,0.3984755,0.00007218154,0.000004741501,0.0150996],"study_design_scores_gemma":[0.0003655095,0.0003001489,0.981568,0.00003677697,0.00001076787,8.066226e-7,0.003993621,0.0003133427,0.01327328,0.00003245287,0.00001642131,0.00008887298],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992666,0.00002589112,0.0000124519,0.0004632179,0.00001454988,0.0001596455,0.00001340479,0.00001488123,0.00002939767],"genre_scores_gemma":[0.9997652,0.00001118258,0.00007989913,0.00004678829,0.00002426772,0.00000473332,0.00004703473,6.472761e-7,0.00002029837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.412434,"threshold_uncertainty_score":0.9925866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02197124527710205,"score_gpt":0.1853799260590736,"score_spread":0.1634086807819716,"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."}}