{"id":"W4302028277","doi":"10.1016/j.watres.2022.119208","title":"Improving the accuracy of nonpoint-source pollution estimates in inland waters with coupled satellite-UAV data","year":2022,"lang":"en","type":"article","venue":"Water Research","topic":"Water-Energy-Food Nexus Studies","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Environmental science; Nonpoint source pollution; Remote sensing; Pollution; Surface runoff; Satellite; Vegetation (pathology); Hydrology (agriculture); Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.002537091,0.0001439244,0.0001792182,0.0001235391,0.0005936701,0.0000539391,0.00124462,0.00002662571,0.0002541172],"category_scores_gemma":[0.0001070297,0.00007526069,0.00001983039,0.0004525073,0.0005827511,0.000314136,0.005416916,0.0003929159,0.00005869517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002564141,"about_ca_system_score_gemma":0.00002141712,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01835471,"about_ca_topic_score_gemma":0.000636094,"domain_scores_codex":[0.9970943,0.0003636147,0.0002626686,0.0005032053,0.001055347,0.0007208749],"domain_scores_gemma":[0.9988556,0.0001423612,0.00005126672,0.0008732563,0.00001899934,0.00005855538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001207613,0.0005921101,0.2526214,0.0001470241,0.0001311723,0.0001565424,0.01906813,0.02857663,0.6765882,0.0002951153,0.002260145,0.01835594],"study_design_scores_gemma":[0.006445704,0.00335107,0.2533885,0.0001800761,0.00009849574,0.0002173811,0.02220693,0.187082,0.4440261,0.01207854,0.06931325,0.001611942],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949355,0.0001057836,0.0001447909,0.002382026,0.00004072736,0.0004369328,0.00004635295,0.00002563488,0.001882225],"genre_scores_gemma":[0.9987965,0.00001140591,0.0002418557,0.00005666797,0.0000178467,0.00009403922,0.00007321385,0.00002470464,0.0006837362],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.232562,"threshold_uncertainty_score":0.9881821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06100121641874449,"score_gpt":0.3032337750002063,"score_spread":0.2422325585814618,"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."}}