{"id":"W4391661497","doi":"10.1109/jstars.2024.3364020","title":"Fuzzy Similarity Analysis of Effective Training Samples to Improve Machine Learning Estimations of Water Quality Parameters Using Sentinel-2 Remote Sensing Data","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina; University of Waterloo","funders":"","keywords":"Computer science; Mean absolute percentage error; Support vector machine; Mean squared error; Water quality; Artificial intelligence; Regression; Similarity (geometry); Data mining; Machine learning; Remote sensing; Statistics; Artificial neural network; Mathematics","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":[0.001865228,0.0001759759,0.0005695044,0.0003871911,0.0001700824,0.00006508059,0.0001377375,0.0001160168,0.000005211557],"category_scores_gemma":[0.0007694114,0.0001419155,0.00008864114,0.001784867,0.0001511375,0.0001515633,0.0001358075,0.0005447067,3.700261e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009745489,"about_ca_system_score_gemma":0.00004558283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001638621,"about_ca_topic_score_gemma":0.0007267087,"domain_scores_codex":[0.9978485,0.000218717,0.0009170675,0.0003486864,0.0003860435,0.0002810174],"domain_scores_gemma":[0.9986665,0.0005171461,0.0003461177,0.0002576739,0.0001234406,0.00008914791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002782454,0.00001130246,0.0009398532,0.00004621514,0.0002055553,0.000009317815,0.001484588,0.4688637,0.3698269,0.000007079842,0.000001269209,0.1585763],"study_design_scores_gemma":[0.0001823071,0.00004577936,0.01845078,0.0001873394,0.0003876233,0.00002462285,0.00006545337,0.9685866,0.01092939,0.0009405203,0.00005001718,0.0001496226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.821454,0.00001822699,0.1779705,0.0002109858,0.00009433399,0.0001499511,0.00001707287,0.00001834921,0.00006654418],"genre_scores_gemma":[0.6643132,0.000007833027,0.3355742,0.00003910721,0.00003207122,9.439827e-9,0.00001793343,0.00001044367,0.000005190378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4997228,"threshold_uncertainty_score":0.5787148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09748984460820852,"score_gpt":0.3131189630593307,"score_spread":0.2156291184511221,"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."}}