{"id":"W2757015653","doi":"10.5194/isprs-archives-xlii-4-w4-245-2017","title":"IMPROVING THE ACCURACY OF EXTRACTING SURFACE WATER QUALITY LEVELS (SWQLs) USING REMOTE SENSING AND ARTIFICIAL NEURAL NETWORK: A CASE STUDY IN THE SAINT JOHN RIVER, CANADA","year":2017,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Water Quality and Pollution Assessment","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"U.S. Geological Survey","keywords":"Surface water; Water quality; Ground truth; Environmental science; Process (computing); Artificial neural network; Computer science; Quality (philosophy); Remote sensing; Water resources; Hydrology (agriculture); Data mining; Artificial intelligence; Geology; Environmental engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0006499444,0.0006036561,0.000363898,0.0008452233,0.001375347,0.001038861,0.0009930023,0.0006211631,0.0005754015],"category_scores_gemma":[0.001566857,0.000201086,0.0004243542,0.001850134,0.0005813492,0.0003397852,0.0003868505,0.0004967978,0.0001102994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00837176,"about_ca_system_score_gemma":0.008662598,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9551263,"about_ca_topic_score_gemma":0.9702104,"domain_scores_codex":[0.9995597,0.00004897877,0.0000246172,0.0000973487,0.0001858942,0.00008345692],"domain_scores_gemma":[0.9989686,0.0002636513,0.00004821959,0.00004574823,0.0006154557,0.00005833025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000627401,0.0006795941,0.3547207,0.0005888143,0.0002940156,0.00561072,0.001827076,0.3984389,0.02709473,0.002326448,0.007542952,0.2002487],"study_design_scores_gemma":[0.00004368638,0.00006136667,0.1322074,0.00002761721,0.00007118747,0.00008664824,0.001471311,0.8524895,0.01088669,0.0003006073,0.002304197,0.00004977503],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885083,0.0001635245,0.006666769,0.0003535789,0.00001670817,0.00007723806,0.000662059,0.0002308792,0.003320975],"genre_scores_gemma":[0.9870999,0.0001086694,0.01026645,0.00004209685,0.000004167596,0.00001774504,0.0005394187,0.00001859675,0.001902931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04487365,"threshold_uncertainty_score":0.09027582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05905881153643699,"score_gpt":0.3175899436654459,"score_spread":0.2585311321290089,"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."}}