{"id":"W2966632903","doi":"10.3808/jeil.201900007","title":"Examination of Multiple Linear Regression (MLR) and Neural Network (NN) Models to Predict Eutrophication Levels in Lake Champlain","year":2019,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"New York State Department of Environmental Conservation","keywords":"Eutrophication; Linear regression; Environmental science; Secchi disk; Alkalinity; Hydrology (agriculture); Chlorophyll a; Empirical modelling; Phosphorus; Water quality; Regression analysis; Lake ecosystem; Nutrient; Ecosystem; Ecology; Statistics; Mathematics; Biology; Chemistry; Computer science; Geology","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":[0.0007405184,0.0001342594,0.0002284758,0.00008780473,0.00003846325,0.00001370168,0.0001764301,0.00007354491,0.0001421079],"category_scores_gemma":[0.00003299264,0.0001074564,0.0000460611,0.0001288318,0.000107551,0.0006584445,0.0001681727,0.0002377423,0.00002163477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492861,"about_ca_system_score_gemma":0.000002551344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004916805,"about_ca_topic_score_gemma":0.00000782228,"domain_scores_codex":[0.9984543,0.00007467195,0.0007263943,0.00009316098,0.0004380853,0.0002133371],"domain_scores_gemma":[0.9991182,0.00009589922,0.0005411245,0.0001401698,0.000003181653,0.0001014161],"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":[0.00004388764,0.00005009416,0.05098909,0.00001464672,0.000005655358,0.000003045869,0.00214981,0.9130148,0.02932132,0.000001724823,0.00008086801,0.004325058],"study_design_scores_gemma":[0.0007635711,0.0003479099,0.3874703,0.0001264238,0.000009683485,0.000046718,0.0001440391,0.6100333,0.0006056039,0.0000458153,0.0002646122,0.0001420865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971131,0.000009301566,0.002047303,0.0003737208,0.00009449858,0.0002304308,0.0000168322,0.000004929479,0.0001098735],"genre_scores_gemma":[0.9891778,0.00001388762,0.009991691,0.0007514923,0.00003447336,0.000001846113,0.000007011548,0.000009634161,0.00001214899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3364812,"threshold_uncertainty_score":0.4381945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02110190721129896,"score_gpt":0.2159192897070044,"score_spread":0.1948173824957055,"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."}}