{"id":"W2998277656","doi":"10.1002/lol2.10134","title":"Increasing accuracy of lake nutrient predictions in thousands of lakes by leveraging water clarity data","year":2019,"lang":"en","type":"article","venue":"Limnology and Oceanography Letters","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"CLARITY; Nutrient; Environmental science; Leverage (statistics); Chlorophyll a; Hydrology (agriculture); Ecology; Statistics; Mathematics; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003925276,0.0005175218,0.0005104153,0.0004768949,0.0005077655,0.000990986,0.0006639216,0.0005000803,0.0009068539],"category_scores_gemma":[0.009598376,0.0004709781,0.0006432564,0.0004442793,0.000434097,0.001678783,0.001323009,0.0008957436,0.0003006078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008895633,"about_ca_system_score_gemma":0.0006943124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02039052,"about_ca_topic_score_gemma":0.02695628,"domain_scores_codex":[0.9991159,0.0003727007,0.00005317367,0.0002957181,0.0001076899,0.00005494232],"domain_scores_gemma":[0.9942669,0.003670398,0.0005747401,0.0007876429,0.0005341793,0.0001661026],"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":[0.0004840759,0.000233495,0.3514853,0.00005355777,0.0007028951,0.00006023443,0.0001771344,0.591296,0.005498555,0.0005384706,0.001211866,0.04825843],"study_design_scores_gemma":[0.00001458191,0.0000323004,0.03097205,0.000007234726,0.00002826328,0.00001056111,0.00002980418,0.9662434,0.001618333,0.0008274515,0.0001991442,0.00001686668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771199,0.0001289043,0.02083515,0.000221323,0.00002224971,0.00001274805,0.0005809555,0.0004223603,0.0006563741],"genre_scores_gemma":[0.9933242,0.00002229162,0.006074057,0.00003371052,0.000009646618,0.000007629408,0.0004087256,0.00001869272,0.000101072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02039052,"threshold_uncertainty_score":0.04054368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008330672976301922,"score_gpt":0.2069061814633694,"score_spread":0.1985755084870675,"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."}}