{"id":"W2040286263","doi":"10.1890/13-1677.1","title":"Determining the probability of cyanobacterial blooms: the application of Bayesian networks in multiple lake systems","year":2015,"lang":"en","type":"article","venue":"Ecological Applications","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":131,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks","funders":"Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences; Global Lake Ecological Observatory Network","keywords":"Ecology; Bayesian network; Environmental science; Algal bloom; Bayesian probability; Biology; Computer science; Phytoplankton; Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007994745,0.00008173382,0.0001719133,0.000008354114,0.00008238431,0.00001076172,0.0003813619,0.00008517342,0.00004016392],"category_scores_gemma":[0.00008846766,0.00004480968,0.00003687089,0.0002558182,0.0002579543,0.00003805929,0.0001258163,0.0001045215,0.00001806316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006326684,"about_ca_system_score_gemma":0.00001400313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001824895,"about_ca_topic_score_gemma":0.005652492,"domain_scores_codex":[0.9989572,0.0001341213,0.0004353377,0.0001885255,0.000145278,0.0001395365],"domain_scores_gemma":[0.9988604,0.0004058131,0.0002662048,0.0003991711,0.00002276384,0.00004566443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001024216,0.0002678368,0.9382049,0.00001199989,0.000004577063,6.274213e-8,0.0001482105,0.0553086,0.0001018035,0.004289854,0.00005819852,0.001593692],"study_design_scores_gemma":[0.000292676,0.00006089783,0.674158,0.000005145194,0.00001098829,0.000001403732,0.000114786,0.3156939,0.00001568884,0.002205746,0.007362259,0.00007860026],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9346366,0.00001006504,0.06175494,0.0001267716,0.00005483321,0.001881402,0.00002807915,0.00001514531,0.001492154],"genre_scores_gemma":[0.9983872,0.000002049149,0.0004505745,0.00002197855,0.00004620079,0.00105086,0.0000221298,0.000004427136,0.00001465086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.264047,"threshold_uncertainty_score":0.3154224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02089675003028081,"score_gpt":0.2255802812696457,"score_spread":0.2046835312393648,"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."}}