{"id":"W4414166724","doi":"10.1021/acs.est.5c06078","title":"Integrating Machine Learning with Flow-Imaging Microscopy for Automated Monitoring of Algal Blooms","year":2025,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Division of Chemical, Bioengineering, Environmental, and Transport Systems; Water Research Foundation","keywords":"Flagging; Pipeline (software); Convolutional neural network; Algal bloom; Scalability; Random forest; Artificial neural network; Deep learning","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005913793,0.0002688661,0.000287064,0.0005058885,0.0005950863,0.0000473305,0.001182027,0.00013704,0.00003669791],"category_scores_gemma":[0.000191988,0.0002299428,0.00004959418,0.001509679,0.003935212,0.0003573177,0.001118221,0.0003839917,0.00002148978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006628858,"about_ca_system_score_gemma":0.00002589536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001237246,"about_ca_topic_score_gemma":0.000007195656,"domain_scores_codex":[0.9977759,0.00002677203,0.0003788373,0.000739925,0.0003933033,0.0006853149],"domain_scores_gemma":[0.9991653,0.0000678891,0.0001973706,0.0005096729,0.000007585041,0.00005218071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001335925,0.00005119642,0.4786679,0.000007103013,0.000006657692,0.000002334374,0.0001061141,0.001261837,0.5082394,0.00008164277,0.0000117101,0.01155064],"study_design_scores_gemma":[0.0004884987,0.0002224961,0.03423911,0.0001042873,0.00002265814,0.00001494768,0.001717049,0.02341462,0.9376734,0.0006058282,0.00122904,0.0002679908],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899575,0.0001438986,0.0072148,0.0005649008,0.0002100655,0.0004215488,0.00001046743,0.001155541,0.0003212934],"genre_scores_gemma":[0.8879063,0.00001605208,0.1117826,0.00001317391,0.000009519417,0.00008290455,0.000003782728,0.00001835364,0.0001672929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4444288,"threshold_uncertainty_score":0.9987755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006652776822791867,"score_gpt":0.2582634336613915,"score_spread":0.2516106568385996,"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."}}