{"id":"W4408253036","doi":"10.1016/j.jenvman.2025.124803","title":"Effect of training sample size, image resolution and epochs on filamentous and floc-forming bacteria classification using machine learning","year":2025,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Suez (Canada); McMaster University","funders":"Global Water Futures; Natural Sciences and Engineering Research Council of Canada","keywords":"Sample (material); Artificial intelligence; Resolution (logic); Bacteria; Training (meteorology); Pattern recognition (psychology); Computer vision; Computer science; Biology; Chemistry; Chromatography; Geography","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":[0.0003605814,0.00009641835,0.0001592536,0.00002363536,0.0001289432,0.00003235482,0.0000561066,0.00003160828,0.00005192708],"category_scores_gemma":[0.00003188633,0.00003967022,0.00004678287,0.0000686247,0.0000397759,0.0001136424,0.00006439295,0.00009463016,4.272969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005077977,"about_ca_system_score_gemma":7.539655e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001592002,"about_ca_topic_score_gemma":0.000004718094,"domain_scores_codex":[0.9993253,0.00008230354,0.0002346085,0.0001157305,0.0001370941,0.0001049963],"domain_scores_gemma":[0.9994958,0.0002390245,0.0002050335,0.00002202014,0.000003648976,0.00003446076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00013173,0.00004685427,0.008759086,0.00003314552,0.00004519305,0.000004577785,0.00007757262,0.00002373483,0.8745171,0.0000364722,0.00002519796,0.1162993],"study_design_scores_gemma":[0.000793343,0.001645839,0.9739314,0.0002635661,0.0001741188,0.00002262307,0.001422644,0.00115724,0.0156176,0.0001404032,0.004682353,0.0001488533],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.999144,0.0001885661,0.00003005163,0.0001512644,0.00005989431,0.0001324503,0.00000737683,0.000003827069,0.0002825866],"genre_scores_gemma":[0.9985657,0.0002951479,0.0009433081,0.00004059613,0.00004992487,0.000001512961,0.000007142706,7.369609e-7,0.00009588651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9651724,"threshold_uncertainty_score":0.1617704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051894083327664,"score_gpt":0.2157013919162435,"score_spread":0.2051824510829668,"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."}}