{"id":"W4416860169","doi":"10.1016/j.ejrh.2025.103007","title":"Enhancing combined sewer flow prediction in data-limited urban areas using a semi-supervised learning framework","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology Regional Studies","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Wilfrid Laurier University; McGill University; Institut National de la Recherche Scientifique; United Nations University Institute for Water, Environment, and Health","funders":"Institut national de la recherche scientifique","keywords":"Benchmark (surveying); Artificial neural network; Combined sewer; Scalability; Key (lock); Cluster analysis; Predictive modelling; Flooding (psychology)","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":[0.001362486,0.0002159372,0.0005674867,0.0002004779,0.0003209579,0.000019356,0.000454523,0.0002159069,0.0001065207],"category_scores_gemma":[0.001933732,0.0001750269,0.00009574468,0.0006114517,0.0004714736,0.0002801309,0.0006006436,0.0009680982,0.0000148963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003555984,"about_ca_system_score_gemma":0.00004263022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004002139,"about_ca_topic_score_gemma":0.00007286982,"domain_scores_codex":[0.9977458,0.0003609759,0.0007507094,0.0003765499,0.0003766869,0.000389274],"domain_scores_gemma":[0.9984916,0.0007406546,0.0003825566,0.000248621,0.00006186817,0.00007467928],"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":[0.0005038448,0.0002328445,0.4607794,0.00002630617,0.000377589,0.0001719557,0.001507943,0.5249187,0.004778847,0.00003721779,0.005914794,0.0007505605],"study_design_scores_gemma":[0.00315755,0.00130058,0.06800646,0.001443234,0.000435181,0.0005966666,0.0007114219,0.8968995,0.0003016186,0.01228924,0.01431019,0.0005484004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922439,0.001119473,0.002757649,0.003036911,0.0004845522,0.0001090458,0.000002541988,0.00003250195,0.0002134265],"genre_scores_gemma":[0.9922586,0.0001561337,0.006182506,0.001042482,0.0001571897,0.000003046003,0.00000685701,0.00001296772,0.0001802109],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3927729,"threshold_uncertainty_score":0.7137391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05839427306579566,"score_gpt":0.3097245248225957,"score_spread":0.2513302517568001,"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."}}