{"id":"W4416443596","doi":"10.1016/j.ejrh.2025.102961","title":"Improving estuarine discharge forecasting with a KAN-augmented LSTM model: A case study of the Yangtze River Estuary","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology Regional Studies","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Natural Science Foundation of Jiangxi Province; Ontario Ministry of Natural Resources and Forestry","keywords":"Estuary; Yangtze river; Artificial neural network; Adaptability; Limiting; Nonlinear system; Streamflow; Deep learning; Stream flow","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007054149,0.0002464393,0.0005690408,0.0001013163,0.0004835417,0.000009911492,0.0004031765,0.00007447338,0.0000126012],"category_scores_gemma":[0.0003320321,0.0001319407,0.0001457267,0.0004648225,0.001022523,0.0001587937,0.0007468777,0.0004798267,0.000001519084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634233,"about_ca_system_score_gemma":0.00004517676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000595224,"about_ca_topic_score_gemma":0.0007525505,"domain_scores_codex":[0.9980251,0.0002010399,0.0006705854,0.0002995768,0.0004624139,0.0003412791],"domain_scores_gemma":[0.9984378,0.0003516268,0.0007989096,0.0002493473,0.00009912824,0.00006319711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00076249,0.001571711,0.4990982,0.00004910359,0.001284236,0.002304174,0.008136541,0.4817457,0.000979404,0.00007267576,0.001560259,0.002435519],"study_design_scores_gemma":[0.01485527,0.01354434,0.06283007,0.0008959016,0.003090512,0.04376112,0.01276695,0.8366591,0.0003795213,0.009265252,0.0007127172,0.001239221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970044,0.0003230472,0.0004197396,0.001582168,0.0001406016,0.0003095653,0.000001014749,0.00001488852,0.0002045366],"genre_scores_gemma":[0.9980034,0.00001541434,0.001258597,0.0004510668,0.00004028502,0.00001328943,1.747269e-7,0.00001297183,0.0002048631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4362681,"threshold_uncertainty_score":0.5380384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04503780182809926,"score_gpt":0.27992526197353,"score_spread":0.2348874601454307,"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."}}