{"id":"W7117570263","doi":"10.1016/j.jenvman.2025.128444","title":"Interpretable deep learning for dynamic rainfall-runoff prediction: Integrating adaptive signal decomposition and spatiotemporal feature extraction","year":2025,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada","keywords":"Decomposition; Particle swarm optimization; Feature extraction; Feature (linguistics); Pattern recognition (psychology); Visualization; Deep learning; SIGNAL (programming language)","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":[0.0004621462,0.0001624935,0.0001880662,0.00009848239,0.0002539757,0.00005620486,0.0001263571,0.00008026034,0.0002806047],"category_scores_gemma":[0.00001798771,0.0001430534,0.00009540298,0.00009671012,0.0001188709,0.0003631733,0.0001711815,0.0003261183,0.000006285021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000597077,"about_ca_system_score_gemma":0.000002730218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006066588,"about_ca_topic_score_gemma":0.000007628752,"domain_scores_codex":[0.9988815,0.00007569863,0.0003584128,0.0002399608,0.0002481124,0.0001963163],"domain_scores_gemma":[0.99946,0.00007632003,0.0003167276,0.00007644104,0.000004590981,0.00006589766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001260463,0.0006200138,0.03756637,0.00008906485,0.0004796191,0.0000739668,0.0008435803,0.298749,0.05269825,0.0001993903,0.001816248,0.6056041],"study_design_scores_gemma":[0.002166847,0.002085101,0.2070073,0.0004281579,0.0003891698,0.0001432826,0.001256933,0.7687994,0.0008559818,0.002879614,0.01361252,0.0003757235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7251325,0.0002059543,0.2698073,0.0004726104,0.0002950373,0.0004455901,0.000005668385,0.00002571615,0.003609612],"genre_scores_gemma":[0.9703812,0.00007149485,0.02811315,0.0001404437,0.00003378112,0.00001336733,0.00001084066,0.00001106389,0.001224655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6052283,"threshold_uncertainty_score":0.5833548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004583492507192762,"score_gpt":0.2385765786828238,"score_spread":0.233993086175631,"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."}}