{"id":"W4414768364","doi":"10.3390/hydrology12100261","title":"Using Entity-Aware LSTM to Enhance Streamflow Predictions in Transboundary and Large Lake Basins","year":2025,"lang":"en","type":"article","venue":"Hydrology","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Oceanic and Atmospheric Administration; Cooperative Institute for Great Lakes Research","keywords":"Streamflow; Hydrological modelling; Drainage basin; Scalability; Catchment hydrology; Water resources; Hydrology (agriculture)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001852045,0.0001068379,0.0001567351,0.0001115231,0.0002489217,0.000009539984,0.0001072499,0.00008481511,0.0005368875],"category_scores_gemma":[0.00001396317,0.0001087094,0.00002210352,0.0002500352,0.0001948728,0.0001055464,0.0002290507,0.0001285743,0.0000654776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004497604,"about_ca_system_score_gemma":0.000006464149,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000201063,"about_ca_topic_score_gemma":0.02992374,"domain_scores_codex":[0.9990606,0.00007256472,0.0001482737,0.0003336431,0.00005914725,0.000325714],"domain_scores_gemma":[0.9997639,0.00003105027,0.00001778321,0.0001446938,0.000002386891,0.00004020275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006988851,0.0002224664,0.9843138,0.00002765484,0.00005992718,0.00004217723,0.001398183,0.008579756,0.0009613169,0.0005376663,0.001950713,0.001836439],"study_design_scores_gemma":[0.00126884,0.0002597651,0.6043736,0.00004779521,0.0001266766,0.0000121491,0.0002080541,0.0304591,0.0006968228,0.005542528,0.3565852,0.0004194158],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685931,0.00004735995,0.01798023,0.003221117,0.0002059947,0.0002291885,0.00003189735,0.00003847881,0.009652589],"genre_scores_gemma":[0.9966048,0.00004415521,0.0002946757,0.001987134,0.00001260896,0.000029237,0.000006625721,0.00000482395,0.001015945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3799402,"threshold_uncertainty_score":0.9877777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007936712895862253,"score_gpt":0.2681530302185337,"score_spread":0.2602163173226715,"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."}}