{"id":"W4417227211","doi":"10.1144/gh2025-4","title":"Unravelling the power of neural networks for flood prediction across complex hydrological systems","year":2025,"lang":"en","type":"article","venue":"GeoHorizons","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science Foundation","keywords":"Flood myth; Hydrometeorology; Artificial neural network; Flooding (psychology); Feature (linguistics); Interpolation (computer graphics); Warning system; Reliability (semiconductor); Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089018,0.0009545375,0.0003576603,0.0003830896,0.0002378164,0.001007926,0.0006518494,0.0005757948,0.0008848319],"category_scores_gemma":[0.004015259,0.00039329,0.0003997177,0.0004668677,0.0004700311,0.002231614,0.0006661114,0.001493767,0.000150438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005936307,"about_ca_system_score_gemma":0.0006444636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01483055,"about_ca_topic_score_gemma":0.0208636,"domain_scores_codex":[0.9998384,0.00005362697,0.00001137002,0.00004715124,0.00003128126,0.00001831433],"domain_scores_gemma":[0.9988633,0.0008622822,0.00007595798,0.00006163426,0.0001086606,0.0000280513],"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":[0.00003948772,0.00002925757,0.004517834,0.00006907863,0.00008396272,0.00004954273,0.00007151633,0.9278445,0.002510416,0.002546549,0.0003095343,0.06192832],"study_design_scores_gemma":[0.000001354975,0.00001265277,0.0004879797,0.000006460203,0.000005638667,0.000004751019,0.00001175912,0.9971946,0.0003570164,0.001798064,0.0001168178,0.000002758254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5182243,0.004533955,0.4674337,0.002782951,0.000127404,0.00005165249,0.0003803774,0.0009833403,0.005482375],"genre_scores_gemma":[0.9572556,0.001213723,0.04037863,0.00007833975,0.0000450318,0.0000201663,0.0001429845,0.00003396801,0.0008315162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01483055,"threshold_uncertainty_score":0.02948844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02632417619365111,"score_gpt":0.2681598292556399,"score_spread":0.2418356530619888,"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."}}