{"id":"W4408430378","doi":"10.5194/egusphere-egu25-14223","title":"On the advancing frontier of deep learning in hydrology:  a hydrologic applications perspective","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Waterloo","funders":"","keywords":"Frontier; Perspective (graphical); Hydrology (agriculture); Hydrological modelling; Environmental science; Geology; Computer science; Geography; Artificial intelligence; Climatology; Archaeology; Geotechnical engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009557965,0.0003181044,0.0004572788,0.0001309328,0.000184466,0.00001914372,0.0007972355,0.0004172382,0.003087279],"category_scores_gemma":[0.0008689935,0.0002184015,0.0001447216,0.0004104447,0.0005206871,0.00003490758,0.001589807,0.00172248,0.0002844105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005990482,"about_ca_system_score_gemma":0.00002471417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001301729,"about_ca_topic_score_gemma":0.001063277,"domain_scores_codex":[0.9975153,0.000397319,0.0004469946,0.0008821723,0.0002962359,0.0004619808],"domain_scores_gemma":[0.9981829,0.0007794533,0.0002847862,0.0006710876,0.00002189983,0.00005985953],"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":[0.00003499504,0.0001583089,0.007164869,0.00001359313,0.00002495701,0.000002105687,0.001103095,0.9849521,0.0002385029,0.003639556,0.0002818535,0.002386077],"study_design_scores_gemma":[0.0005702825,0.0003729888,0.007753941,0.0001691571,0.0001126709,0.000008633574,0.0007201054,0.5492164,0.0003105272,0.4276564,0.01216733,0.0009415667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7533412,0.0001364328,0.02181332,0.002611914,0.0001195568,0.001103468,0.000008825614,0.0001711645,0.2206941],"genre_scores_gemma":[0.9908913,0.0000285931,0.005423487,0.0009480229,0.0000244024,0.0003485444,0.00001335789,0.0000146776,0.002307654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4357356,"threshold_uncertainty_score":0.997824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01526356058470408,"score_gpt":0.2677436371206251,"score_spread":0.252480076535921,"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."}}