{"id":"W4221024110","doi":"10.5194/egusphere-egu22-3281","title":"Assessment of Transfer Learning Techniques to Improve Streamflow Predictions in Data-Sparse Regions","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; Institut National de la Recherche Scientifique","funders":"","keywords":"Streamflow; Flood forecasting; Hydrometeorology; Environmental science; Precipitation; Drainage basin; Flood myth; Meteorology; Hydrology (agriculture); Geography; Cartography; Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004552607,0.001828059,0.0007020329,0.001074756,0.0003875217,0.0008534107,0.001521006,0.001596605,0.001486872],"category_scores_gemma":[0.01258399,0.0002844114,0.0007250333,0.0007518425,0.0005354477,0.002210415,0.001380781,0.001668598,0.0005620859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000980386,"about_ca_system_score_gemma":0.001065712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01015829,"about_ca_topic_score_gemma":0.004978463,"domain_scores_codex":[0.9992862,0.0002493896,0.00006027762,0.0001807412,0.0001391795,0.0000843035],"domain_scores_gemma":[0.9955936,0.002661919,0.0002191974,0.0003830945,0.0009506512,0.0001914399],"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":[0.0006400543,0.0006918176,0.007169557,0.0002494166,0.0002202591,0.00009492099,0.00007156913,0.7613019,0.002333026,0.0007306918,0.003250351,0.2232465],"study_design_scores_gemma":[0.0000267445,0.0002369367,0.001078812,0.00001809149,0.0000244228,0.000008910979,0.00002384404,0.9965327,0.001271606,0.0005357554,0.0002358132,0.000006395626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8114117,0.006592293,0.1620308,0.002599558,0.0006420845,0.0005042632,0.001227681,0.004359137,0.01063255],"genre_scores_gemma":[0.963526,0.0006061968,0.03276922,0.0002190745,0.0001017093,0.0001298149,0.001163267,0.00008444883,0.001400266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01015829,"threshold_uncertainty_score":0.02407676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02955579270063472,"score_gpt":0.2967222165527326,"score_spread":0.2671664238520978,"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."}}