{"id":"W3167890350","doi":"10.5194/egusphere-egu21-1644","title":"Improving Deep Learning hydrological time series modeling using Gaussian Filter preprocessing","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Series (stratigraphy); Time series; Streamflow; Computer science; Filter (signal processing); Preprocessor; Autoregressive integrated moving average; Autoregressive model; Artificial intelligence; Noise (video); Machine learning; Statistics; Geography; Mathematics; Cartography; Geology; Drainage basin","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004223331,0.000228218,0.0002454955,0.00002541075,0.0005648053,0.0001762909,0.0002044036,0.0001741917,0.008206756],"category_scores_gemma":[0.0004602119,0.0001889689,0.00008884456,0.0003177232,0.0001707307,0.0005070717,0.0006519376,0.0003983886,0.0005453212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432213,"about_ca_system_score_gemma":0.00001844176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001336851,"about_ca_topic_score_gemma":0.00002347258,"domain_scores_codex":[0.9978533,0.0001545211,0.0003267404,0.0007429317,0.0003265603,0.0005959048],"domain_scores_gemma":[0.999432,0.00005043467,0.0000891609,0.0002543322,0.00001775733,0.0001563587],"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":[0.00001302167,0.00002833263,0.005336496,0.000008576824,0.000005639918,0.00007485618,0.0001717805,0.8676949,0.119291,0.00001033283,0.000005556954,0.00735953],"study_design_scores_gemma":[0.0001178263,0.0000528884,0.0001934693,0.0000206008,0.00001767294,0.0001960255,0.00003887532,0.9945509,0.003782791,0.0006056573,0.0001495621,0.0002736985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9055625,0.00004120957,0.07277871,0.0001837128,0.00005221805,0.00006385938,3.518484e-7,0.0002980602,0.02101936],"genre_scores_gemma":[0.924574,0.000001907714,0.07247677,0.0003336504,0.00006664452,0.000003594173,0.000005160684,0.00002758446,0.002510696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1268561,"threshold_uncertainty_score":0.9926999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0226043929346843,"score_gpt":0.2344544224875279,"score_spread":0.2118500295528436,"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."}}