{"id":"W4389885075","doi":"10.5194/hess-2023-282","title":"Closing the data gap: runoff prediction in fully ungauged settings using LSTM","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Sample (material); Computer science; Context (archaeology); Benchmarking; Generalization; Field (mathematics); Artificial intelligence; Deep learning; Artificial neural network; Surface runoff; Operations research; Geology; Mathematics","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":[0.00109418,0.0007621824,0.0006756313,0.0004098284,0.0003140662,0.0008107508,0.001200152,0.00125666,0.00102369],"category_scores_gemma":[0.003442951,0.0003262373,0.0004450608,0.0006825165,0.0006943938,0.001978923,0.001316841,0.001446058,0.0002882429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007615587,"about_ca_system_score_gemma":0.0009743581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0152348,"about_ca_topic_score_gemma":0.01481981,"domain_scores_codex":[0.9996511,0.0001101122,0.00001867479,0.0001241419,0.00003530346,0.00006072801],"domain_scores_gemma":[0.9992049,0.0004526601,0.00007377595,0.0001061884,0.0001106596,0.0000519086],"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":[0.0003126885,0.000129594,0.006724386,0.00005839437,0.00006609514,0.0001907044,0.000107142,0.9469608,0.001538966,0.0009006684,0.002073235,0.04093722],"study_design_scores_gemma":[0.000005556599,0.00001509549,0.0003931676,0.000002931405,0.000002791729,0.000004467123,0.00001631819,0.9984217,0.0002839111,0.0007756525,0.00007560726,0.000002852768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8631927,0.000853817,0.1289387,0.001131136,0.0001400032,0.00004525478,0.0009934879,0.002477644,0.002227222],"genre_scores_gemma":[0.9909965,0.00004522221,0.007933957,0.00009860018,0.00002053244,0.00001495865,0.0005454369,0.00002974378,0.0003148923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0152348,"threshold_uncertainty_score":0.03029227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1028070653258622,"score_gpt":0.2978763018645202,"score_spread":0.195069236538658,"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."}}