{"id":"W2797692099","doi":"10.5194/hess-2018-168","title":"HESS Opinions: Deep learning as a promising avenue toward knowledge discovery in water sciences","year":2018,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Big data; Transformative learning; Data science; Variety (cybernetics); Deep learning; Computer science; Field (mathematics); Artificial intelligence; Set (abstract data type); Stakeholder; Political science; Sociology; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007105289,0.0001109919,0.0001167236,0.00004654769,0.0003234153,0.0001234255,0.0002676241,0.00005987409,0.00142719],"category_scores_gemma":[0.000194222,0.00006985493,0.00003067554,0.0002803155,0.0008406524,0.0003908652,0.000372961,0.000160538,0.002959903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001052565,"about_ca_system_score_gemma":0.00001130123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003867922,"about_ca_topic_score_gemma":0.0002349035,"domain_scores_codex":[0.9986998,0.0001074888,0.0001694568,0.0003979489,0.0001868629,0.0004383981],"domain_scores_gemma":[0.9997466,0.00005513866,0.00002792659,0.0001057871,0.00000450685,0.00006004721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001932724,0.001255662,0.5653502,0.00008908906,0.00003058799,0.0001112883,0.06014674,0.08126847,0.1274602,0.003002467,0.001397098,0.159695],"study_design_scores_gemma":[0.002751779,0.005187514,0.1041626,0.0008317041,0.00003708329,0.000182453,0.00166702,0.4598462,0.231233,0.06503218,0.1259871,0.003081335],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9366354,0.00001412213,0.0004495534,0.0004226754,0.0001559826,0.0001035357,1.696658e-7,0.00005942628,0.06215908],"genre_scores_gemma":[0.9966756,0.000001796166,0.001255178,0.0001570922,0.00007655729,0.000008279638,0.000001805088,0.000008299497,0.001815396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4611876,"threshold_uncertainty_score":0.9994856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03507288553710524,"score_gpt":0.2978376948507449,"score_spread":0.2627648093136397,"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."}}