{"id":"W4285095106","doi":"10.1007/s00521-022-07529-2","title":"Structural-optimized sequential deep learning methods for surface soil moisture forecasting, case study Quebec, Canada","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Preprocessor; Computer science; Data pre-processing; Data mining; Artificial intelligence; Machine learning; Standardization; Environmental science","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002847227,0.0001515195,0.0001716286,0.00001448037,0.002202071,0.00005769742,0.0001271681,0.00002563213,0.00001886617],"category_scores_gemma":[0.00002177656,0.0001422582,0.00004493574,0.0002095624,0.00005482398,0.00003505205,0.0003151025,0.0003264995,3.241256e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001798615,"about_ca_system_score_gemma":0.0000297478,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6791497,"about_ca_topic_score_gemma":0.7523206,"domain_scores_codex":[0.998722,0.0002414033,0.0002134861,0.0004071378,0.0001595351,0.0002564589],"domain_scores_gemma":[0.9992859,0.0003138556,0.0001361155,0.0001614599,0.00001505065,0.00008765324],"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":[0.00001103048,0.00002190074,0.005909621,0.000006843057,0.00001747524,0.00004868794,0.001129526,0.7181439,0.0006068375,0.000005256261,0.000200883,0.2738981],"study_design_scores_gemma":[0.0006122661,0.0000657274,0.004756777,0.000001667613,0.00006357741,0.001033947,0.006459696,0.9804699,0.00007828312,0.00005371916,0.006148921,0.0002554986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783779,0.00008973963,0.02006219,0.000193001,0.0001461073,0.0007270784,0.000002259115,0.00006885297,0.0003328358],"genre_scores_gemma":[0.9825333,5.35147e-7,0.0168543,0.0001449934,0.00009489204,0.00001537215,0.00001734803,0.00001916622,0.0003201361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2736426,"threshold_uncertainty_score":0.9990969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02244105369011835,"score_gpt":0.2954665577139,"score_spread":0.2730255040237817,"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."}}