{"id":"W2621194191","doi":"10.5194/tc-12-891-2018","title":"Improving gridded snow water equivalent products in British Columbia, Canada: multi-source data fusion by neural network models","year":2018,"lang":"en","type":"article","venue":"˜The œcryosphere","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pacific Institute for Climate Solutions; University of Victoria; Environment and Climate Change Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Goddard Space Flight Center; Ministry of Environment; National Aeronautics and Space Administration","keywords":"Snow; Environmental science; Water equivalent; Linear regression; Physical geography; Mean absolute error; Artificial neural network; Regression; Vegetation (pathology); Climatology; Meteorology; Geography; Mean squared error; Statistics; Mathematics; Geology; Computer 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003915589,0.0001662385,0.0002380268,0.000002787556,0.0008435279,0.0003048271,0.0008128298,0.00006748666,0.001458259],"category_scores_gemma":[0.00003988944,0.000155524,0.00002867872,0.0003141708,0.0001483934,0.0003197302,0.0002816015,0.0002298485,0.00002692887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002922448,"about_ca_system_score_gemma":0.0001648021,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9865984,"about_ca_topic_score_gemma":0.9997443,"domain_scores_codex":[0.997787,0.00009034144,0.0003600334,0.0006194856,0.0003624581,0.0007806576],"domain_scores_gemma":[0.9988841,0.00008100209,0.00009373613,0.0007250868,0.000102235,0.0001137936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002349063,0.0000489756,0.3901567,0.00003564174,0.00003718753,0.0000294963,0.0004729487,0.03062236,0.00003976999,4.90835e-7,0.4263072,0.1522257],"study_design_scores_gemma":[0.0004974438,0.00007662151,0.2774261,0.00004591879,0.00002736762,0.00001505301,0.0006790273,0.5916319,0.000005154705,0.0000377306,0.1291963,0.0003613469],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926311,0.003487626,0.0006126207,0.000784039,0.001348174,0.0005687808,0.0003727101,0.00005587506,0.0001390769],"genre_scores_gemma":[0.9904974,0.0001058332,0.001073304,0.00100819,0.0007840088,0.000006400855,0.0007312293,0.00001512296,0.005778578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5610095,"threshold_uncertainty_score":0.9994546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03326244423954439,"score_gpt":0.2035161409178028,"score_spread":0.1702536966782584,"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."}}