{"id":"W3171320818","doi":"10.5194/hess-25-3017-2021","title":"Investigating ANN architectures and training to estimate snow water equivalent from snow depth","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; Université de Sherbrooke","funders":"Environment and Climate Change Canada","keywords":"Snowpack; Snow; Snowmelt; Perceptron; Environmental science; Water equivalent; Artificial neural network; Range (aeronautics); Meteorology; Computer science; Machine learning; Geography; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.000444524,0.0001357801,0.00023876,0.0000353472,0.0009101938,0.000127084,0.0001142402,0.00005445239,0.0001695044],"category_scores_gemma":[0.0001169982,0.00008961572,0.00002478029,0.0001955481,0.000377809,0.00008417164,0.00005689085,0.00009132669,0.00002672363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001235142,"about_ca_system_score_gemma":0.0000403317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001353112,"about_ca_topic_score_gemma":0.01174459,"domain_scores_codex":[0.998638,0.0001125814,0.0002124435,0.0004504717,0.0001727012,0.0004137399],"domain_scores_gemma":[0.9992886,0.0003594935,0.00004401629,0.000101151,0.00002464155,0.0001821052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007650413,0.000004365751,0.9164715,0.00003049845,0.00003379865,0.00003896442,0.008142457,0.02553869,0.0003245343,0.0003015388,0.00005240301,0.04905363],"study_design_scores_gemma":[0.0001849187,0.000183546,0.9338027,0.000113458,0.00002321399,0.0001178641,0.004663868,0.05798118,0.000389178,0.0008214908,0.001509854,0.0002086976],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937791,0.001777108,0.0002435769,0.001714477,0.0003245637,0.00009702386,0.00002497628,0.00004332815,0.001995855],"genre_scores_gemma":[0.9937345,0.00002143604,0.005361015,0.0006862487,0.0001071324,0.000002656878,0.00002042348,0.000002057673,0.00006448846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04884493,"threshold_uncertainty_score":0.7000567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04615429935927689,"score_gpt":0.2604692983607468,"score_spread":0.2143149990014699,"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."}}