{"id":"W4405565140","doi":"10.1016/j.jhydrol.2024.132519","title":"Interpretation of glacier mass change within the Upper Yukon Watershed from GRACE using Explainable Automated Machine Learning Algorithms","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; University of Northern British Columbia; University of Washington","keywords":"Watershed; Glacier; Interpretation (philosophy); Geology; Algorithm; Hydrology (agriculture); Artificial intelligence; Geomorphology; Physical geography; Computer science; Machine learning; Geotechnical engineering; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004594541,0.000350869,0.0001756382,0.0009047316,0.0002292598,0.0005981133,0.0004101342,0.0003686775,0.0008669395],"category_scores_gemma":[0.001789926,0.0001224998,0.0006210273,0.0005110711,0.0002842753,0.0004627185,0.000431048,0.0003656381,0.0001043082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008562473,"about_ca_system_score_gemma":0.0007872015,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03818241,"about_ca_topic_score_gemma":0.04479529,"domain_scores_codex":[0.999902,0.00002862724,0.000008484813,0.00002780132,0.00001710239,0.00001604486],"domain_scores_gemma":[0.9996607,0.0001534974,0.00005589109,0.00005254725,0.0000611707,0.00001619109],"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":[0.00005878674,0.00004774285,0.05493021,0.00004665099,0.0001152421,0.0002371244,0.0001868442,0.8707712,0.00249122,0.00890014,0.001210332,0.0610045],"study_design_scores_gemma":[0.000003581509,0.000006630804,0.00576451,0.000003603796,0.00001009828,0.00001170657,0.00003526509,0.9899287,0.000346264,0.003476398,0.0004074764,0.000005827617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7338562,0.0002525005,0.2590323,0.0007061993,0.00002885152,0.00004148043,0.001959943,0.001675481,0.002447064],"genre_scores_gemma":[0.9786277,0.00004773418,0.01999498,0.00002743926,0.00000977847,0.00001450536,0.0008939176,0.00002945583,0.0003544209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9618176,"threshold_uncertainty_score":0.07592034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02700545505457869,"score_gpt":0.2512069255006109,"score_spread":0.2242014704460322,"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."}}