{"id":"W4310741902","doi":"10.5194/egusphere-2022-938","title":"Automatic classification and segmentation of Snow Micro Penetrometer profiles with machine learning algorithms","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Horizon 2020; Swiss Polar Institute; Deutsche Forschungsgemeinschaft; European Commission; Alfred Wegener Institute Helmholtz Centre for Polar and Marine Research; WSL-Institut für Schnee- und Lawinenforschung SLF","keywords":"Snow; Snowpack; Computer science; Artificial intelligence; Machine learning; Segmentation; Artificial neural network; Perceptron; Algorithm; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007297119,0.001087145,0.0005247951,0.001577961,0.0003565268,0.0007699883,0.00091123,0.000864649,0.0007485036],"category_scores_gemma":[0.001665023,0.0003260725,0.0007823055,0.001073121,0.0002880512,0.0009217085,0.0004648172,0.0008695206,0.0007511342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009339262,"about_ca_system_score_gemma":0.0007681465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01118711,"about_ca_topic_score_gemma":0.0137285,"domain_scores_codex":[0.9995808,0.00007495736,0.00002936366,0.000163714,0.00007794214,0.0000732628],"domain_scores_gemma":[0.9991303,0.0002646488,0.0001055618,0.0001139651,0.0003346049,0.00005094742],"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":[0.0004244878,0.0006124636,0.03325089,0.0001484719,0.0001541219,0.0001723062,0.0002129284,0.530022,0.02191588,0.0008219166,0.007249233,0.4050153],"study_design_scores_gemma":[0.000003895614,0.00001400537,0.001847273,0.000005022162,0.000003763241,0.000007006028,0.00002177911,0.9954448,0.002183318,0.0002476663,0.0002177558,0.000003809151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6977544,0.0005787066,0.2881278,0.0003698461,0.0001704665,0.0002204281,0.001888063,0.00750012,0.003390353],"genre_scores_gemma":[0.856967,0.0001046172,0.1375342,0.00008638907,0.00003383858,0.00009755959,0.003620399,0.0001418764,0.001414208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01118711,"threshold_uncertainty_score":0.02224398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03194358135416669,"score_gpt":0.2414534727382895,"score_spread":0.2095098913841228,"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."}}