{"id":"W2923568062","doi":"10.5194/amt-12-4591-2019","title":"Development and validation of a supervised machine learning radar Doppler spectra peak-finding algorithm","year":2019,"lang":"en","type":"article","venue":"Atmospheric measurement techniques","topic":"Atmospheric aerosols and clouds","field":"Environmental Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Leibniz-Institut für Troposphärenforschung; Leibniz-Gemeinschaft; Office of Science; Biological and Environmental Research; European Commission; Deutsche Forschungsgemeinschaft; U.S. Department of Energy","keywords":"Algorithm; Radar; Doppler effect; Doppler radar; Zenith; Remote sensing; Computer science; Smoothing; Spectral line; Cloud computing; Meteorology; Environmental science; Geology; Physics; Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008838893,0.0002484231,0.0002934597,0.00000108949,0.0001348949,0.00003049144,0.000203437,0.00008888906,0.001824326],"category_scores_gemma":[0.00002341224,0.0002224057,0.00005427276,0.0002734764,0.00007684882,0.000186007,0.0001791648,0.0001742579,0.00005548988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002967071,"about_ca_system_score_gemma":0.00003173949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003232432,"about_ca_topic_score_gemma":0.00001672214,"domain_scores_codex":[0.9979256,0.00007281305,0.0004145177,0.0004196532,0.0008545985,0.0003128301],"domain_scores_gemma":[0.9994088,0.00001704218,0.0002086912,0.0002413054,0.00003201843,0.00009213001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003441117,0.0001913421,0.2606764,0.00007706857,0.00007809152,0.000005581624,0.001707314,0.0001072872,0.2982426,0.00009412133,0.0003687844,0.438417],"study_design_scores_gemma":[0.001285871,0.0006809772,0.07069405,0.0002497915,0.00008550489,0.00003288578,0.0008521061,0.01322742,0.8453292,0.0002749617,0.06602655,0.001260733],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9266065,0.000251009,0.0649767,0.00005297257,0.00006636007,0.0007080986,9.693581e-7,0.0002589277,0.007078415],"genre_scores_gemma":[0.53649,0.0000629161,0.4630164,0.00004187426,0.00001434675,0.00003089339,0.000005631519,0.00002533112,0.0003126668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5470866,"threshold_uncertainty_score":0.9990882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818093698511782,"score_gpt":0.2154625447770543,"score_spread":0.1972816077919365,"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."}}