{"id":"W4388294481","doi":"10.1002/jrs.6611","title":"Machine learning methods applied to combined Raman and LIBS spectra: Implications for mineral discrimination in planetary missions","year":2023,"lang":"en","type":"article","venue":"Journal of Raman Spectroscopy","topic":"Laser-induced spectroscopy and plasma","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Agencia Estatal de Investigación; Ministerio de Economía y Competitividad; European Commission","keywords":"Raman spectroscopy; Mars Exploration Program; Laser-induced breakdown spectroscopy; Support vector machine; Artificial intelligence; Characterization (materials science); Calcite; Mineral; Machine learning; Analytical Chemistry (journal); Artificial neural network; Materials science; Spectroscopy; Pattern recognition (psychology); Computer science; Biological system; Mineralogy; Chemistry; Nanotechnology; Optics; Physics; Environmental chemistry; Astrobiology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006504443,0.0002267142,0.000423629,0.0005951829,0.0001380382,0.00008073099,0.0001939515,0.0001055916,0.00003061924],"category_scores_gemma":[0.0001083833,0.0002093317,0.00008695031,0.0005584332,0.00002205992,0.0001553337,0.00003025404,0.0005324967,0.000007083942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128627,"about_ca_system_score_gemma":0.00003526521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001137252,"about_ca_topic_score_gemma":0.00007409287,"domain_scores_codex":[0.9986546,0.00006266221,0.0005319117,0.0001985882,0.0001375829,0.0004146608],"domain_scores_gemma":[0.9990873,0.0003686957,0.0001242934,0.000155508,0.00003670201,0.0002275185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002760067,0.00006940537,0.003090028,0.00009993222,0.00007648055,0.00001422784,0.0009544939,0.02015385,0.9649869,0.004037793,0.003624816,0.002616042],"study_design_scores_gemma":[0.007014862,0.002407985,0.313406,0.0003307658,0.0002982559,0.0002409663,0.0009191221,0.1101368,0.5178019,0.02935934,0.01675454,0.0013294],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9446548,0.0002016986,0.04907236,0.003197454,0.0004625789,0.0005864637,0.00004585115,0.000207177,0.001571611],"genre_scores_gemma":[0.8943633,0.0003151203,0.1045854,0.00008102355,0.0002783716,0.00003545187,0.0001194271,0.00005252651,0.0001693735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.447185,"threshold_uncertainty_score":0.85363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02183891707168372,"score_gpt":0.3140706201011259,"score_spread":0.2922317030294422,"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."}}