{"id":"W4310986242","doi":"10.1103/physrevmaterials.6.113803","title":"Machine learning surrogate models for strain-dependent vibrational properties and migration rates of point defects","year":2022,"lang":"en","type":"article","venue":"Physical Review Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Regroupement Québécois sur les Matériaux de Pointe","funders":"Euratom Research and Training Programme; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; EUROfusion","keywords":"Statistical physics; Entropy (arrow of time); Dimensionality reduction; Surrogate data; Curse of dimensionality; Energy landscape; Surrogate model; Nonlinear system; Saddle point; Artificial intelligence; Materials science; Algorithm; Computer science; Machine learning; Mathematics; Thermodynamics; Physics; Quantum mechanics","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":[0.001183172,0.0004486397,0.0005850443,0.0005719599,0.000184663,0.0007743772,0.001018652,0.0009216088,0.001054875],"category_scores_gemma":[0.004603677,0.0002592796,0.000555423,0.0005313091,0.0007155716,0.001039546,0.0004788803,0.0008867778,0.0002270308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000614684,"about_ca_system_score_gemma":0.0005478666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001345755,"about_ca_topic_score_gemma":0.00112857,"domain_scores_codex":[0.9997213,0.0001023502,0.00001712717,0.00004641861,0.00008034256,0.00003236977],"domain_scores_gemma":[0.9983059,0.001061976,0.0002165236,0.0001736577,0.000196704,0.00004523708],"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":[0.00001245015,0.00001525829,0.0003948642,0.00001066359,0.000005287168,0.00001043574,0.000007001214,0.9924827,0.0004210718,0.004519179,0.00008138783,0.002039709],"study_design_scores_gemma":[6.41598e-7,0.000003094626,0.00003904496,7.900578e-7,3.203467e-7,0.000001191468,8.424306e-7,0.9988269,0.00009833591,0.001007109,0.00002068111,9.531843e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2884098,0.0002751754,0.7067004,0.0003613717,0.00004661943,0.00006729453,0.0005407791,0.000310644,0.003287916],"genre_scores_gemma":[0.9779158,0.0001415149,0.0193995,0.0000382628,0.0000119239,0.0001233821,0.0004201154,0.00002675891,0.001922663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001345755,"threshold_uncertainty_score":0.006257236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04447938553346107,"score_gpt":0.3006344680499253,"score_spread":0.2561550825164642,"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."}}