{"id":"W4387666276","doi":"10.1016/j.mattod.2023.09.007","title":"Tailoring the mechanical properties of 3D microstructures: A deep learning and genetic algorithm inverse optimization framework","year":2023,"lang":"en","type":"article","venue":"Materials Today","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inverse; Microstructure; Genetic algorithm; Computer science; Materials science; Process (computing); Transferability; Range (aeronautics); Limiting; Algorithm; Mathematical optimization; Mechanical engineering; Machine learning; Mathematics; Engineering; Composite material","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":[0.001316254,0.0002255021,0.0003520629,0.0001003674,0.0004022307,0.0003678948,0.0004382578,0.0001384511,0.001170043],"category_scores_gemma":[0.001103159,0.000151606,0.00002854417,0.0003165576,0.0003304407,0.0001735932,0.000485529,0.0001459305,0.0001174093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002356514,"about_ca_system_score_gemma":0.00003323505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001226088,"about_ca_topic_score_gemma":0.000003463997,"domain_scores_codex":[0.9976717,0.0005427128,0.0005192037,0.0004517836,0.0003856504,0.0004289756],"domain_scores_gemma":[0.9990539,0.0001705349,0.0003020281,0.0003209462,0.00008298583,0.00006958249],"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":[0.00002858176,0.000006142707,0.00007715614,0.00009789264,0.000004734311,0.000006748547,0.0009973048,0.04674936,0.9511619,0.00009433569,0.0000139342,0.000761864],"study_design_scores_gemma":[0.0001854836,0.00008384477,0.0008876442,0.0001605416,0.00002384812,0.00003793415,0.0003027325,0.04829798,0.9490723,0.0004958787,0.0002106885,0.0002411365],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9826651,0.00008721048,0.01515936,0.0001853198,0.001322883,0.0003155263,0.00001477836,0.0002364161,0.00001340452],"genre_scores_gemma":[0.8495187,0.0001324492,0.1498305,0.00008114074,0.000232307,0.00005373058,0.000007614466,0.00004176901,0.0001017827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1346711,"threshold_uncertainty_score":0.999743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229509010684038,"score_gpt":0.2416701502508446,"score_spread":0.2293750601440042,"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."}}