{"id":"W4388644149","doi":"10.1016/j.conbuildmat.2023.134083","title":"Forecasting unconfined compressive strength of calcium sulfoaluminate cement mixtures using ensemble machine learning techniques integrated with shapely-additive explanations","year":2023,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Concrete and Cement Materials Research","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Compressive strength; Ensemble learning; Boosting (machine learning); Cement; Extreme learning machine; Shrinkage; Feature (linguistics); Artificial intelligence; Feature selection; Ensemble forecasting; Machine learning; Computer science; Pattern recognition (psychology); Mathematics; Materials science; Artificial neural network; Composite material","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004246985,0.0006468716,0.0004306495,0.0008000085,0.0001721727,0.000357567,0.0004846219,0.0007500463,0.000424124],"category_scores_gemma":[0.00111804,0.0002637805,0.000646243,0.0004959993,0.000178512,0.00073138,0.000254131,0.000579996,0.0001354261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005256445,"about_ca_system_score_gemma":0.0003945837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01035863,"about_ca_topic_score_gemma":0.01621259,"domain_scores_codex":[0.9998943,0.00001808037,0.000007287003,0.00003660927,0.00002668955,0.000017087],"domain_scores_gemma":[0.9994285,0.0003034784,0.00007895986,0.00003977779,0.0001157308,0.00003355682],"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":[0.0004021175,0.0002626193,0.02729288,0.00005011001,0.0001117567,0.000124488,0.00003825443,0.8913692,0.02049043,0.0003620352,0.0005053062,0.05899087],"study_design_scores_gemma":[0.000002202905,0.0000105062,0.00227267,6.433689e-7,0.000005990425,0.000002252287,0.000002502492,0.9963281,0.001278679,0.00006748168,0.00002597267,0.000003039444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9759485,0.0001777943,0.02282237,0.00006916426,0.00003605967,0.000009190389,0.000206922,0.0002388294,0.0004911136],"genre_scores_gemma":[0.9964741,0.00003861172,0.003087038,0.000006997639,0.00000928578,0.000004153412,0.0001913755,0.000008664944,0.0001797254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01035863,"threshold_uncertainty_score":0.02059668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03477574948928393,"score_gpt":0.2689385908361584,"score_spread":0.2341628413468745,"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."}}