{"id":"W4405363780","doi":"10.1016/j.dche.2024.100207","title":"Ensemble machine learning to accelerate industrial decarbonization: Prediction of Hansen solubility parameters for streamlined chemical solvent selection","year":2024,"lang":"en","type":"article","venue":"Digital Chemical Engineering","topic":"Crystallization and Solubility Studies","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Natural Resources Canada","funders":"Canadian Forest Service; Office of Energy Research and Development; Natural Sciences and Engineering Research Council of Canada","keywords":"Solubility; Selection (genetic algorithm); Solvent; Computer science; Hildebrand solubility parameter; Machine learning; Process (computing); Chemistry; Process engineering; Biochemical engineering; Artificial intelligence; Thermodynamics; Engineering; Organic chemistry; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001673521,0.0001586193,0.0002233787,0.00007001201,0.00003780432,0.0001740003,0.00008861369,0.0001075199,0.00002169868],"category_scores_gemma":[0.000930468,0.0001587619,0.00009338324,0.0003196676,0.00002813308,0.0002362412,0.00007034574,0.000130606,0.00000364172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001375669,"about_ca_system_score_gemma":0.00003712555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008594041,"about_ca_topic_score_gemma":8.024442e-7,"domain_scores_codex":[0.9988385,0.000007373209,0.0003764756,0.0003480641,0.0001958559,0.0002336987],"domain_scores_gemma":[0.9994754,0.0001886721,0.00003592253,0.0000924268,0.000107403,0.0001002196],"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":[0.00007237223,0.00004761507,0.0003052785,0.0001547199,0.00002516658,4.102767e-7,0.0002444489,0.03007222,0.9678683,0.00008664882,0.000116135,0.001006646],"study_design_scores_gemma":[0.0002372585,0.00006710554,0.00001120578,0.00006656435,0.00001731569,0.000002382588,0.00002426785,0.2770216,0.7213264,0.00005171354,0.001051757,0.0001223618],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8859777,0.000044882,0.1127647,0.00009276959,0.0002965273,0.000330647,0.0001105576,0.0003395315,0.00004262559],"genre_scores_gemma":[0.9980345,0.000001820188,0.001507045,0.000008394312,0.0001488422,0.0000608237,0.0001669019,0.00002544423,0.00004624576],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2469494,"threshold_uncertainty_score":0.6474124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03210325346859885,"score_gpt":0.240626866084187,"score_spread":0.2085236126155881,"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."}}