{"id":"W4399585942","doi":"10.1038/s41598-024-63159-9","title":"Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"CO2 Sequestration and Geologic Interactions","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Christian-Albrechts-Universität zu Kiel","keywords":"Gradient boosting; Boosting (machine learning); Solubility; Computer science; Artificial intelligence; Chemistry; Random forest","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":[0.0008379839,0.000578969,0.0006153009,0.0003871324,0.0001734609,0.000467827,0.0005711951,0.0006152331,0.0004055316],"category_scores_gemma":[0.001126197,0.000224285,0.0005415801,0.0003031766,0.0002603733,0.0004203846,0.0003188769,0.0004631986,0.0001371622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003909782,"about_ca_system_score_gemma":0.0004712143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00486775,"about_ca_topic_score_gemma":0.003347337,"domain_scores_codex":[0.9998347,0.00005634344,0.000008799193,0.00003545071,0.00003687542,0.00002785404],"domain_scores_gemma":[0.9997116,0.0001546311,0.00002920462,0.00001625779,0.00007393678,0.00001438881],"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":[0.00006972278,0.0000655902,0.002338215,0.00002356417,0.00003219757,0.00002601197,0.00001781661,0.9649149,0.004428396,0.0005572145,0.0002283523,0.02729797],"study_design_scores_gemma":[7.697722e-7,0.000007700361,0.000104879,4.180699e-7,0.000001143878,9.127045e-7,5.877357e-7,0.9994519,0.0003195051,0.00008723036,0.00002421175,8.260931e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3758703,0.0004094424,0.6208069,0.0002442738,0.00006886957,0.00007492502,0.000100926,0.0006688721,0.001755488],"genre_scores_gemma":[0.9645127,0.00007008477,0.03465901,0.00003830548,0.00001556479,0.00003369147,0.00006364632,0.00001248495,0.0005945851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00486775,"threshold_uncertainty_score":0.009678841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02520073616333747,"score_gpt":0.2657120970334429,"score_spread":0.2405113608701054,"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."}}