{"id":"W4386274145","doi":"10.1016/j.scitotenv.2023.166678","title":"Machine learning based prediction and experimental validation of arsenite and arsenate sorption on biochars","year":2023,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Arsenic contamination and mitigation","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Biochar; Arsenate; Adsorption; Arsenite; Mean squared error; Arsenic; Sorption; Coefficient of determination; AdaBoost; Chemistry; Environmental chemistry; Environmental science; Mathematics; Statistics; Machine learning; Computer science; Support vector machine; Organic chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0005833794,0.00006889085,0.00005734608,0.00004334839,0.00029637,0.000008329046,0.0001027673,0.00001837201,0.0001369767],"category_scores_gemma":[0.00002756912,0.00004421879,0.00002306405,0.0001897057,0.0009494554,0.0001121699,0.0002649411,0.00005462044,0.00002587544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001083673,"about_ca_system_score_gemma":0.000004399496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003067786,"about_ca_topic_score_gemma":4.808604e-7,"domain_scores_codex":[0.9990808,0.00005990617,0.000135667,0.0001822478,0.0004364268,0.0001049859],"domain_scores_gemma":[0.9996471,0.0000355788,0.0001281186,0.0001537066,0.000002228447,0.00003321555],"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":[0.00001786151,0.00002497153,0.0007333848,0.000002053672,0.000001877181,8.291146e-8,0.0007316313,0.1355726,0.861209,0.00007007922,0.000007933647,0.001628439],"study_design_scores_gemma":[0.000257794,0.0001158964,0.1239737,0.00001221666,0.000008788864,0.000002923304,0.0002396961,0.1664271,0.7087948,0.00007845515,0.00003843345,0.00005018717],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988241,0.00001328282,0.00002803604,0.0004479814,0.00005477439,0.0001958995,0.000007228178,0.0000125709,0.0004161049],"genre_scores_gemma":[0.9991435,0.0000245391,0.00003101573,0.00001206001,0.000004302279,0.000007836605,0.000004284941,0.000004203281,0.0007682056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1524142,"threshold_uncertainty_score":0.3498308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009443802533158923,"score_gpt":0.2076700988335653,"score_spread":0.1982262963004064,"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."}}