首页|North Carolina State University Reports Findings in Machine Learning (Machine Le arning Models to Predict Early Breakthrough of Recalcitrant Organic Micropolluta nts in Granular Activated Carbon Adsorbers)
North Carolina State University Reports Findings in Machine Learning (Machine Le arning Models to Predict Early Breakthrough of Recalcitrant Organic Micropolluta nts in Granular Activated Carbon Adsorbers)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Raleigh, North Carolina, by NewsRx journalists, research stated, “Granular activated carbon (GAC) adsorp tion is frequently used to remove recalcitrant organic micropollutants (MPs) fro m water. The overarching aim of this research was to develop machine learning (M L) models to predict GAC performance from adsorbent, adsorbate, and background w ater matrix properties.” The news correspondents obtained a quote from the research from North Carolina S tate University, “For model calibration, MP breakthrough curves were compiled an d analyzed to determine the bed volumes of water that can be treated until MP br eakthrough reaches ten percent of the influent MP concentration (BV10). Over 400 data points were split into training, validation, and testing sets. Seventeen v ariables describing MP, background water matrix, and GAC properties were explore d in ML models to predict log-transformed BV10 values. Using the ML models on th e testing set, predicted BV10 values exhibited mean absolute errors of 0.12 log units and were highly correlated with experimentally determined values ( 0.88). The top three drivers influencing BV10 predictions were the air-hexadecane parti tion coefficient and hydrogen bond acidity (Abraham parameters and ) of the MPs and the dissolved organic carbon concentration of the GAC influent water.”
RaleighNorth CarolinaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
