首页|Department of Biotechnology Reports Findings in Machine Learning (Accurate Machi ne Learning for Predicting the Viscosities of Deep Eutectic Solvents)
Department of Biotechnology Reports Findings in Machine Learning (Accurate Machi ne Learning for Predicting the Viscosities of Deep Eutectic Solvents)
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 out of Andhra Pradesh,India,by NewsRx editors,research stated,"Deep eutectic solvents (DESs) are emerging as environmentally friendly designer solvents for mass transport and heat trans fer processes in industrial applications; however,the lack of accurate tools to predict and thus control their viscosities under both a range of environmental factors and formulations hinders their general application.While DESs may serve as designer solvents,with nearly unlimited combinations,this unfortunately ma kes it experimentally infeasible to comprehensively measure the viscosities of a ll DESs of potential industrial interest." Our news journalists obtained a quote from the research from the Department of B iotechnology,"To assist in the design of DESs,we have developed several new ma chine learning (ML) models that accurately and rapidly predict the viscosities o f a diverse group of DESs at different temperatures and molar ratios using,to d ate,one of the most comprehensive data sets containing the properties of over 6 70 DESs over a wide range of temperatures (278.15-385.25 K).Three ML models,in cluding support vector regression (SVR),feed forward neural networks (FFNNs),a nd categorical boosting (CatBoost),were developed to predict DES viscosity as a function of temperature and molar ratio and contrasted with multilinear and two -factor polynomial regression baselines.Quantum chemistry-based,COSMO-RS-deriv ed sigma profile (s-profile) features were used as inputs for the ML models.The CatBoost model is excellent at externally predicting DES viscosity,as indicate d by high (0.99) and low root-mean-square-error (RMSE) and average absolute rela tive deviations (AARD) (5.22%) values for the testing data sets,an d 98% of the data points lie within the 15% of AARD deviations.Furthermore,SHapley additive explanation (SHAP) analysis was employ ed to interpret the ML results and rationalize the viscosity predictions."
NETL
NSTL
