首页|Investigators from University of Manchester Report New Data on Machine Learning (Multi-scale Computational Design of Metalorganic Frameworks for Carbon Capture Using Machine Learning and Multi-objective Optimization)
Investigators from University of Manchester Report New Data on Machine Learning (Multi-scale Computational Design of Metalorganic Frameworks for Carbon Capture Using Machine Learning and Multi-objective Optimization)
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 – Research findings on Machine Learning are discussed in a new report. According to news reporting originating from Manc hester, United Kingdom, by NewsRx correspondents, research stated, “In this arti cle, we computationally design a series of metal-organic frameworks (MOFs) optim ized for postcombustion carbon capture. Our workflow includes assembling buildin g blocks and topologies into an initial set of hypothetical MOFs, using genetic algorithms to optimize this initial set for high CO2/N-2 selectivity, and furthe r evaluating the top materials through process-level modeling of their performan ce in a modified Skarstrom cycle.” Our news editors obtained a quote from the research from the University of Manch ester, “We identify two groups of MOFs that exhibit excellent process performanc e: one with relatively small pores in the range of 3-5 & Aring; an d another with larger pores of 6-30 & Aring;. The performance of t he first group is driven effectively by the exclusion of N-2 from adsorption, wi th binding sites able to accommodate only CO2 molecules. The second group, with larger pores, features binding sites where CO2 molecules form multiple interacti ons with oxygen and functional groups of several building blocks, leading to a h igh CO2/N-2 selectivity. Within the employed process model and its assumptions, the materials generated in this study substantially outperform 13X reference zeo lites, in silico optimized ion-exchanged LTA zeolites, and CALF-20. While this s tudy does not address the synthesizability, stability, or water interactions of the proposed materials, it marks a significant step forward in developing practi cal MOFs for carbon capture in three key areas. First, it introduces a generativ e workflow based on the process-level performance of new materials. Second, it i dentifies structural features of optimal MOFs for carbon capture, which can serv e as design guidelines for future development.”
ManchesterUnited KingdomEuropeCybo rgsEmerging TechnologiesMachine LearningUniversity of Manchester
NETL
NSTL
