๐จ Revolutionizing Energy Efficiency in Chemical Separations! We’re thrilled to share our latest open access research ๐, just out in Nature Energy!
Our paradigm-shifting hybrid modeling approach combines cutting-edge machine learning with mechanistic insights, unlocking the potential to…
๐ slash energy use and COโ emissions by up to 90% in pharmaceutical purifications;
๐ achieve 40% energy reduction overall in chemical separations; and
๐ก enable membrane technology to enhance up to 74% of chemical separations.
We analyzed a staggering 7.1 million scenarios across a wide range of application domains to guide sustainable technology choices in the chemical industry.
๐ A huge congratulations to the team:
Gergล Ignรกcz ๐ค๐ – The Robot, who trained the AI
Aron Kristof Beke โ๏ธโก – The Energizer, who powered the separations
Viktor Toth โ๏ธ๐ฅผ – The Chemist, who cooked the drugs
๐จโ๐ป Dive into the future of energy-efficient separations here if you want to read the article, or listen to an AI-generated podcast:
Read the story behind the article in the KAUST Discovery magazine published under ‘Slashing industrial emissions using a hybrid model approach‘.
Read the commentary by Professor Michael Tsapatsis from Johns Hopkins University under ‘Facilitating decision making‘ published in the News & Views section of Nature Energy.
๐ Use our online open access tools to enhance your separations at the OSN Database: www.OSNdatabase.com








