Machine learning for membrane design and discovery

Understanding Single-Protein Fouling in Micro- and Ultrafiltration Systems via Machine-Learning-Based Models

“…Overall, these results show the efficacy of these data-driven machine-learning models to enhance the understanding on and prediction of protein fouling, without the need for any governing equations. A more uniform way of reporting the important parameters available databases would improve the quality of the database, and thus enhance the capability of ML models in understanding and predicting protein fouling in the future . Beyond membrane-fouling, such tools are useful in the absence of first-principles understanding for many naturally occurring phenomena in such industrially relevant processes.…”

Sustainable valorisation of food waste into engineered biochars for CO2 capture towards a circular economy

“…Machine learning-aided synthesis approaches Machine learning (ML) is one of the most widespread datadriven approaches in many fields. For example, ML approaches have been applied in many studies on material discovery, process optimization, and environmental protection [48][49][50] as they provide valuable insights that aid the understanding, interpretation, and inverse design of complicated systems. Moreover, as shown in Fig.…”

Data-driven future for nanofiltration: Escaping linearity

“…To effectively examine these molecular level interactions, digitalization of collected data, miniaturization of testing methods, and automation considerations for material deployment must be co-developed alongside new material design. For interested readers, we recommend review articles concerning machine learning (ML) in membrane science ( Nunes et al, 2020 ;Artrith et al, 2021 ;Yin et al, 2022 ).…”