A short narrative review that frames machine learning as data, representations and models, lists opportunities and drawbacks, and ends with three recommendations. Useful as a pointer to its sources; weak as a source itself. [read]
2026-10-11 / reading, machine-learning, chemical-engineering
A thirty-three page review of AI in process systems engineering with 174 references, a catalogue of reported results by function, a barrier list, and a roll call of industrial deployments. Every number in it is secondhand and the industrial evidence rests on company pages. [read]
2026-10-11 / reading, machine-learning, process-systems-engineering
A history of machine learning in chemical engineering along three threads, models, data and applications, with a four-step workflow, three application classes and an outlook that argues general materials databases cannot carry process problems. [read]
2026-10-11 / reading, machine-learning, chemical-engineering
A short opinion piece on end-to-end molecular models, graph networks, transformers and matrix completion, for pure and mixture properties, with practical guidance on when they beat UNIFAC and COSMO-RS and a route for carrying them into process simulators. [read]
2026-10-11 / reading, machine-learning, thermodynamics, process-design