The US National Science Foundation (NSF) has launched a new $380 million (£285 million) effort to establish a nationwide network of automated laboratories enabled by artificial intelligence (AI), and as part of this initiative North Carolina State University (NCSU) will lead a project that aims to build ‘self-driving’ chemistry labs.
Dubbed the self-driving platforms for experimental co-design in chemistry and materials science (Speed lab), the four-year, $20 million grant will be directed by NCSU chemical engineer Milad Abolhasani with assistance from the University of North Carolina (UNC) Chapel Hill organometallic chemist Alex Miller. The initiative’s objective is to advance autonomous labs in which scientists direct the research goals and smart robotics carry out the procedures, and to facilitate remote control of automated instrumentation. It will initially focus on catalysts for more efficient chemical manufacturing, semiconductor materials for energy, sensing and electronics, as well as photocatalytic materials.
What is AI?
Artificial intelligence (AI) is an umbrella term often incorrectly used to encompass a variety of connected but simpler processes.
AI is the ability of machines and computer programmes to perform tasks that typically only humans could do, such as reasoning, responding to feedback and decision making.
Generative AI is a newer variant of AI that analyses and detects patterns in training datasets to generate original text, images and videos in response to requests from users. ChatGPT, Microsoft Copilot, Google Gemini and more recently X’s Grok are all examples of chatbots that use generative AI.
Neural networks are an interconnected array of artificial neurons, akin to biological brains, that identify, analyse and learn from statistical patterns in data.
Machine learning is a subset of AI that allows machines to learn from datasets and make predictions based on new data, without programmers explicitly asking it to do so. Machine learning models improve their performance as they receive more data.
Deep learning is an enhanced type of machine learning that uses neural networks with many layers to analyse complex data from very large datasets. Applications of deep learning include speech recognition, image generation and translation.
Large language models or LLMs are a type of deep learning trained on large amounts of data to understand and generate language. LLMs learn patterns in text by predicting the next word in the sequence and these models are now able to write prose, analyse text from the internet and hold dialogues with users.
‘Speed will allow researchers to compress the discovery of functional materials and molecules from years to weeks in areas such as advanced electronics, pharmaceuticals and agriculture,’ Abolhasani stated.
Researchers at the Massachusetts Institute of Technology will also contribute their expertise in machine learning and AI for use in chemistry research. One important aspect of this initiative will involve experts from Chapel Hill developing new access and control interfaces and piloting a broad range of different chemical reactions.
‘The development of hardware and software tools that enable users that don’t have access to advanced instrumentation to test their research ideas could be revolutionary,’ Miller said. As the individual self-driving lab modules within Speed will be able to perform experiments in parallel and use machine learning methods to predict the most promising next set of experiments, he estimates that they will be able to accelerate the process of moving from lead discovery to optimised outcome by 100 times or more.
The NSF grant will also fund projects in biotechnology, biochemistry, soft materials and electronics over the next four years.
No comments yet