New invention cuts the job of sorting AI Tools from 7 years to a month

There are so many AI tools for chemical engineering jobs that it takes years to find the right one. So researchers at North Caroline State University have trained a ‘virtual lab’ to choose the best AI tools for each job. 

Having the right tool for the job makes the job a lot easier, less expensive and faster. 

They simulated 600,000 experiments, assessed 150 AI-guided decision-making strategies and claim to have cut 7.5 years of continuous robotic operation into one month’s work.

Chemical engineering researchers have now developed a virtual laboratory that can be used to determine the artificial intelligence (AI) tools best suited for addressing various chemical synthesis challenges in flow chemistry systems.

Autonomous systems can accelerating chemical R&D and manufacturing, but they are not in widespread use for two reasons. It’s hard to select the right hardware for automated synthesis – and it’s impossible to find AI-guided decision-making algorithm, says Milad Abolhasani, assistant professor of chemical engineering at North Carolina State University. 

There are three reasons why: One, there’s a huge choice of AI tools available. Two, there’s not information about them – which is add omission for artificial intelligence – so it’s hard to decide which tool is the best for each material synthesis problem. Three, the admin doesn’t stop once you have made your decision because each tool, once selected, still needs to be fine tuned.

“Recently, there has been increased interest in using off-the-shelf AI programs for modelling and optimisation of chemical reactions,” Abolhasani says. “But those off-the-shelf AI techniques are not one-size-fits-all – they’re not all equally good at solving whatever material synthesis problem you want to address.

“Ultimately, we want to find the best AI model architecture for determining the best material formulation that gives you the target properties you are looking for. Not just identifying the best material, but the best way of producing that material so that it has the best possible combination of characteristics. And the best AI model architecture is going to vary depending on the material and the complexity of the challenge.”

So Abolhasani and his collaborators took an AI-driven approach to finding the best AI tool for each material synthesis problem.

“It would be impossible to do the millions of experiments necessary to determine which AI tools do the best job for addressing different kinds of material synthesis problems,” Abolhasani says. “So, we wanted a model that simulates a real-world microfluidic experimental platform to effectively run those millions of experiments for us.”

The researchers ran 1,000 experiments using their automated Artificial Chemist platform and used those experimental data points to train the virtual experimental platform.

The paper, Accelerated AI development for autonomous materials synthesis in flow, is published in the journal Chemical Science. 

Advertisement

How Sunrise has swiped away the call centre

A mobile phone service in Switzerland has completely done away with call centres and all human customer support – and it’s all that to the introduction of eSIM.

Swiss operator Sunrise UPC (owned by Liberty Global) runs a digitally supported mobile service called swype, which users can connect each new customer’s phones to the network with an electronic version of the SIM card. 

By giving running the subscriber information module (SIM) through software rather than a card, they seduce users into the first step towards automation. Having done away with one manual operation, subscribers become emboldened to take on more. As Confucius said, the hardest part of the 1000 mile journey is the first step. In this case, the eSIM is the first step on the way to automation.

As a new subscriber to swype, once you have downloaded the eSIM from the Apple/Google store, you might feel confident about other forms of self-management. The installation is easy and the flat rate subscription (1.5 swiss francs day) is designed to be simple. The key is to avoid making people fear they are being locked in. In this scheme, the monthly plan can be cancelled at any time.

At first, companies used the vast arsenal of digital weapons to make life really complicated.

You never feel more manipulated than when you’ve tried to claim your ‘reward’ from a Loyalty scheme. That’s when you find out manipulative the marketing was and, as a result, you start to associate deviousness with the company. That’s not brand stigma.

If you don’t want your company to be branded as a cheat, keep your loyalty (i.e. customer service) strategy simple.

For swype subscribers customer service has become 100% digital onboarding. No paperwork, no post and no contact with a call centre, says Christoph Richartz, Chief YOL Officer Sunrise UPC. 

Ideally, I’d like to interview someone from the company about this, but there don’t seem to be any human contacts!