Over the last 6 to 9 months, AI has taken the world by storm. Normal people started using AI to create art and write emails. LLMs like ChatGPT have become immensely popular, but people forgot that AI isn’t just used for generating words and pixels on a screen. AI helps solve real-world problems in energy, computer chip manufacturing, and consumer goods.
Let’s take an inventory of some of these real-world problems.
Electric car batteries are hugely expensive, take a long time to recharge, provide shorter driving ranges than gasoline cars, and depend on foreign-sourced rare-earth materials.
Maintaining the pace of innovation in computer chip manufacturing has gotten a lot harder. Fundamental limits in physics no longer allow us to regularly shrink chip sizes and increase transistor counts as we have for decades. And we heavily rely on foreign manufacturing and foreign-sourced rare earth materials to build them.
Consumer staples like non-stick cookware and stretch-resistant clothing produce toxic byproducts that cause cancer and negatively alter hormones.
All these problems are material science issues. Finding better materials and improving on the manufacturing process solves them. This is where AI comes in.
Research is material science’s bottleneck for innovation
Finding the right materials with the right mix of special properties to use in consumer and industrial applications is incredibly hard. There are nearly infinite material combinations to research, refine, and test, and testing each one takes a large amount of time and effort.
Materials science research is complex, relying on multifactorial physical and chemical analysis with many important variables. This makes it difficult to fully understand and predict material properties and behavior.
Materials science often involves conducting experiments to test and verify theories and predictions. These experiments can be time-consuming, particularly if they involve synthesizing and characterizing new materials.
These experiments generate huge amounts of data that need to be analyzed and interpreted.
State of the art AI models are fantastically good at identifying and recognizing patterns in huge datasets of raw data. That makes AI models a great fit for modeling the structure and behavior of alternative materials and detecting the important differences so that we can identify and implement better alternatives.
AI models for material science dramatically speed up materials research in two ways: predicting which material combinations are most likely to result in useful materials, analyzing huge volumes of data from experiments to quickly reach useful conclusions.
Augmenting the current material science research process with AI reduces the identification of new potentially useful materials search from weeks, months, or even years to mere seconds.
Innovation in energy storage has often felt elusive. Over many decades, researchers have experimented and made substantial progress, but we have never gained a fundamental understanding of how energy storage and battery technology works as the details of what happen inside of batteries remained hard to observe and hard to measure.
Batteries are still expensive compared tofossil fuels. Batteries degrade over time, which reduces their efficiency and lifespan. And large batteries that can power multiple homes aren’t scalable, which makes it difficult to integrate them into electric grids or meet the needs of large industrial facilities.
Battery technologies, such as lithium-ion, pose safety risks. If they are not designed and operated properly, they can catch fire and potentially explode when damaged or charged and discharged too quickly.
Understanding the materials behind batteries is key to delivering higher capacity, faster charging, and ultimately cheaper and more sustainable batteries.
Computer Chip Manufacturing
Making chips smaller makes chips faster and more efficient. We’ve reduced transistor sizes every 18 to 24 months for several decades, but reducing computer chip die sizes below 5nm has proven particularly challenging because of issues in quantum mechanics.
Now in order to regain our previous pace of innovation, we need to reinvent several aspects of our chip manufactruing processes.
AI helps us build smaller, faster, and more efficient chips by modeling alternative structures and materials that can reliably communicate information at smaller die sizes where quantum mechanics become important.
Home cooked meals are synonomous with health and yet some of the most popular cooking tools produce dangerous toxins.
Non-stick coatings have been linked to cancer and reproductive issues and aren’t safe to use at high temperatures and when the cookware is scratched or damaged. Even disposing of non-stick cookware poses environmental risks.
AI can help us find alternative non-stick cooking materials that are resilient to modern cooking techniques, hold up at high temperatures, and are long-lasting. AI materials research helps us make cooking safe while still keeping it easy.
Stretch-Resistant and Resilient Clothing
Most clothing is made using synthetic fabrics such as polyester, nylon, or acrylic. These materials are made of plastic, which is created from fossil fuels.
Evidence suggests that most synthetic fabrics interfere with the production of human hormones.
One study found that men who wore polyester-cotton blend underwear had lower levels of free testosterone compared to those who wore pure cotton. Researchers suggested that this may be due to the estrogen-like effects of chemicals used in synthetic fabrics’ production.
Synthetic fabrics, such as polyester and nylon, release harmful chemicals when they break down or are washed. These chemicals have negative impacts on human health, particularly when they’re inhaled or absorbed through the skin.
Plastic-based clothing, particularly synthetic fabrics, shed tiny plastic fibers during washing and wear. These microfibers can end up in the environment, where they can be ingested by wildlife and enter the food chain.
AI can help us find non-toxic and non-estrogenic clothing materials. AI can help us make clothing with utility of today’s synthetics without its associated negative health effects.
The Path Forward
AI breakthroughs in material science are far more compelling than its current abilities for generating text and image content and greatly benefit society as a whole.
Developing, understanding, and predicting new materials’ behavior leads to significant cost savings, improved consumer safety, and dramatically speeds up innovation.
Science’s next generation of innovation will come from applying methods AI researchers have used to train and build today’s art and text generation models and produce much material results.