The stakes for the global battery market are incredibly high. Some predictions estimate that it will be worth over £250bn per year from 2025, with the possible creation of four million jobs in the EU alone. And batteries – already essential for most consumer goods – will be even more vital for widespread adoption of electric vehicles.

Currently, no automotive or battery manufacturer can claim to offer an EV battery that charges as quickly as it takes to fill the tank of a traditional fossil-fuel-based vehicle, nor can it offer the same range. The Volkswagen e-Up offers 99 miles at full charge, the Tesla Model S 100D 335 miles. However, none can be fully charged in a matter of minutes. Today, a Tesla supercharging station will take 75 minutes to reach full charge, whereas SP Group, the largest EV network in Singapore, takes only half an hour.

The potential for lithium-ion batteries to solve some of these issues is enormous. However, there are a number of challenges that prevent a rapid charge, from the need for higher energy density to pre-eminent rate performance and improved safety requirements. Overcoming issues in battery chemistry is a slow research process, largely based on an iterative process of design, experimentation and systematic trial and error. Indeed, many new advances fail before they make it to market.

In R&D facilities, cyclers gather data from battery cells every second, including performance parameters such as cell temperature, real-time resistance, operating voltage window, charge and discharge current, and swelling levels. Collecting this information simultaneously from thousands of batteries means that terabytes of data are accumulated in every experiment. As a result, the number of combinations for these materials is endless, and the number of experiments needed to test each combination equally so. Analysis using traditional statistical or manual methods is extremely challenging.

A holistic approach to employing data science in battery development could hold the key to solving such complex models. Artificial intelligence – or machine learning – can assess information and construct a mathematical model at a far quicker pace than the human brain. Systems can automatically learn and improve from experience, without being explicitly programmed.

AI’s current and potential impact across multiple industries is staggering. In manufacturing, some of the world’s largest companies are already using it with impressive results. Royal Dutch Shell’s Smart Manufacturing System uses AI to predict demand for oil, measure shortages of supply and analyse the correct mix/blends for an exact refining process. BASF and SAP claim to have automated 94 per cent of payment processing with AI.

Potential applications are broad, ranging from material design and synthesis to experiment design, fault analysis and minimising waste. The potential impact on battery development is not to be understated. The technology can browse through millions of records to describe the relationship between measured data and battery parameters. Manufacturers can test millions of combinations of electrolytes, anodes and cathodes at any given time.

Scientists can not only evaluate batteries in development, but also achieve a better understanding of existing batteries. The ability to rapidly test limitless combinations means that the ultimate formulation of the materials used to make the battery cell is reached far more quickly. This dramatically reduces the number of experiments necessary, dramatically cutting development time, as well as significantly reducing development costs. For example, a team of 50 researchers working on a particular battery formulation can save up to $1m in R&D efforts per month by deploying machine-learning capabilities.

At StoreDot, an initial foray into this technique has achieved remarkable results. The team developing the first generation of our ultra-fast charging FlashBattery technology used machine learning to discover that a few simple changes could double the number of cycles of the battery under development from 300 to over 600 cycles. It was this discovery that inspired us to dedicate an entire R&D group just to building our capabilities in machine learning.

This dramatic result is now being applied to the next generation of our electric vehicle batteries. Ultra-fast charging presents a very complex issue – whereas in a traditional battery methodology we would typically change only one component, here we may need to change far more to achieve the desired breakthrough. By combining innovative data science, powered by AI, with expertise in electrochemistry, cell structure, anodes, cathodes and electrolytes, far more complex conclusions can be reached.

Using machine learning in the R&D process isn’t the only way in which AI can be implemented to advance EVs. A very different and intriguing application would be to implement it within a vehicle’s operational software, where it would continuously monitor battery performance and health, circulating data back to improve product improvement. Moreover, by creating smarter batteries with embedded sensing capabilities, and with self-healing functionalities, the battery-management system can be aware of their ‘state of health’ and can even rejuvenate battery cells or modules when necessary.

By enabling innovators to change more than one component at a time and analyse evidence more rapildy, AI helps them reach conclusions that traditional statistical analysis cannot accomplish. This evidence allows for faster development cycles and the ability to overcome problems that might not otherwise be solved. For the adoption of EVs, this capability is paramount in solving one of the biggest consumer barriers, ‘range anxiety’. By bringing battery charging times down by using machine-learning technology, quite literally, the entire EV industry could be overhauled.

Dr Doron Myersdorf is CEO of battery company StoreDot.

The stakes for the global battery market are incredibly high. Some predictions estimate that it will be worth over £250bn per year from 2025, with the possible creation of four million jobs in the EU alone. And batteries – already essential for most consumer goods – will be even more vital for widespread adoption of electric vehicles.

Currently, no automotive or battery manufacturer can claim to offer an EV battery that charges as quickly as it takes to fill the tank of a traditional fossil-fuel-based vehicle, nor can it offer the same range. The Volkswagen e-Up offers 99 miles at full charge, the Tesla Model S 100D 335 miles. However, none can be fully charged in a matter of minutes. Today, a Tesla supercharging station will take 75 minutes to reach full charge, whereas SP Group, the largest EV network in Singapore, takes only half an hour.

The potential for lithium-ion batteries to solve some of these issues is enormous. However, there are a number of challenges that prevent a rapid charge, from the need for higher energy density to pre-eminent rate performance and improved safety requirements. Overcoming issues in battery chemistry is a slow research process, largely based on an iterative process of design, experimentation and systematic trial and error. Indeed, many new advances fail before they make it to market.

In R&D facilities, cyclers gather data from battery cells every second, including performance parameters such as cell temperature, real-time resistance, operating voltage window, charge and discharge current, and swelling levels. Collecting this information simultaneously from thousands of batteries means that terabytes of data are accumulated in every experiment. As a result, the number of combinations for these materials is endless, and the number of experiments needed to test each combination equally so. Analysis using traditional statistical or manual methods is extremely challenging.

A holistic approach to employing data science in battery development could hold the key to solving such complex models. Artificial intelligence – or machine learning – can assess information and construct a mathematical model at a far quicker pace than the human brain. Systems can automatically learn and improve from experience, without being explicitly programmed.

AI’s current and potential impact across multiple industries is staggering. In manufacturing, some of the world’s largest companies are already using it with impressive results. Royal Dutch Shell’s Smart Manufacturing System uses AI to predict demand for oil, measure shortages of supply and analyse the correct mix/blends for an exact refining process. BASF and SAP claim to have automated 94 per cent of payment processing with AI.

Potential applications are broad, ranging from material design and synthesis to experiment design, fault analysis and minimising waste. The potential impact on battery development is not to be understated. The technology can browse through millions of records to describe the relationship between measured data and battery parameters. Manufacturers can test millions of combinations of electrolytes, anodes and cathodes at any given time.

Scientists can not only evaluate batteries in development, but also achieve a better understanding of existing batteries. The ability to rapidly test limitless combinations means that the ultimate formulation of the materials used to make the battery cell is reached far more quickly. This dramatically reduces the number of experiments necessary, dramatically cutting development time, as well as significantly reducing development costs. For example, a team of 50 researchers working on a particular battery formulation can save up to $1m in R&D efforts per month by deploying machine-learning capabilities.

At StoreDot, an initial foray into this technique has achieved remarkable results. The team developing the first generation of our ultra-fast charging FlashBattery technology used machine learning to discover that a few simple changes could double the number of cycles of the battery under development from 300 to over 600 cycles. It was this discovery that inspired us to dedicate an entire R&D group just to building our capabilities in machine learning.

This dramatic result is now being applied to the next generation of our electric vehicle batteries. Ultra-fast charging presents a very complex issue – whereas in a traditional battery methodology we would typically change only one component, here we may need to change far more to achieve the desired breakthrough. By combining innovative data science, powered by AI, with expertise in electrochemistry, cell structure, anodes, cathodes and electrolytes, far more complex conclusions can be reached.

Using machine learning in the R&D process isn’t the only way in which AI can be implemented to advance EVs. A very different and intriguing application would be to implement it within a vehicle’s operational software, where it would continuously monitor battery performance and health, circulating data back to improve product improvement. Moreover, by creating smarter batteries with embedded sensing capabilities, and with self-healing functionalities, the battery-management system can be aware of their ‘state of health’ and can even rejuvenate battery cells or modules when necessary.

By enabling innovators to change more than one component at a time and analyse evidence more rapildy, AI helps them reach conclusions that traditional statistical analysis cannot accomplish. This evidence allows for faster development cycles and the ability to overcome problems that might not otherwise be solved. For the adoption of EVs, this capability is paramount in solving one of the biggest consumer barriers, ‘range anxiety’. By bringing battery charging times down by using machine-learning technology, quite literally, the entire EV industry could be overhauled.

Dr Doron Myersdorf is CEO of battery company StoreDot.