Uploaded August 2026 | Updated September 2026, 2 weeks ago
Batteries power almost everything in modern life but for 200 years, building a better one has meant slow, expensive trial and error. That's changing.
In this Royal Institution event, in collaboration with the Faraday Institution, three leading scientists reveal how artificial intelligence is transforming battery science at every scale. Exploring the atoms that make up a material, the microscopic structure of an electrode and the algorithms predicting how long your battery will actually last.
π¬ Aaron Walsh (CuspAI / Imperial College London) explains how AI acts as a "digital alchemist" β simulating billions of possible crystal structures to discover battery materials that don't exist yet.
βοΈ Sam Cooper (Imperial College London) reveals how machine learning is used to reverse-engineer the perfect internal "microstructure" of a battery electrode β the missing link between atoms and real-world performance.
π Mona Faraji Niri (WMG, University of Warwick) shows how AI acts as a forensic investigator, decoding sensor data to detect hidden faults and predict a battery's remaining lifespan β sometimes before it's even been used.
Chaired by Dr James Le Houx (University of Greenwich / Faraday Institution), this talk traces a direct line from Humphry Davy and Michael Faraday's first electrochemical experiments β performed in this very lecture theatre 200 years ago β to the AI-powered battery labs of today.
This event was filmed at the Royal Institution on 15 June 2026.
β±οΈ CHAPTERS
00:00 β Davy, Faraday & the birth of electrochemistry
02:50 β Why batteries became critical national infrastructure
03:53 β The hidden chaos inside every battery
07:18 β Aaron Walsh: AI at the atomic scale
09:56 β Turning 200 years of chemistry into numbers
12:05 β A search space bigger than the universe
16:17 β Can AI actually "generate" a new material?
22:17 β Live demo: asking AI to design a battery
25:07 β Mona Faraji Niri: AI at the system scale
27:36 β Batteries start dying before you even use them
33:02 β The billion-dollar question: how long will it last?
35:56 β Teaching AI the physics of degradation
41:37 β Narrow AI, general AIβ¦ and "super AI"
43:26 β Sam Cooper: AI for microstructure
44:38 β How a lithium-ion battery actually works
46:47 β Why physics-based models fall short
47:10 β Teaching AI to read a battery's internal anatomy
51:25 β Robots that never get bored
π Learn more about the Faraday Institution: faraday.ac.uk
π Subscribe to the Ri for more science talks: bit.ly/RiSubscRibe
π Become a channel member to get access to exclusive Q&As: youtube.com/channel/UCYeF244yNGuFefuFKqxIAXw/join
#Batteries #ArtificialIntelligence #Faraday #Electrochemistry #MaterialsScience #RoyalInstitution #ClimateΠ’ech #EV #ClimateChange
The Ri is on Facebook: facebook.com/royalinstitution
and TikTok: tiktok.com/@ri_science
Listen to the Ri podcast: podcasters.spotify.com/pod/show/ri-science-podcast
Donate to the RI and help us bring you more lectures: rigb.org/support-us/donate-ri
Our editorial policy: rigb.org/editing-ri-talks-and-moderating-comments
Subscribe for the latest science videos: bit.ly/RiNewsletter
Product links on this page may be affiliate links which means it won't cost you any extra but we may earn a small commission if you decide to purchase through the link.
Batteries power almost everything in modern life but for 200 years, building a better one has meant slow, expensive trial and error. That's changing.
In this Royal Institution event, in collaboration with the Faraday Institution, three leading scientists reveal how artificial intelligence is transforming battery science at every scale. Exploring the atoms that make up a material, the microscopic structure of an electrode and the algorithms predicting how long your battery will actually last.
π¬ Aaron Walsh (CuspAI / Imperial College London) explains how AI acts as a "digital alchemist" β simulating billions of possible crystal structures to discover battery materials that don't exist yet.
βοΈ Sam Cooper (Imperial College London) reveals how machine learning is used to reverse-engineer the perfect internal "microstructure" of a battery electrode β the missing link between atoms and real-world performance.
π Mona Faraji Niri (WMG, University of Warwick) shows how AI acts as a forensic investigator, decoding sensor data to detect hidden faults and predict a battery's remaining lifespan β sometimes before it's even been used.
Chaired by Dr James Le Houx (University of Greenwich / Faraday Institution), this talk traces a direct line from Humphry Davy and Michael Faraday's first electrochemical experiments β performed in this very lecture theatre 200 years ago β to the AI-powered battery labs of today.
This event was filmed at the Royal Institution on 15 June 2026.
β±οΈ CHAPTERS
00:00 β Davy, Faraday & the birth of electrochemistry
02:50 β Why batteries became critical national infrastructure
03:53 β The hidden chaos inside every battery
07:18 β Aaron Walsh: AI at the atomic scale
09:56 β Turning 200 years of chemistry into numbers
12:05 β A search space bigger than the universe
16:17 β Can AI actually "generate" a new material?
22:17 β Live demo: asking AI to design a battery
25:07 β Mona Faraji Niri: AI at the system scale
27:36 β Batteries start dying before you even use them
33:02 β The billion-dollar question: how long will it last?
35:56 β Teaching AI the physics of degradation
41:37 β Narrow AI, general AIβ¦ and "super AI"
43:26 β Sam Cooper: AI for microstructure
44:38 β How a lithium-ion battery actually works
46:47 β Why physics-based models fall short
47:10 β Teaching AI to read a battery's internal anatomy
51:25 β Robots that never get bored
π Learn more about the Faraday Institution: faraday.ac.uk
π Subscribe to the Ri for more science talks: bit.ly/RiSubscRibe
π Become a channel member to get access to exclusive Q&As: youtube.com/channel/UCYeF244yNGuFefuFKqxIAXw/join
#Batteries #ArtificialIntelligence #Faraday #Electrochemistry #MaterialsScience #RoyalInstitution #ClimateΠ’ech #EV #ClimateChange
The Ri is on Facebook: facebook.com/royalinstitution
and TikTok: tiktok.com/@ri_science
Listen to the Ri podcast: podcasters.spotify.com/pod/show/ri-science-podcast
Donate to the RI and help us bring you more lectures: rigb.org/support-us/donate-ri
Our editorial policy: rigb.org/editing-ri-talks-and-moderating-comments
Subscribe for the latest science videos: bit.ly/RiNewsletter
Product links on this page may be affiliate links which means it won't cost you any extra but we may earn a small commission if you decide to purchase through the link.
