BIG-MAP · Project

AI Platform That Finds New Battery Materials 10 Times Faster

energyTestedTRL 5

Imagine you need a better battery — one that charges faster, lasts longer, and costs less. Normally, scientists test thousands of chemical combinations by hand, which takes years. BIG-MAP built a system where AI and robots work together to run experiments automatically, predict which materials will work, and skip the ones that won't. Think of it like GPS for chemistry: instead of wandering every possible road, it calculates the fastest route to the best battery material.

By the numbers

10-fold

targeted increase in battery materials discovery rate

consortium partners across the full battery discovery chain

countries represented in the consortium

key demonstrators delivered

total project deliverables completed

industry partners in the consortium

The business problem

What needed solving

Developing new battery chemistries takes 10-20 years from lab to market, making it nearly impossible for companies to keep pace with demand for better energy storage. Current trial-and-error approaches are slow, expensive, and produce mostly dead ends. Companies in the battery value chain need a way to dramatically compress that discovery timeline or risk falling behind competitors.

The solution

What was built

The project delivered 12 key demonstrators including an active learning module for experimental data, automated synthesis procedures, simulation-experiment feedback loops, and transfer of AI models to new battery chemistries. In total, 32 deliverables were produced across the platform covering AI-orchestrated materials discovery from atomic scale to battery cell level.

Audience

Who needs this

Battery cell manufacturers looking to develop next-generation chemistriesAutomotive OEMs with in-house battery R&D divisionsChemical companies supplying battery materials (electrolytes, cathodes, anodes)Energy storage system integrators seeking differentiated cell chemistryNational research labs and universities building battery testing infrastructure

Business applications

Who can put this to work

Battery Manufacturing

enterprise

Target: Battery cell producers developing next-generation chemistries

If you are a battery manufacturer struggling to find better electrode or electrolyte materials — this project built an AI-orchestrated platform with automated synthesis and active learning that aims for a 10-fold increase in discovery speed. The system demonstrated transfer of trained models to entirely new battery chemistries, meaning your R&D team could screen candidate materials far faster than traditional lab work. With 12 demonstrators validated across the discovery chain, this is ready to plug into existing R&D pipelines.

Automotive

enterprise

Target: Car makers with in-house battery development programs

If you are an automotive company racing to secure proprietary battery technology — this project created a closed-loop system where simulations drive experiments and experiments refine simulations automatically. The consortium of 39 partners across 15 countries built coordinated multi-technique experimental capabilities that generate multi-scale data on battery interfaces. This means your materials team can evaluate more chemistry options in less time, giving you a competitive edge in the EV market.

Chemical Supply

mid-size

Target: Specialty chemical companies producing battery-grade materials

If you are a chemical supplier looking to develop new battery materials for an exploding market — this project demonstrated automated synthesis procedures and active learning modules that predict promising formulations from existing data. Instead of running thousands of expensive experiments, the platform narrows the field to the most likely winners. With 10 industry partners already involved in the 39-member consortium, the technology has been shaped by real industrial needs.

Frequently asked

Quick answers

What would it cost to access or license this platform?

Based on available project data, specific licensing terms or pricing are not disclosed. The platform was developed as a Research and Innovation Action under Horizon 2020 with 39 partners. Companies interested in access should contact the coordinator at Danmarks Tekniske Universitet to discuss collaboration or licensing arrangements.

Can this work at industrial scale or is it still a lab tool?

The project delivered 12 key demonstrators including automated synthesis procedures and coordinated multi-technique experiments at multiple scales. However, these were demonstrated in research settings across the consortium. Scaling to full industrial throughput would require further engineering and integration work.

What is the IP situation — can we use this technology?

As a Horizon 2020 RIA project with 39 partners across 15 countries, IP is typically shared among consortium members according to contribution. The 10 industry partners likely hold rights to specific components. Interested companies should inquire with the coordinator about licensing specific modules or the open-source components.

How proven is the AI — does it actually speed up discovery?

The project demonstrated active learning on real experimental datasets, transfer of trained models to new battery chemistries, and simulation-experiment feedback loops. The stated target is a 10-fold increase in the rate of materials discovery. The 32 deliverables across the project provide documented evidence of these capabilities.

Does this only work for batteries or can it be adapted?

The platform was designed to be chemistry-neutral, meaning the AI and automation infrastructure could potentially apply to other materials discovery challenges. However, all 12 demonstrators and the training data focus specifically on battery materials and interfaces. Adaptation to other domains would require new datasets and domain expertise.

How does this connect to the broader European battery strategy?

BIG-MAP is a core project of the BATTERY 2030+ initiative, Europe's large-scale battery research roadmap. The consortium includes 13 core BATTERY 2030+ partners plus 21 additional specialists. This positions the technology within Europe's strategic push for battery independence and gives it strong institutional backing.

Consortium

Who built it

This is one of the largest battery research consortia in Europe: 39 partners from 15 countries, bringing together 17 universities, 11 research organizations, and 10 industry players. The 26% industry ratio shows meaningful commercial involvement, though notably zero SMEs participated — this is big-player territory. The project is anchored by Danmarks Tekniske Universitet and backed by the BATTERY 2030+ initiative, giving it serious institutional weight. For a company looking to adopt this technology, the large consortium means broad expertise but also complex IP arrangements that would need careful navigation.

DANMARKS TEKNISKE UNIVERSITETCoordinator · DK
INSTITUT MAX VON LAUE - PAUL LANGEVINparticipant · FR
UNIVERSITE DE PICARDIE JULES VERNEthirdparty · FR
UNIVERSITAET MUENSTERparticipant · DE
TARTU ULIKOOLparticipant · EE
THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGEparticipant · UK
SYNCHROTRON SOLEIL SOCIETE CIVILEparticipant · FR
IT-UNIVERSITETET I KOBENHAVNparticipant · DK
FORSCHUNGSZENTRUM JULICH GMBHparticipant · DE
UNIVERSITAT BASELparticipant · CH
NORTHVOLT ABparticipant · SE
UNIVERSITAT WIENparticipant · AT
COMMISSARIAT A L ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVESparticipant · FR
EUROPEAN SYNCHROTRON RADIATION FACILITYparticipant · FR
UPPSALA UNIVERSITETparticipant · SE
KEMIJSKI INSTITUTparticipant · SI
ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNEparticipant · CH
SINTEF ASparticipant · NO
AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICASparticipant · ES
UMICORE SPECIALTY POWDERS FRANCEthirdparty · FR
CONSIGLIO NAZIONALE DELLE RICERCHEparticipant · IT
BASF SEparticipant · DE
KARLSRUHER INSTITUT FUER TECHNOLOGIEparticipant · DE
DASSAULT SYSTEMES DEUTSCHLAND GMBHparticipant · DE
POLITECHNIKA WARSZAWSKAparticipant · PL
ENERGY MATERIALS INDUSTRIAL RESEARCH INITIATIVEparticipant · BE
SOLVAY SAparticipant · BE
POLITECNICO DI TORINOparticipant · IT
THE UNIVERSITY OF LIVERPOOLparticipant · UK
THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORDparticipant · UK
RHODIA OPERATIONSthirdparty · FR
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRSparticipant · FR
FUNDACION CIDETECparticipant · ES
UMICORE SAparticipant · BE
SAFTparticipant · FR
TECHNISCHE UNIVERSITEIT DELFTparticipant · NL
CHALMERS TEKNISKA HOGSKOLA ABparticipant · SE

How to reach the team

Danmarks Tekniske Universitet (DTU), Denmark — reach out to the BIG-MAP project coordination team

Order a report on this consortium See DANMARKS TEKNISKE UNIVERSITET profile →

Next steps

Talk to the team behind this work.

Want an introduction to the BIG-MAP team or a tailored briefing on how their AI-driven materials platform could accelerate your battery R&D? Contact SciTransfer — we connect businesses with EU research teams.

Order a report on this topic More in Energy & Climate