
Advances in battery materials development are driving a new era of energy storage innovation, paving the way for safer, more efficient, and longer-lasting batteries. Lithium-ion batteries are now deeply embedded in our daily lives, powering everything from electric vehicles to mobile phones, laptops, wearables, and drones.
As demand grows for higher-capacity and more reliable batteries, researchers are exploring new chemistries to overcome the limitations of current technologies.
While different types of lithium-ion batteries offer various benefits, they also involve trade-offs between cost, performance, and safety. Next-generation batteries promise to address these challenges and will be essential to powering the future of clean energy and connected devices.
In this article, we explore how artificial intelligence is accelerating battery materials development—and how much of a game-changer it could really be.
Why Next-Gen Batteries Are Crucial for a Sustainable Energy Future
Next gen batteries like solid-state, lithium-sulfur, or lithium-metal are an essential component for a more sustainable future. They will enable the ability to store more energy in a smaller space and reduce charging times—critical for the scalability and convenience of EVs and e-mobility solutions.
Many next-gen batteries can eliminate flammable liquid electrolytes found in current lithium-ion batteries, reducing the risk of overheating or fire—especially important in cars, aircraft, and large-scale storage.
Enhancing the cycle life (number of charge/discharge cycles) of batteries will mean they can be replaced less often, which will lower costs and waste over time. Using less cobalt, nickel, or other scarce/raw materials, will help develop more sustainable batteries that are easier to recycle or repurpose.
Battery innovation is vital to electrifying transport, integrating renewables into the grid, and reducing greenhouse gas emissions across industries. Without better batteries, the transition to a low-carbon economy will stall.
The rise of AI in materials research

Australia is quickly becoming a global hub for battery innovation—driven not just by rich reserves of critical minerals like lithium and cobalt, but by the rapid adoption of artificial intelligence (AI) in battery research and development.
From mining to manufacturing to recycling, AI is helping Australian scientists and engineers build better batteries, faster. AI can help accelerate innovation in battery development while reducing costs and optimising performance.
Earth AI, an exploration technology company operating in Australia, offers a new approach to secure new mineral production in an industry that has remained stagnant and unchanged for decades. Earth AI is transforming critical minerals exploration through the innovative use of their proprietary artificial intelligence (AI) targeting software, integrated with a vertically integrated exploration model. Earth AI is vertically integrated from data driven target generation, to on-ground validation, and through to drilling using its own dedicated diamond drill rigs. This comprehensive structure enables rapid decision-making, reduces discovery timelines, and minimises environmental impact. The result is a scalable, next-generation exploration model that has already led to the identification of several new high-value prospects in overlooked terrains across Australia.
Earth AI’s purchase of Thermo Fisher’s Desktop Phenom XL G2 SEM as an in-house, low-maintenance scanning electron microscope is assisting in expediting the analysis and evaluation of potential mineral targets. The addition of this system to the company’s existing capabilities is allowing more rapid turn around times for sample analysis, letting them pivot and move faster through the mineral landscape.This ease of use of the Phenom XL G2 has meant that any mineralogies of a curious nature or importance can be identified within a quick time frame. This gives its users the benefit of having a more robust understanding of the geology as quickly as possible, which in turn can be implemented in exploration processes.
Can AI truly make a difference?
Traditional battery research relies on essential experimentation, which can be slow and expensive. In comparison AI can analyse vast datasets and run multiple simulations, to predict the performance of new battery materials before they’re even created in the lab. This is helping Australian researchers discover next-gen cathodes, anodes, and electrolytes with higher energy density and longer life.
For example, teams at CSIRO and leading Australian universities are using machine learning to screen thousands of material combinations—cutting down years of research into months.
This accelerated approach is vital for staying competitive in the global battery race. Lithium-ion battery manufacturer Recharge Industries has ventured into a partnership with Deakin University’s Applied Artificial Intelligence Institute (A2I2) to leverage AI in making better batteries. By integrating AI into their production lines the company hopes to reduce waste, lower costs, and boost scalability, which will help position Australia as a serious player in the battery supply chain.
Once batteries are in use, AI can help manage them more efficiently. AI-powered Battery Management Systems (BMS) can monitor performance, detect early signs of degradation, and optimise charging cycles. This extends battery life and ensures safe operation, which is especially critical in many challenging Australian environments. For grid-scale applications, AI can even help balance energy loads across multiple battery installations—supporting Australia’s transition to a clean energy future.
AI for Battery Sustainability & Recycling

AI can play a significant role in solving recycling and circularity challenges, particularly in the battery industry. AI-driven image recognition and robotics are already being used to identify, sort, and disassemble batteries more efficiently, helping to recover valuable materials like lithium, cobalt, and nickel. Machine learning algorithms can also optimise recycling processes by analysing chemical compositions and predicting the most effective methods for extracting and purifying materials from spent batteries.
Overview of Battery Materials and Their Role in Energy Storage

Materials are the heart of battery performance. The cathode and anode determine how much energy a battery can store and how long it lasts. For example, lithium nickel manganese cobalt oxide (NMC) offers high energy density, while newer materials like silicon anodes promise even greater capacity.
Importance for EVs, grid storage, and renewable energy
In EVs, materials that enable higher energy density, faster charging, and improved thermal stability directly contribute to longer driving ranges, enhanced safety, and better overall performance—key factors for broader adoption. For grid storage, durable and low-maintenance materials support batteries that can withstand daily charge-discharge cycles, helping to stabilise energy supply and reduce reliance on fossil fuels.
For renewable energy, these materials allow intermittent sources like solar and wind to be stored and used reliably, making clean energy more viable at scale. Ultimately, innovations in battery chemistry are foundational to building a more sustainable, electrified future.
The Rise of Next-Generation Battery Chemistries

Emerging battery types and materials (solid-state, lithium-sulfur, etc.)
Solid-state batteries, which replace liquid electrolytes with solid ones, promise higher energy density and enhanced safety with reduced risk of fire. Lithium-sulfur batteries are gaining interest due to their potential for much higher energy capacity and lower material costs compared to traditional lithium-ion batteries. Sodium-ion batteries offer a more abundant and cost-effective alternative to lithium, making them attractive for large-scale storage applications. Meanwhile, flow batteries, which store energy in liquid electrolytes held in external tanks, are emerging as a strong contender for long-duration grid storage thanks to their scalability and long cycle life.
The need for innovation and material breakthroughs
Current materials often limit energy density, degrade over time, or rely on scarce and expensive elements like cobalt and lithium. Advancements in materials science—such as developing more stable solid electrolytes, high-capacity anodes like silicon, or sustainable cathode alternatives—are essential for overcoming these limitations. These breakthroughs will be key to enabling batteries that can meet the demands of electric vehicles, renewable energy storage, and future smart grid systems.
Can AI Overcome Current Battery Material Challenges?
AI works exceptionally well in areas of battery material development where large datasets are available and patterns can be uncovered faster than traditional methods. For example, AI excels at predicting material properties, screening potential candidates, optimising formulations, and simulating chemical interactions—all of which can significantly speed up the discovery process.
Machine learning models can analyse thousands of material combinations, identify promising structures, and guide researchers toward the most viable candidates for lab testing.
AI struggles when data is limited, noisy, or inconsistent—which is often the case with novel materials or proprietary datasets. It also faces challenges in extrapolating beyond the training data, meaning that predictions can be less reliable for completely new material systems.
Additionally, translating AI-generated insights into practical, scalable materials still requires deep domain expertise and experimental validation, so AI is a powerful assistant or complement, but not yet a complete solution nor a replacement for lab work.
Key Instruments for Battery Research:
1. Particle Size Analysis

Mastersizer 3000+ uses laser diffraction to provide rapid and precise measurements of particle size distributions. It is used for assessing electrode material quality, essential for problem-free manufacturing and battery performance. From optimising the flow of battery slurries, the packing density and porosity of electrode coatings, and charge rate capacity and cycling durability of battery cells – it is important to have an accurate and reliable measurement of the material particle size distribution.
The Mastersizer 3000+ features the most advanced AI and automation solutions of any Mastersizer to date. The Data Quality Guidance feature provides alerts if it detects a change from the optimal path and provides instructions to get back on track, ensuring high-quality particle size data. The SOP Architect is an intelligent method development tool designed for wet dispersion measurements. It covers all core components of the method development process, providing guidance through a standardised workflow.
Adaptive Diffraction uses machine learning for data assessment, for more reliable sample results in challenging scenarios, such as bubbles or contaminants in the dispersant.
The Mastersizer acquires data at 10kHz, capturing data chunks every tenth of a millisecond. Previously, this volume of data was averaged to produce a single scattering pattern, but now, machine learning allows for the processing of these individual data chunks to determine if they are in a ‘steady state’ or ‘transient state.’
Mastersizer Auto-Lab enables automation for the analysis of up to 45 regular samples, including three priority samples, for wet analyses. It handles sample addition, performs size measurements using a chosen method, and cleans the system in preparation for the next analysis. Smart Manager provides automated support, automatically monitoring and reporting the instrument’s performance enabling remedial action can be taken immediately when needed.

Morphologi 4 combines the power of optical microscopy with sophisticated software algorithms to analyse and quantify particle shape (or size). Unlike traditional microscopy, which requires manual operation and analysis, automated optical imaging can capture the shape, size, texture, and distribution of thousands of particles at once. Using Morphologi 4’s fully automated image analysis capabilities, users can measure circularity, elongation/aspect ratio, circular Equivalent (CE) diameter, transparency and more for particles as small as 0.5 μm, and sample sizes from 10,000 to 500,000 particles.
In addition, with the Morphologi 4-ID, these automated static imaging capabilities can be combined with Raman spectroscopy, enabling users to simultaneously measure particle size, shape, and chemical identity on one platform aiding in the evaluation of battery material quality.
2. Microscopy and Imaging

Phenom ParticleX elevates the capabilities of the Phenom XL Desktop Scanning Electron Microscope (SEM) with automated SEM-EDS workflows. Offering high resolution imaging combined with integrated Energy-Dispersive Spectroscopy (EDS), the system has the ability to automatically locate, study the distribution and characterise the morphology of contaminant particles in samples.
Small contaminants in the NCM powder, for example, can jeopardise the performance, safety, and longevity of the final lithium battery. EDS enables users to identify the elemental and chemical composition of the particle in order to perform a root cause analysis of the contamination such as locating the source of the contaminant in the production workflow.
ChemiSEM Technology simplifies EDS analysis by combining SEM and EDS functions into a single, cohesive user interface. Based on live quantification and building on decades of expertise in EDS analysis, the technology provides elemental information quickly and easily, guaranteeing reliable results in less time. ChemiSEM Technology comes with ChemiPhase. ChemiPhase identifies unique phases with a big data approach, finding minor and trace elements while eliminating user bias and reducing possible mistakes.
Phenom XL Desktop SEM offers high-resolution imaging of large sample sizes (100 mm x 100 mm) and elemental analysis (EDS) of battery materials and can include argon-filled glove boxes. This setup enables research on air-sensitive battery samples since it decreases the risk of sample degradation due to lithium oxidation. By eliminating the need to move the research sample from one instrument to another, users can retain sample integrity and save time and resources.
ParticleX automation provides the ability to prepare sample batches to run overnight, using a step-and-repeat process to microscopically examine samples to locate, measure and classify any contaminant particles for remedial actions. Accessible via PPI (Phenom Programming Interface), a powerful method to command the Phenom XL Desktop SEM via Python scripting, the system is ideal for SEM workflows with repetitive tasks to analyse particles, pores, fibers, or large SEM images automatically.
As AI technologies continue to advance, their potential applications in scientific research, particularly in materials science, are becoming increasingly apparent.
“In the near future, AI will become the ‘professional videographer’ for scientific researchers,” said scientists from MIT. The group recently explored the possibility of autonomously operating laboratory equipment like the Phenom desktop SEM by integrating robotics with AI.
Experimental processes such as data collection and analysis were conducted with minimal human intervention, which allowed for continuous and efficient operation. However the automated operation of desktop Phenom SEM needed to be operated using scripting languages like Python, which restricted usage. Therefore, the group developed a voice-activated AI interface so that anyone, regardless of coding experience, could be empowered by the autonomous laboratory.
ATA Scientific’s range of battery characterisation technologies leverage decades of analytical expertise from multiple global leading manufacturers to advance the development and performance of battery technologies. Our suite of characterisation tools and techniques addresses the critical needs of battery research, development and production, ensuring optimal performance and safety of energy storage systems.
Contact us for more information or a demo.
FAQs
- Can AI fully replace traditional battery R&D?
The short answer is NO – While AI can help guide researchers toward better decisions, faster, human expertise and hands-on lab work is still required for testing, safety assessments, manufacturing and long-term performance validation. R&D involves deep experimental work—synthesising materials, testing physical and chemical properties, and validating performance in real-world conditions. These steps are critical, especially when scaling lab discoveries into commercially viable battery technologies.
- What’s the biggest challenge for AI in battery material discovery?
The biggest challenge for AI in battery material discovery is data quality and availability. AI models are only as good as the data they’re trained on. In battery research, there’s often a lack of large, standardised, high-quality datasets—especially for new or proprietary materials. Many experimental results are locked away in lab notebooks, published in inconsistent formats, or never shared at all. This makes it hard for AI to learn reliably or generalise beyond narrow datasets.
- What instruments are critical for battery analysis?
ATA Scientific offers advanced analytical instruments tailored for battery research and development, supporting advancements from material characterisation to quality control. These tools are essential for optimising battery performance, safety, and longevity. Instruments include: Mastersizer 3000+ particle size analyser, Morphologi 4 automated imaging system, KRÜSS DSA100 Drop Shape Analyser, KRÜSS BP100 Bubble Pressure Tensiometer, Phenom XL G2 Desktop SEM, and more.
By integrating these instruments into battery research workflows, scientists can achieve a deeper understanding of material properties, leading to the development of more efficient and reliable energy storage solutions.
References:
Advancing Asbestos Analysis in Bulk Samples with Artificial Intelligence
Harnessing the Power of AI for Automated SEM Explorations | Nanoscience Instruments