BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//aichemy - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aichemy.ac.uk
X-WR-CALDESC:Events for aichemy
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20260513T090000
DTEND;TZID=UTC:20260513T180000
DTSTAMP:20260611T135441
CREATED:20260211T154100Z
LAST-MODIFIED:20260512T150610Z
UID:7352-1778662800-1778695200@aichemy.ac.uk
SUMMARY:Applications of AI for Catalysis and Energy Materials Discovery
DESCRIPTION:KEY DETAILS\n\n\n\n\nDATE13th May 2026 TIME09:00 – 18:00 COSTFree to Attend \n\n\n\nbook now\n\n\n\n\n\n\nEVENT LOCATION\n\n\n\n\nMolecular Sciences Research Hub (MSRH)\,  Imperial College London82 Wood Ln\, London W12 0BZ \n\n\n\n\n\n\n\n\nJoin us for a one-day symposium bringing together researchers working in catalysis and energy materials with AI experts developing and applying machine learning methods in this space.  \n\n\n\nThe programme features talks from leading researchers across chemistry\, materials science\, and AI\, showcasing real-world applications of data-driven approaches in catalysis\, interfaces\, electrolytes\, membranes\, and energy materials. \n\n\n\nThe day will combine invited talks\, discussion\, and dedicated networking time\, providing opportunities to share ideas\, learn about emerging methods\, and spark new interdisciplinary collaborations across experimental\, computational and machine learning research in the area of catalysis and energy materials. \n\n\n\nWho Should Attend:\n\n\n\nThis symposium is designed for: \n\n\n\n\nAcademics and researchers in catalysis\, interfaces\, and energy materials who are interested in applying AI and machine learning to enhance\, accelerate\, or expand their research.\n\n\n\nAI and machine learning experts looking to apply novel computational approaches to challenges in catalysis\, reaction engineering\, molecular discovery\, and energy‑relevant materials.\n\n\n\n\nWhether your work is experimental\, theoretical\, computational\, or method‑development‑focused\, this event offers a unique opportunity to build connections across disciplines and gain insights into the rapidly evolving intersection of AI\, catalysis\, and materials discovery. \n\n\n\n\n\n\n\n\nAgenda\n\n\n\nTimeSession09:00 – 09:30Registration and Coffee09:30 – 09:40Welcome & Opening Remarks – Maryam Mansoori Kermani (Imperial)Chair: Carla Molteni (KCL)09:40 – 10:15Speaker: Evgeny A. Pidko (Delft University of Technology)Phase Boundaries under CO₂ Hydrogenation Conditions on Ni-Ga Catalyst: Coincidence? I Think Not!10:15 – 10:50Speaker: Fernanda Duarte (University of Oxford)Reaction Modelling in the Age of Machine Learning10:50 – 11:20Coffee BreakChair: Chun Ann Huang (Imperial)11:20 – 11:55Speaker: Ricardo Grau Crespo (Queen Mary University of London)Designing materials for thermoelectric applications: density functional theory and machine learning11:55 – 12:30Speaker: James Durrant (University of Oxford) Optical Spectroscopic Analysis of Metal Oxide: Electrolyte Interfaces for Photo- and Electro-Catalysis12:30 – 13:30Lunch BreakChair: Shijing Sun (Cambridge)13:30 – 14:05Speaker: James A. Dawson (Newcastle University) Interfacial Design in Next-Generation Solid Electrolytes14:05 – 14:40Speaker: Qilei Song (Imperial) Molecular Engineering of Polymer Membranes for Sustainable Separation and Energy Processes14:40 – 15:10Coffee Break                      Chair: Sam Cooper (Imperial)15:10 – 15:45Speaker: Jacqueline Cole (University of Cambridge)Data-driven Materials Science for Energy-Sustainable Applications15:45 – 16:20Speaker: Maria Lukatskaya (ETH Zürich)Engineering Local Chemical Environments in Electrolytes for Efficient Batteries16:20 – 16:30Closing remark by Jarvist Frost (Imperial)16:30Networking\n\n\n\n\n\nSpeakers:\n\n\n\n\nProf. Evgeny Pidko – Delft University of Technology (TU Delft)\n\n\n\nProf. Fernanda Duarte – University of Oxford\, Department of Chemistry\n\n\n\nProf. Jacqui Cole – University of Cambridge\n\n\n\nDr. James Dawson – Newcastle University\n\n\n\nProf. James Durrant – University of Oxford\n\n\n\nProf. Maria Lukatskaya – ETH Zürich\n\n\n\nDr. Ricardo Grau‑Crespo – Queen Mary University of London\n\n\n\nDr. Qilei Song – Imperial College London\n\n\n\n\n\n\nTalk Abstracts:\n\n\n\nDesigning materials for thermoelectric applications: density functional theory and machine learning \n\n\n\nDesigning high-performance thermoelectric materials requires optimising a delicate balance of electronic transport\, lattice thermal conductivity\, and chemical stability. This talk will introduce a combined density functional theory (DFT) and machine-learning (ML) framework for accelerating this search. I will first outline how advanced first-principles workflows\, including anharmonic force-constant modelling and Boltzmann transport calculations\, provide detailed insight into carrier transport and heat flow in chalcopyrite compounds and related materials. I will then show how ML-based models such as hiPhive and CraTENet can dramatically reduce computational cost\, enabling rapid prediction of electronic and thermal transport properties across very large chemical spaces. Finally\, I will discuss how composition-driven screening coupled with generative AI crystal structure prediction techniques might open new routes for discovering Earth-abundant\, high-zT thermoelectrics. \n\n\n\nOptical Spectroscopic Analysis of Metal Oxide: Electrolyte Interfaces for Photo- and Electro-Catalysis  \n\n\n\nI will start by discussing the potential importance of both photoelectrocatalytic and electrocatalytic strategies in our transition to more sustainable energy systems. I will consider both the importance of water splitting to yield molecular hydrogen\, and also the wider challenges of CO2 and nitrogen reduction. A key challenge is eluciation of the materials design requirements for efficient catalytic function. I will go on to discuss the use of optical spectroscopies to provide insight into (photo)electrocatalytic function\, employing water oxidation as our most widely studied exemplar. In particular I will discuss how operando optical spectroelectrochemistry can used to determine redox state population densities and kinetics in metal oxides electrodes and photoelectrodes during water oxidation. This spectroelectrochemical approach is based on the idea that the redox states of most transition metal oxides are coloured\, allowing the specific concentrations of each state to be tracked by their optical absorption/reflection as a function of material\, applied bias\, time\, electrolyte etc. Such optical data can be complimentary to more widely employed electrochemical analyses such as J/V plots and Tafel analyses. In my talk I will discuss examples of the insights gained from operando spectroelectrochemistry into the design and function of a selection of materials\, including Iridium Oxide and Nickel/Iron Oxyhydroxide electrocatalysts\, as well as Hematite\, Bismuth vanadate and Strontium Titanate photoelectrodes/photocatalysts. \n\n\n\nInterfacial Design in Next-Generation Solid Electrolytes \n\n\n\nInterfaces are central to the performance\, functionality and longevity of energy materials and devices\, whether they be batteries\, fuel cells or a plethora of other crucial technologies. In solid-state batteries\, interfaces govern how efficiently ions move between the solid electrolyte and the electrodes. Poorly engineered interfaces can lead to high resistance\, reduced performance and even instability\, while well-designed interfaces enhance conductivity\, battery life and safety. In the first part of this talk\, I will discuss how machine learning interatomic potentials have enabled us to explore interfaces and ion transport at scales far beyond the capabilities of ab initio molecular dynamics. This includes the investigation of solid electrolyte interphase formation between argyrodite Li6PS5Cl and Li metal and universal cation transport in LaCl and LaBr-based solid electrolytes. In the second part of this talk\, I will present our recent atomistic simulations of grain boundaries in topical solid electrolytes\, including garnet Li7La3Zr2O12 and argyrodite Li6PS5Cl. Specifically\, I will discuss how the different electronic structures of Li7La3Zr2O12 and Li6PS5Cl grain boundaries lead to fundamentally different mechanisms of lithium ion incorporation and reduction and lithium atom nucleation in these two materials. \n\n\n\nData-driven Materials Science for Energy-Sustainable Applications \n\n\n\nThis lecture presents the development and application of data-extraction tools andmachine-learning (ML) models that are enabling data-driven materials science forenergy-sustainable applications. The talk describes how to source high-quality data tobuild custom databases and apply them to (a) train ML models; (b) realise data-drivenmaterials discovery; (c) conduct data-driven materials science for the energy sector; (f)create energy-efficient domain-specific language models for materials science to feedagentic AI and help democratise AI for the materials research community. The casestudies presented track a theme of energy-sustainable materials \n\n\n\nEngineering Local Chemical Environments in Electrolytes for Efficient Batteries \n\n\n\n“Electrolytes play a crucial role in energy storage devices\, impacting their environmental footprint\, safety\, cost\, and performance. This talk will cover two areas of electrolyte research for improving batteries. \n\n\n\nFirst\, we will explore water-based batteries. Aqueous electrolytes\, being non-flammable and less toxic\, offer safer battery operation. However\, their limited electrochemical stability window reduces energy density. To address this\, highly concentrated “”water-in-salt”” (WIS) electrolytes have been developed\, significantly expanding the stability window and enhancing the performance of Li-ion and Zn metal batteries for grid energy storage. Despite their advantages\, WIS electrolytes have high viscosity and require large amounts of potentially toxic salts\, which limits their usability. We will discuss how cation solvation\, electrolyte structure\, and hydrogen bonding influence the electrochemical properties and performance\, particularly in Zn plating/stripping and electrolyte decomposition. Additionally\, we will explore strategies for engineering relatively dilute electrolytes for efficient aqueous batteries. \n\n\n\nSecond\, the talk will present a novel method for stabilizing interfaces in Li metal batteries (LiMBs). Conventional electrolytes result in low cycle life and safety issues due to “”dead”” lithium and dendrite formation. Prior research suggests that fluorine-rich interfacial layer chemistry is important for the stabilization of Li-metal anodes\, which can be achieved when electrolytes with a high fraction of fluorinated solvents and/or salts are used. We propose an alternative approach using electrostatic attraction between positively charged readily reducible fluorinated cations and the negatively charged anode. This method enables the formation of a robust fluorine-rich interfacial layer with minimal additive (as low as 1 mM) facilitating dense\, conformal Li deposition. This strategy can offers a cost-effective\, environmentally friendly solution for enhancing high-energy batteries.” \n\n\n\n\n\nContact details:Aysel Sarzosa (asarzosa@ic.ac.uk) or Chris Mellor (c.mellor@imperial.ac.uk). \n\n\n\nIn addition\, if you have caring responsibilities that may affect your ability to attend\, take a look at our Conference Care Fund and get in touch to see how we can support you to attend. \n\n\n\n\n\n\n\n\n\nOrganised by:\n\n\n\nDr Maryam Mansoori Kermani\, MSCA Fellow at Imperial College London with the support of AIchemy Hub – Project Team.
URL:https://aichemy.ac.uk/event/applications-of-ai-for-catalysis-and-energy-materials-discovery/
CATEGORIES:Symposium,Workshop
ATTACH;FMTTYPE=image/png:https://aichemy.ac.uk/wp-content/uploads/2026/02/Applications-of-AI-for-Catalysis-and-Energy-Materials-Discovery-Symposium.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20260520T140000
DTEND;TZID=UTC:20260520T150000
DTSTAMP:20260611T135441
CREATED:20260508T151957Z
LAST-MODIFIED:20260518T105820Z
UID:9410-1779285600-1779289200@aichemy.ac.uk
SUMMARY:AIchemy’s Monthly Webinar Series – May 2026
DESCRIPTION:KEY DETAILS\n\n\n\n\nDATE20th May 2026 TIME14:00 – 15:00 COSTFree LOCATIONOnline MS Teams \n\n\n\nREGISTER HERE\n\n\n\n\n\n\n\n\nWe are delighted to welcome you to our AIchemy Hub’s monthly webinar series. \n\n\n\nThis month’s talks: \n\n\n\nProf. Bao Nguyen – University of Leeds \n\n\n\nTalk Title: Who’s learning from whom? Beyond the black boxes of chemical models. \n\n\n\nArtificial intelligence and machine learning are now central tools for chemists seeking to predict molecular properties and reaction outcomes. Yet as these models grow increasingly sophisticated\, their inner workings often remain opaque\, and the chemical data they rely on—like all experimental data—can be noisy\, sparse\, or biased. In this talk\, Bao will illustrate how we address these challenges in the context of solubility prediction: from handling imperfect datasets to building models that both perform robustly and provide trustworthy predictions on previously unseen data. \n\n\n\nHe will then show how the usual paradigm can be reversed. Rather than using algorithms solely to predict the results of complex reactions\, we can use the data generated through Bayesian Optimisation to reveal mechanistic insights that would otherwise remain hidden. This shift—from prediction to understanding—opens new opportunities for rationally tackling selectivity problems in modern synthetic chemistry. \n\n\n\nNikola Radulov – University of Liverpool \n\n\n\nTalk Title: FLIP: Flowability-Informed Powder Weighing \n\n\n\nAutonomous manipulation of powders remains a significant challenge for robotic automation in scientific laboratories. The inherent variability and complex physical interactions of powders in flow\, coupled with variability in laboratory conditions necessitates adaptive automation. We introduce FLIP\, a flowability-informed powder weighing framework designed to enhance robotic policy learning for granular material handling. The core of the framework lies in using material flowability\, quantified by the angle of repose\, to optimise physics-based simulations through Bayesian inference. This yields material-specific simulation environments capable of generating accurate training data\, which reflects diverse powder behaviours\, for training “robot chemists”.  We demonstrate how FLIP integrates quantified flowability into a curriculum learning strategy\, fostering efficient acquisition of robust robotic policies by gradually introducing more challenging\, less flowable powders. We validate the efficacy of our method on a robotic powder weighing task under real-world laboratory conditions. Experimental results show that FLIP with a curriculum strategy achieves a low dispensing error of 2.12 +/- 1.53 mg\, outperforming methods that do not leverage flowability data\, such as domain randomisation (6.11 +/- 3.92 mg). These results demonstrate FLIP’s improved ability to generalise to previously unseen\, more cohesive powders and to new target masses.Following the presentations\, there will be time for questions from the audience. \n\n\n\n\n\nSpeakers\n\n\n\n\n\nProf. Bao Nguyen Physical Organic Chemistry\n\n\n\n\n\nNikola RadulovEarly Career Research\n\n\n\n\n\nDr. Adam ClaytonAssociate Professor
URL:https://aichemy.ac.uk/event/aichemys-monthly-webinar-series-may-2026/
CATEGORIES:Webinar
ATTACH;FMTTYPE=image/jpeg:https://aichemy.ac.uk/wp-content/uploads/2026/05/May-Webinar-2026.jpg
END:VEVENT
END:VCALENDAR