Luca Torresi

Luca Torresi

Auto-generated profile, based on publicly available information

Luca Torresi

Institute of Theoretical Informatics Karlsruhe Institute of Technology Karlsruhe Germany

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2022 in Communications Materials
Verified
Journal Article
Open access
PDF file
PRPatrick Reiser
Patrick Reiser
MNMarlen Neubert
Marlen Neubert
AEAndré Eberhard
André Eberhard
LTLuca Torresi
Luca Torresi
CZChen Zhou
Chen Zhou
PFPascal Friederich
Pascal Friederich
Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.

13 December 2024 in Science
Verified
Journal Article
Closed access
JWJianchang Wu
Jianchang Wu
LTLuca Torresi
Luca Torresi
MHManMan Hu
ManMan Hu
PRPatrick Reiser
Patrick Reiser
JZJiyun Zhang
Jiyun Zhang
CBChristoph J. Brabec
Christoph J. Brabec
The inverse design of tailored organic molecules for specific optoelectronic devices of high complexity holds an enormous potential but has not yet been realized. Current models rely on large data sets that generally do not exist for specialized research fields. We demonstrate a closed-loop workflow that combines high-throughput synthesis of organic semiconductors to create large datasets and Bayesian optimization to discover new hole-transporting materials with tailored properties for solar cell applications. The predictive models were based on molecular descriptors that allowed us to link the structure of these materials to their performance. A series of high-performance molecules were identified from minimal suggestions and achieved up to 26.2% (certified 25.9%) power conversion efficiency in perovskite solar cells.

13 December 2023 in Journal of Materials Chemistry A
Verified
Journal Article
Open access
PDF file
KJKen J. Jenewein
Ken J. Jenewein
LTLuca Torresi
Luca Torresi
NHNavid Haghmoradi
Navid Haghmoradi
AKAttila Kormányos
Attila Kormányos
PFPascal Friederich
Pascal Friederich
SCSerhiy Cherevko
Serhiy Cherevko
Experimental catalyst optimization is plagued by slow and laborious efforts. Finding innovative materials is key to advancing research areas for sustainable energy conversion, such as electrocatalysis. Artificial intelligence (AI)-guided optimization bears great potential to autonomously learn from data and plan new experiments, identifying a global optimum significantly faster than traditional design of experiment approaches. Furthermore, it is vital to incorporate essential electrocatalyst features such as activity and stability into the optimization campaign to screen for a truly high-performing material. In this study, a multiobjective Bayesian optimization (MOBO) was used in conjunction with an experimental high-throughput (HT) pipeline to refine the composition of a non-noble Co–Mn–Sb–Sn–Ti oxide toward its activity and stability for the oxygen evolution reaction (OER) in acid. The viability of the MOBO algorithm was verified on a gathered data set, and an acceleration of 17x was achieved in subsequent experimental screening compared to a hypothetical grid search scenario. During the ML-driven assessment, Mn-rich compositions were critical to designing high-performing OER catalysts, while Ti incorporation into MnOx triggered an improved activity after short accelerated stress tests. To examine this finding further, an operando mass spectrometry technique was used to probe the evolution of activity, metal dissolution, and surface area over 3 h of operation. This work demonstrates the importance of respecting the multiobjective nature in electrocatalyst performance during HT campaigns. AI-based decision-making helps to bridge the gap between fast HT screening (limited property extraction) and slow fundamental research (rich property extraction) by avoiding less informative experiments.

26 February 2026 in Advanced Materials
Verified
Journal Article
Open access
HMHoussam Metni
Houssam Metni
LRLaura Ruple
Laura Ruple
LWLauren N. Walters
Lauren N. Walters
LTLuca Torresi
Luca Torresi
JTJonas Teufel
Jonas Teufel
PFPascal Friederich
Pascal Friederich
Understanding structure‐property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end‐to‐end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

19 July 2022 in Frontiers in Physics
Verified
Journal Article
Open access
Stefano GiaguStefano Giagu
Stefano Giagu
LTLuca Torresi
Luca Torresi
MFMatteo Di Filippo
Matteo Di Filippo
Efficient and accurate reconstruction and identification of tau lepton decays plays a crucial role in the program of measurements and searches under the study for the future high-energy particle colliders. Leveraging recent advances in machine learning algorithms, which have dramatically improved the state of the art in visual object recognition, we have developed novel tau identification methods that are able to classify tau decays in leptons and hadrons and to discriminate them against QCD jets. We present the methodology and the results of the application at the interesting use case of the IDEA dual-readout calorimeter detector concept proposed for the future FCC-ee electron–positron collider.

21 October 2023
Verified
Book Chapter
Closed access
PDF file
JTJonas Teufel
Jonas Teufel
LTLuca Torresi
Luca Torresi
PRPatrick Reiser
Patrick Reiser
PFPascal Friederich
Pascal Friederich