SKStefan Kesselheim

Stefan Kesselheim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Stefan Kesselheim has a total of 119 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MatBind: a shared embedding space for multimodal materials characterization

    by Le Yang, Anoop K. Chandran, Jona Östreicher, Evgenii Sovetkin, Adrian Mirza, Sebastien Bompas, Bashir Kazimi, Pascal Friederich, Stefan Kesselheim, Kevin Maik Jablonka, et al.

    Fully characterizing a crystalline material requires integrating heterogeneous data sources—atomic structures, diffraction patterns, electronic density of states, and natural language—each of which captures a different facet of the same physical object. In practice, however, these modalities are stored and analyzed in isolation, making it difficult to relate or query materials across representational boundaries. We present MatBind , a contrastive learning framework that aligns four material modalities—crystal structure, powder X-ray diffraction (pXRD) simulated from structures, density of states (DOS), and text—into a unified embedding space using crystal structure as the central physical anchor. The framework induces alignment between modalities never explicitly paired during training, enabling emergent zero-shot cross-modal retrieval as a direct consequence of the shared representation. The learned embedding space organizes materials according to physically meaningful properties without explicit supervision, and retrieval performance improves systematically when modalities are combined at query time. These results demonstrate that treating heterogeneous materials data as complementary projections of a single physical reality, rather than as isolated data sources, is not a practical choice but is consistent with the underlying physics.

  • Open Access

    Machine learning for neutron source distributions

    by José Ignacio Robledo, Norberto Schmidt, Klaus Lieutenant, Jingjing Li, Stefan Kesselheim, Paul Zakalek

    In light of the recent advancements in machine learning (ML), we propose a novel approach to neutron source distribution estimation through the utilization of probabilistic generative models (PGMs). The estimation is based on a Monte Carlo particle list, which is only required during the training stage of the ML model. Once the source distribution has been learned, the model is independent of the original particle list, allowing for further sampling in an efficient, rapid, and memory-costless manner. The performance of various generative models is evaluated, including a variational autoencoder, a normalizing flow, a generative adversarial network, and a denoising diffusion model. These approaches are then compared to existing source distribution estimations, and the advantages and disadvantages of each approach are discussed. The results demonstrate that source distributions can be modeled through the use of PGMs, which paves the way for further advancements in this field.

  • Fourier Neural Operators for Rayleigh–Bénard Convection

    by Chelsea Maria John, Thibaut Lunet, Sebastian Götschel, Andreas Herten, Stefan Kesselheim, Daniel Ruprecht

  • Open Access

    Highly Polygenic Control of Photosynthetic Responses to Nighttime Temperature Studied by Genomic Prediction

    by Ana Carolina dos Santos Sá, Alina Bazarova, Andreas Fischbach, Stefan Kesselheim, Benjamin Stich, Shizue Matsubara

    Rising nighttime temperature (T night ) can reduce crop yields while low T night may restrict plant growth and development. Despite quantifiable effects of T night , genetic basis underlying plant responses to T night remains unclear. We investigated natural variation in long‐term response of effective photosynthetic efficiency (F q ’/F m ’) to T night among Arabidopsis accessions. Genome‐wide association study (GWAS) was conducted for F q ’/F m ’ of the plants grown under 15°C or 20°C T night . GWAS revealed highly polygenic architecture of F q ’/F m ’, with associated single nucleotide polymorphisms (SNPs) varying across T night conditions and measurement days. Notably, 15°C T night stabilised the contributions of a subset of SNPs, whereas 20°C T night enhanced day‐to‐day variations in SNP‐trait associations. We then incorporated the associated SNPs in genomic prediction (GP) models to assess the improvement of prediction accuracy. The GWAS‐derived SNPs significantly improved the prediction ability of GP models, indicating collective influence of numerous small‐effect SNPs. Finally, the model predictions were experimentally validated in an independent, genetically diverse population, which confirmed the correct identification of low‐F q ’/F m ’ accessions in 15°C T night . These results uncover the genetic underpinnings of long‐term F q ’/F m ’ response to cool vs warm nights and establish a framework for leveraging GWAS and GP to explore complex traits, such as photosynthesis, toward breeding climate‐resilient crops.

  • Open Access

    Highly polygenic control of photosynthetic responses to nighttime temperature in Arabidopsis studied by genomic prediction

    by Ana Carolina dos Santos Sá, Alina Bazarova, Andreas Fischbach, Stefan Kesselheim, Benjamin Stich, Shizue Matsubara

    Summary: Rising nighttime temperature (T night ) can reduce crop yields, while low T night may restrict plant growth and development. Despite these quantifiable effects of T night , the genetic basis underlying plant responses to T night remains unclear. We investigated natural variation in long-term response of effective photosynthetic efficiency (F q ’/F m ’) to T night among Arabidopsis accessions. Genome-wide association study (GWAS) was conducted for F q ’/F m ’ of the accessions grown under 15°C or 20°C T night . The associated single nucleotide polymorphisms (SNPs) were identified and incorporated in genomic prediction (GP) models to assess the improvement of prediction accuracy. The predictions were experimentally validated in an independent, genetically diverse population. GWAS revealed highly polygenic architecture of F q ’/F m ’, with associated SNPs varying across T night conditions and measurement days. Notably, 15°C T night stabilized the contributions of a subset of associated SNPs, whereas 20°C T night enhanced day-to-day variations in SNP-trait associations. The GWAS-derived SNPs significantly improved the prediction accuracy of GP models, indicating their collective influence. The validation experiment confirmed the identification of low-F q ’/F m ’ accessions in 15°C T night . The results uncover the genetic underpinnings of long-term F q ’/F m ’ response to cool vs warm nights and establish a framework for leveraging GWAS and GP to explore complex traits, such as photosynthesis, toward breeding climate-resilient crops.

  • Lossy Neural Compression for Geospatial Analytics: A review

    by Carlos Gomes, Isabelle Wittmann, Damien Robert, Johannes Jakubik, Tim Reichelt, Stefano Maurogiovanni, Rikard Vinge, Jonas Hurst, Erik Scheurer, Rocco Sedona, et al.

    Over the past decades, there has been an explosion in the amount of available Earth observation (EO) data. The unprecedented coverage of Earth’s surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth system models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates because of their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC, including seminal works in its traditional applications to image and video compression domains with a focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with “natural images,” and we explain the additional challenges and opportunities they present. Additionally, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FMs) has advanced methods to efficiently distill representations from vast amounts of unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine-to-machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESMs.


  • Open Access

    Nanopore- and AI-empowered microbial viability inference

    by Harika Ürel, Sabrina Benassou, Hanna Marti, Tim Reska, Ela Sauerborn, Yuri Pinheiro Alves De Souza, Albert Perlas, Enrique Rayo, Michael Biggel, Stefan Kesselheim, et al.

    Background: The ability to differentiate between viable and dead microorganisms in metagenomic data is crucial for various microbial inferences, ranging from assessing ecosystem functions of environmental microbiomes to inferring the virulence of potential pathogens from metagenomic analysis. Established viability-resolved genomic approaches are labor-intensive as well as biased and lacking in sensitivity. Results: We here introduce a new fully computational framework that leverages nanopore sequencing technology to assess microbial viability directly from freely available nanopore signal data. Our approach utilizes deep neural networks to learn features from such raw nanopore signal data that can distinguish DNA from viable and dead microorganisms in a controlled experimental setting of UV-induced Escherichia cell death. The application of explainable artificial intelligence (AI) tools then allows us to pinpoint the signal patterns in the nanopore raw data that allow the model to make viability predictions at high accuracy. Using the model predictions as well as explainable AI, we show that our framework can be leveraged in a real-world application to estimate the viability of obligate intracellular Chlamydia, where traditional culture-based methods suffer from inherently high false-negative rates. This application shows that our viability model captures predictive patterns in the nanopore signal that can be utilized to predict viability across taxonomic boundaries. We finally show the limits of our model’s generalizability through antibiotic exposure of a simple mock microbial community, where a new model specific to the killing method had to be trained to obtain accurate viability predictions. Conclusions: While the potential of our computational framework’s generalizability and applicability to metagenomic studies needs to be assessed in more detail, we here demonstrate for the first time the analysis of freely available nanopore signal data to infer the viability of microorganisms, with many potential applications in environmental, veterinary, and clinical settings.


  • Top Cited Papers
    Open Access

    Automatic heliostat learning for in situ concentrating solar power plant metrology with differentiable ray tracing

    by Max Pargmann, Jan Ebert, Markus Götz, Daniel Maldonado Quinto, Robert Pitz-Paal, Stefan Kesselheim

    Concentrating solar power plants are a clean energy source capable of competitive electricity generation even during night time, as well as the production of carbon-neutral fuels, offering a complementary role alongside photovoltaic plants. In these power plants, thousands of mirrors (heliostats) redirect sunlight onto a receiver, potentially generating temperatures exceeding 1000°C. Practically, such efficient temperatures are never attained. Several unknown, yet operationally crucial parameters, e.g., misalignment in sun-tracking and surface deformations can cause dangerous temperature spikes, necessitating high safety margins. For competitive levelized cost of energy and large-scale deployment, in-situ error measurements are an essential, yet unattained factor. To tackle this, we introduce a differentiable ray tracing machine learning approach that can derive the irradiance distribution of heliostats in a data-driven manner from a small number of calibration images already collected in most solar towers. By applying gradient-based optimization and a learning non-uniform rational B-spline heliostat model, our approach is able to determine sub-millimeter imperfections in a real-world setting and predict heliostat-specific irradiance profiles, exceeding the precision of the state-of-the-art and establishing full automatization. The new optimization pipeline enables concurrent training of physical and data-driven models, representing a pioneering effort in unifying both paradigms for concentrating solar power plants and can be a blueprint for other domains.


  • Open Access

    Nanopore- and AI-empowered microbial viability inference

    by Harika Ürel, Sabrina Benassou, Hanna Marti, Tim Reska, Ela Sauerborn, Yuri Pinheiro Alves De Souza, Albert Perlas, Enrique Rayo, Michael Biggel, Stefan Kesselheim, et al.

    The ability to differentiate between viable and dead microorganisms in metagenomic data is crucial for various microbial inferences, ranging from assessing ecosystem functions of environmental microbiomes to inferring the virulence of potential pathogens from metagenomic analysis. While established viability-resolved genomic approaches are labor-intensive as well as biased and lacking in sensitivity, we here introduce a new fully computational framework that leverages nanopore sequencing technology to assess microbial viability directly from freely available nanopore signal data. Our approach utilizes deep neural networks to learn features from such raw nanopore signal data that can distinguish DNA from viable and dead microorganisms in a controlled experimental setting of UV-induced Escherichia cell death. The application of explainable AI tools then allows us to pinpoint the signal patterns in the nanopore raw data that allow the model to make viability predictions at high accuracy. Using the model predictions as well as explainable AI, we show that our framework can be leveraged in a real-world application to estimate the viability of obligate intracellular Chlamydia , where traditional culture-based methods suffer from inherently high false negative rates. This application shows that our viability model captures predictive patterns in the nanopore signal that can be utilized to predict viability across taxonomic boundaries. We finally show the limits of our model’s generalizability through antibiotic exposure of a simple mock microbial community, where a new model specific to the killing method had to be trained to obtain accurate viability predictions. While the potential of our computational framework’s generalizability and applicability to metagenomic studies needs to be assessed in more detail, we here demonstrate for the first time the analysis of freely available nanopore signal data to infer the viability of microorganisms, with many potential applications in environmental, veterinary, and clinical settings. Author summary: Metagenomics investigates the entirety of DNA isolated from an environment or a sample to holistically understand microbial diversity in terms of known and newly discovered microorganisms and their ecosystem functions. Unlike traditional culturing of microorganisms, genomic approaches are not able to differentiate between viable and dead microorganisms since DNA might persist under different environmental circumstances. The viability of microorganisms is, however, of importance when making inferences about a microorganism’s metabolic potential, a pathogen’s virulence, or an entire microbiome’s impact on its environment. As existing viability-resolved genomic approaches are labor-intensive, expensive, and lack sensitivity, we here investigate our hypothesis if freely available nanopore sequencing signal dat that captures DNA molecule information beyond the DNA sequence might be leveraged to infer such viability. This hypothesis assumes that DNA from dead microorganisms accumulates certain damage signatures that reflect microbial viability and can be read from nanopore signal data using fully computational frameworks. We here show first evidence that such a computational framework might be feasible by training a deep model on controlled experimental data to predict viability at high accuracy, exploring what the model has learned, and using it in a real-world application by application to a bacterial species of veterinary relevance. We finally show that a specific model has to be trained to accurately predict viability after antibiotic exposure of a mock microbial community. While the generalizability of our computational framework therefore needs to be assessed in much more detail, we here demonstrate that freely available data might be usable for relevant viability inferences in environmental, veterinary, and clinical settings.


  • Top Cited Papers
    Open Access

    MISATO: machine learning dataset of protein–ligand complexes for structure-based drug discovery

    by Till Siebenmorgen, Filipe Menezes, Sabrina Benassou, Erinc Merdivan, Kieran Didi, André Santos Dias Mourão, Radosław Kitel, Pietro Liò, Stefan Kesselheim, Marie Piraud, et al.

    Large language models have greatly enhanced our ability to understand biology and chemistry, yet robust methods for structure-based drug discovery, quantum chemistry and structural biology are still sparse. Precise biomolecule–ligand interaction datasets are urgently needed for large language models. To address this, we present MISATO, a dataset that combines quantum mechanical properties of small molecules and associated molecular dynamics simulations of ~20,000 experimental protein–ligand complexes with extensive validation of experimental data. Starting from the existing experimental structures, semi-empirical quantum mechanics was used to systematically refine these structures. A large collection of molecular dynamics traces of protein–ligand complexes in explicit water is included, accumulating over 170 μs. We give examples of machine learning (ML) baseline models proving an improvement of accuracy by employing our data. An easy entry point for ML experts is provided to enable the next generation of drug discovery artificial intelligence models.