@article{AntonHendersonDaRosetal.2024, author = {Anton, Oliver and Henderson, Victoria A. and Da Ros, Elisa and Sekulic, Ivan and Burger, Sven and Schneider, Philipp-Immanuel and Krutzik, Markus}, title = {Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments}, volume = {5}, journal = {Mach. Learn. Sci. Technol.}, arxiv = {http://arxiv.org/abs/2312.13397}, doi = {10.1088/2632-2153/ad3cb6}, pages = {025022}, year = {2024}, language = {en} } @inproceedings{SekulicSchneiderAntonetal.2023, author = {Sekulic, Ivan and Schneider, Philipp-Immanuel and Anton, Oliver and Da Ros, Elisa and Henderson, Victoria and Krutzik, Markus}, title = {Efficient machine-learning approach to optimize trapped cold atom ensembles for quantum memory applications}, volume = {12740}, booktitle = {Proc. SPIE}, doi = {10.1117/12.2684406}, pages = {127400F}, year = {2023}, language = {en} } @article{SekulicSchaibleMuelleretal.2025, author = {Sekulic, Ivan and Schaible, Jonas and M{\"u}ller, Gabriel and Plock, Matthias and Burger, Sven and Mart{\´i}nez-Lahuerta, V{\´i}ctor Jos{\´e} and Gaaloul, Naceur and Schneider, Philipp-Immanuel}, title = {Physics-informed Bayesian optimization of expensive-to-evaluate black-box functions}, volume = {6}, journal = {Mach. Learn. Sci. Technol.}, publisher = {IOP Publishing}, doi = {10.1088/2632-2153/ae1f5f}, pages = {040503}, year = {2025}, abstract = {Abstract Bayesian optimization with Gaussian process surrogates is a popular approach for optimizing expensive-to-evaluate functions in terms of time, energy, or computational resources. Typically, a Gaussian process models a scalar objective derived from observed data. However, in many real-world applications, the objective is a combination of multiple outputs from physical experiments or simulations. Converting these multidimensional observations into a single scalar can lead to information loss, slowing convergence and yielding suboptimal results. To address this, we propose to use multi-output Gaussian processes to learn the full vector of observations directly, before mapping them to the scalar objective via an inexpensive analytical function. This physics-informed approach retains more information from the underlying physical processes, improving surrogate model accuracy. As a result, the approach accelerates optimization and produces better final designs compared to standard implementations.}, language = {en} } @misc{SekulicSchaibleMuelleretal.2025, author = {Sekulic, Ivan and Schaible, Jonas and M{\"u}ller, Gabriel and Plock, Matthias and Burger, Sven and Martinez-Lahuerta, Victor J. and Gaaloul, Naceur and Schneider, Philipp-Immanuel}, title = {Data publication for Physics-informed Bayesian optimization of expensive-to-evaluate black-box functions}, journal = {Zenodo}, doi = {10.5281/zenodo.16751507}, year = {2025}, language = {en} } @misc{SekulicSchneiderHammerschmidtetal.2024, author = {Sekulic, Ivan and Schneider, Philipp-Immanuel and Hammerschmidt, Martin and Burger, Sven}, title = {Machine-learning driven design of metasurfaces: learn the physics and not the objective function}, volume = {PC13017}, journal = {Proc. SPIE}, doi = {10.1117/12.3022119}, pages = {PC130170X}, year = {2024}, language = {en} } @article{MuellerMartinezLahuertaSekulicetal.2025, author = {M{\"u}ller, Gabriel and Mart{\´i}nez-Lahuerta, Victor J. and Sekulic, Ivan and Burger, Sven and Schneider, Philipp-Immanuel and Gaaloul, Naceur}, title = {Bayesian optimization for state engineering of quantum gases}, volume = {10}, journal = {Quantum Sci. Technol.}, arxiv = {http://arxiv.org/abs/2404.18234}, doi = {10.1088/2058-9565/ad9050}, pages = {015033}, year = {2025}, language = {en} } @article{SchaibleWinartoŠkorjancetal.2025, author = {Schaible, Jonas and Winarto, Hanifah and Škorjanc, Viktor and Yoo, Danbi and Zimmermann, Lea and J{\"a}ger, Klaus and Sekulic, Ivan and Schneider, Philipp-Immanuel and Burger, Sven and Wessels, Andreas and Bl{\"a}si, Benedikt and Becker, Christiane}, title = {Optimizing Aesthetic Appearance of Perovskite Solar Cells Using Color Filters}, volume = {9}, journal = {Solar RRL}, publisher = {Wiley}, doi = {10.1002/solr.202400627}, pages = {2400627}, year = {2025}, abstract = {The significance of color aesthetics in photovoltaic (PV) modules gains importance, especially in design-centric applications like building-integrated PVs. Color filters based on distributed Bragg reflectors, consisting of alternating thin-film layers of different refractive indices, can modify the appearance of standard silicon modules. This approach is also extended to optimize the color appearance of emerging PV technologies such as perovskite solar cells, which typically exhibit a less appealing gray-brownish appearance. In this contribution, perovskite solar-cell stacks combined with MorphoColor color filters are presented. Angular-resolved reflectance simulations based on wave optics and ray tracing with experimental data are validated, and the color appearance from various viewing angles is evaluated. Additionally, the impact of individual layers on color appearance and the maximum achievable short-circuit current density in the perovskite solar cell is investigated. By applying Bayesian optimization, the color distance is minimized to the targeted appearance. Tailoring the bridging layers between the color filter and the perovskite solar cell is found to strongly influence the color impression due to the coherently combined color filter and perovskite solar cell. The presented color optimization concept allows to customize the aesthetics of emerging PV thin-film technologies such as perovskite solar cells.}, language = {en} } @inproceedings{SchaibleWinartoSkorjancetal.2025, author = {Schaible, Jonas and Winarto, Hanifah and Skorjanc, Victor and Yoo, Danbi and Zimmermann, Lea and Wessels, Andreas and J{\"a}ger, Klaus and Sekulic, Ivan and Schneider, Philipp-Immanuel and Bl{\"a}si, Benedikt and Burger, Sven and Becker, Christiane}, title = {Optimization strategies for colorful thin film solar cells}, volume = {PC13361}, booktitle = {Proc. SPIE}, doi = {10.1117/12.3041408}, pages = {PC133610E}, year = {2025}, language = {en} } @inproceedings{SekulicSchneiderHammerschmidtetal.2025, author = {Sekulic, Ivan and Schneider, Philipp-Immanuel and Hammerschmidt, Martin and Schaible, Jonas and Burger, Sven}, title = {Physics informed Bayesian optimization for inverse design of diffractive optical elements}, volume = {PC13573}, booktitle = {Proc. SPIE}, doi = {10.1117/12.3064372}, pages = {PC135730R}, year = {2025}, language = {en} } @article{BinkowskiKoulasSimosBetzetal.2025, author = {Binkowski, Felix and Koulas-Simos, Aris and Betz, Fridtjof and Plock, Matthias and Sekulic, Ivan and Manley, Phillip and Hammerschmidt, Martin and Schneider, Philipp-Immanuel and Zschiedrich, Lin and Munkhbat, Battulga and Reitzenstein, Stephan and Burger, Sven}, title = {High Purcell enhancement in all-TMDC nanobeam resonator designs with active monolayers for nanolasers}, volume = {112}, journal = {Phys. Rev. B}, arxiv = {http://arxiv.org/abs/2508.05333}, doi = {10.1103/nxh9-dhvx}, pages = {235410}, year = {2025}, language = {en} }