2026-04-16T16:08:11Zhttps://www.radar-service.eu/oai/OAIHandler

10.35097/n8zc8hdj9myu0dj02026-03-16T06:34:36Zradar4kit

10.35097/n8zc8hdj9myu0dj0 Dreisbach, Maximilian Maximilian Dreisbach 0000-0001-6308-0982 Kiyani, Elham Elham Kiyani Kriegseis, Jochen Jochen Kriegseis 0000-0002-2737-2539 Karniadakis, George Em George Em Karniadakis Stroh, Alexander Alexander Stroh 0000-0003-0850-9883 Karlsruhe Institute of Technology 2026 2026 Engineering two-phase flow interfacial dynamics physics-informed neural networks volumetric reconstruction deep learning Open Access Creative Commons Attribution 4.0 International Dreisbach, Maximilian 0000-0001-6308-0982 Kiyani, Elham Kriegseis, Jochen 0000-0002-2737-2539 Karniadakis, George Em Stroh, Alexander 0000-0003-0850-9883 Two-phase flow phenomena underpin critical technologies such as hydrogen fuel cells, spray cooling, and combustion, where droplet dynamics govern performance and efficiency. Conventional optical diagnostics, including shadowgraphy and particle image velocimetry, provide valuable insights but are limited to two-dimensional projections of inherently three-dimensional flows. We employ a specialized optical technique that encodes droplet surface information through color-coded glare points, enabling enhanced reconstruction of gas-liquid interfaces. To interpret these measurements, we introduce video-conditioned physics-informed neural networks VcPINNs, which integrate experimental observations with governing fluid dynamics equations. This hybrid framework leverages the strengths of both data-driven learning and physical constraints, allowing accurate volumetric flow reconstruction from limited input images. Applied to droplet impingement experiments, our method yields highly resolved and physically consistent 3D interface and flow dynamics. The combined imaging and PINN reconstruction strategy provides a powerful platform for advancing multiphase-flow analysis, with broad potential impact across energy, cooling, and propulsion applications. This dataset consists of raw and processed images, supplementary videos, and the neural network weights of the trained PINNs from the research work "PINNs4Drops: Video-conditioned physics-informed neural networks for two-phase flow reconstruction". The images were obtained by glare-point shadowgraphy experiments of impinging droplets. The raw images are saved in the uncompressed file format .tif, and processed images are saved as .png. https://publikationen.bibliothek.kit.edu/1000191059 12,1 GB application/x-tar