## Description *Optimized Ray-tracing for Cloud-Radiation Interaction Simulations in 3D using GPUs and Machine Learning (ORCRIST)* and *Scalable UNified Beam-tracing for Earth–Atmosphere Models (SUNBEAM)* are two sister projects in collaboration with the group of Ben van Werkhoven at [Leiden University](https://www.universiteitleiden.nl). ORCRIST is funded by the [NWO Open Technology Programme](https://www.nwo.nl/nieuws/zes-veelzijdige-toewijzingen-binnen-het-open-technologieprogramma) and SUNBEAM by the [Netherlands eScience Center](https://www.esciencecenter.nl/news/awarded-proposals-open-escience-call-2025-oec25/) in the Open eScience Call 2025. Accurately simulating how sunlight and heat travel through the atmosphere is crucial for predicting weather, climate change, the development of wildfires, and the production of solar energy. Weather and climate models rely on strongly simplified one-dimensional radiative transfer, because three-dimensional simulations are computationally too expensive. In ORCRIST and SUNBEAM, we use GPU computing and machine learning to accelerate our Monte Carlo ray tracer, so that high-resolution atmospheric models such as [[MicroHH]] can capture the realistic 3D interactions between sunlight, clouds, wildfire smoke, and the Earth's surface. ## Output