A dive into the different ways that Artificial Intelligence (AI) can and is being used in the VFX industry.
Due to the complex interplay of various meteorological phenomena, simulating weather is a challenging and open problem. We propose a novel physics-based model that enables simulating weather at interactive rates. By considering atmosphere and pedosphere, we can describe local phenomena in unprecedented detail. Specifically, our model captures different warm and cold clouds, such as mammatus, hole-punch, multi-layer, and cumulonimbus clouds as well as their dynamic transitions. We also model different precipitation types, such as rain, snow, and graupel.
Our model enables us to interactively explore various complex weather phenomena, including the hydrologic cycle, Foehn winds, high-precipitation cumulonimbus, complex 3D dynamic scenes of weatherscapes, and even nowcasting real weather conditions as simulations by streaming weather data into our framework. Moreover, a machine learning scheme can then be trained on these physics-based examples, resulting in an approximation of the simulation that is computationally cheap enough for real-time applications.
Project Contributors: Jorge Alejandro Amador Herrera, Torsten Hadrich, Wojtek Palubicki, Daniel T. Banuti, Soren Pirk, Dominik L. Michels.
SPEAKER
Jorge Alejandro Amador Herrera
Ph.D. Candidate // King Abdullah University of Science and Technology
Alejandro Amador is a Ph.D. candidate in the Computational Sciences Group of the King Abdullah University of Science and Technology (KAUST). His research interests are the physically-based simulation of natural phenomena and interactive modelling approaches in the field of computer graphics, as well as the development of AI solutions for diverse optimization problems and the production of synthetic data. Previously, he studied Applied Mathematics (M. Sc.), Physics (B. Sc.) and Mathematics (B.Sc.).
A dive into the different ways that Artificial Intelligence (AI) can and is being used in the VFX industry.
Due to the complex interplay of various meteorological phenomena, simulating weather is a challenging and open problem. We propose a novel physics-based model that enables simulating weather at interactive rates. By considering atmosphere and pedosphere, we can describe local phenomena in unprecedented detail. Specifically, our model captures different warm and cold clouds, such as mammatus, hole-punch, multi-layer, and cumulonimbus clouds as well as their dynamic transitions. We also model different precipitation types, such as rain, snow, and graupel.
Our model enables us to interactively explore various complex weather phenomena, including the hydrologic cycle, Foehn winds, high-precipitation cumulonimbus, complex 3D dynamic scenes of weatherscapes, and even nowcasting real weather conditions as simulations by streaming weather data into our framework. Moreover, a machine learning scheme can then be trained on these physics-based examples, resulting in an approximation of the simulation that is computationally cheap enough for real-time applications.
Project Contributors: Jorge Alejandro Amador Herrera, Torsten Hadrich, Wojtek Palubicki, Daniel T. Banuti, Soren Pirk, Dominik L. Michels.
SPEAKER
Jorge Alejandro Amador Herrera
Ph.D. Candidate // King Abdullah University of Science and Technology
Alejandro Amador is a Ph.D. candidate in the Computational Sciences Group of the King Abdullah University of Science and Technology (KAUST). His research interests are the physically-based simulation of natural phenomena and interactive modelling approaches in the field of computer graphics, as well as the development of AI solutions for diverse optimization problems and the production of synthetic data. Previously, he studied Applied Mathematics (M. Sc.), Physics (B. Sc.) and Mathematics (B.Sc.).
