Dani Jones

Dani Jones

By |

Dani Jones’ research program drives CIGLR’s portfolio of research in data science, machine learning, and artificial intelligence, as applied to physical limnology, weather forecasting, water cycle predictions, ecology, and observing system design. This research program aims is to advance societal adaptations to the effects of climate change, including flooding of coasts, rivers, and cities. Dani’s background is in physical oceanography, with specific expertise in adjoint modeling for comprehensive sensitivity analysis and unsupervised classification for data analysis, mostly applied to the North Atlantic and Southern Ocean. In Dani’s current role, they are establishing CIGLR’s new Artificial Intelligence Laboratory, leveraging the institute’s extensive observing assets, datasets, modeling capacity, interdisciplinary expertise, and numerous regional and international partnerships.

Yulin Pan

Yulin Pan

By |

My research is mainly concerned with theoretical and computational hydrodynamics, with applications in nonlinear ocean wave prediction and dynamics, wave-body interactions, and wave turbulence theory. I have incorporated the data science tools in my research, especially in the following two projects:

1. Quantification of statistics of extreme ship motions in irregular wave fields: In this project, we propose a new computational framework that directly resolves the statistics (and causal factors) of extreme ship responses in a nonlinear wave field. The development leverages a range of physics and learning based approaches, including nonlinear wave simulations (potential flow), ship response simulations (e.g., CFD), dimension-reduction techniques, sequential sampling, Gaussian process regression (Kriging) and multi-fidelity methods. The key features of the new approach include (i) description of the stochastic wave field by a low-dimensional probabilistic parameter space, and (ii) use of minimum number of CFD simulations to provide most information for converged statistics of extreme motions.

2. Real-time wave prediction with data assimilation from radar measurements: In this project, we develop the real-time data assimilation algorithm adapted to the CPU-GPU hardware architecture, to reduce the uncertainties associated with radar measurement errors and environmental factors such as wind and current in the realistic ocean environment. Upon integration with advanced in-situ or remote wave sensing technology, the developed computational framework can provide heretofore unavailable real-time forecast capability for ocean waves.