Data Driven
Data-driven approaches are revolutionizing scientific research and engineering by leveraging vast datasets to build predictive models and automate complex tasks. Current research focuses on developing and refining algorithms like neural networks (including transformers and graph neural networks), Gaussian processes, and ADMM for diverse applications, ranging from autonomous systems and financial forecasting to scientific discovery and healthcare. This shift towards data-centric methodologies promises to accelerate scientific progress and improve the efficiency and effectiveness of various technological systems, particularly in areas where traditional modeling approaches are limited by complexity or data scarcity.
Papers
Depth video data-enabled predictions of longitudinal dairy cow body weight using thresholding and Mask R-CNN algorithms
Ye Bi, Leticia M. Campos, Jin Wang, Haipeng Yu, Mark D. Hanigan, Gota Morota
On the choice of training data for machine learning of geostrophic mesoscale turbulence
F. E. Yan, J. Mak, Y. Wang