IDEAL

Image across Domains, Experiments, Algorithms and Learning

Dani Ushizima, Ph.D. is a scientist who investigates computational approaches based on Machine Learning to interface data-driven models to materials characterization. Main expertise is on Computer Vision applied to multimodal imaging for measuring 2D and 3D structure across spatial scales, which is key to advance research and design of new materials imaged using instruments reliant on x-ray, electron, confocal, and other light-matter interactions. The current focus is on lithium metal batteries and biofuel. She is also a Faculty affiliated with the Bakar Institute, at UC San Francisco, consulting on biomedical imaging projects, and BIDS, UC Berkeley.

Almost 15 years at LBNL, her research in image analysis and pattern recognition has impacted a broad array of scientific investigations that depend upon images. In 2016, Ushizima received the U.S. Department of Energy Early Career Research award to focus on pattern recognition applied to diverse scientific domains - images range from biomedical to new materials science samples. She is also the recipient of the Science without Borders Special Researcher award (CNPq/Brazil) for her work on machine learning applied to cytology, as part of a cancer research initiative focused on women's healthcare. She has also led the Computer Vision team for the Center for Advanced Mathematics for Energy Related Applications (CAMERA). Other initiatives she co-leads are CRIC (cancer), ImageXD (multimodal imaging) and ACTS (COVID-19 screening). Proud to be part of the Machine Learning and Analytics Group.