Dive into this foundational video on unsupervised learning by Dr. Jordan Malof. This talk introduces common unsupervised learning techniques and how they can be applied to energy challenges. You’ll hear about mixed clustering, dimensionality reduction, and more!
The Duke University Energy Initiative and Innovation & Entrepreneurship Initiative have awarded the 2021 Clean Energy Prize to Michael Valerino, a Ph.D. student in civil and environmental engineering at the Pratt School of Engineering. The prize will support Valerino’s project team to develop an interactive, data-driven platform aimed at reducing dust-related solar energy losses.
Check out this introductory talk by Dr. Kyle Bradbury (Energy Data Analytics Lab & Pratt School of Engineering) on computer vision. Featuring discussion of segmentation, object detection, and more along with examples of how computer vision can be applied to get insights about energy systems! The first part of a new series on Foundations for Energy Data Analytics.
Dozens of undergraduate and graduate students from across Duke University are taking deep dives into the energy industry this summer.
Two of Duke’s interdisciplinary units will be merged as the university continues its efforts to address climate change and its impacts. The Nicholas Institute for Environmental Policy Solutions and Duke University Energy Initiative will begin the merger process at the start of Duke’s fiscal year on July 1. Energy Initiative director Dr. Brian Murray, Ph.D., will assume the interim directorship of the newly formed unit at that time.
The team used machine learning to create a model that detected wind turbines solely from satellite imagery by training it first with real images of turbines. Since these images are scarce and in practice the machine learning techniques need to be applied to different locations than from where the training data are available, this approach was compared to data resulting from a model which also was trained on synthetic images of wind turbines. Synthetic images, while they might look real to the machine, are generated images and are not genuine photos. Feeding the model synthetic images of wind turbines increased the accuracy or “average precision” of the predicted turbine location.
Duke in DC brings together experts on a variety of topics that have direct or downstream effects on environmental justice, both domestically and abroad. Panelists consider ways to improve affordability, advance sustainability, and increase access to essential resources as well as provide their recommendations and policy considerations for Congress and the Biden administration. Panelists include: Rachel Brewster, Jeffrey and Bettysue Hughes Professor of Law, Duke School of Law; Jackson Ewing, Senior Fellow, Duke Nicholas Institute for Environmental Policy Solutions; and moderated by Jariel Arvin, Foreign and World Fellow, Vox.
While electric vehicles are growing in popularity, they still face hurdles as they head toward mainstream acceptance among drivers. Two Duke scholars, Tim Johnson and Jennifer Weiss, discussed the benefits and challenges of electric vehicles during a virtual briefing with journalists.
Hear from Latinx Duke alumni as they share their knowledge from the field, motivations for addressing climate change, and how this challenging issue is more than a problem for science; it’s also personal. Hosted by Duke University Hispanic/Latino Alumni Association (DUHLAA), this webinar also features Dr. Luana Lima Associate Director for Educational Programs within the Energy Initiative.
The Duke University Energy Initiative and Innovation & Entrepreneurship Initiative announce the return of the Clean Energy Prize to support the development of energy technologies, products, and services at Duke. The Prize makes a $10,000 award to support novel ideas, potential products, and services that advance an accessible, reliable, affordable, and clean energy future.