Supported by the Alfred P. Sloan Foundation, the Energy Data Analytics Ph.D. Student Fellows program at Duke University readies emerging scholars to apply cutting-edge data science techniques to energy challenges.
The program has recently expanded and is currently accepting applications for its 2021 cohort from doctoral students at Duke University, North Carolina A&T State University, North Carolina State University, University of North Carolina at Chapel Hill, University of North Carolina at Charlotte, and University of North Carolina at Greensboro.
Want to apply? Submit the application form to Trey Gowdy (firstname.lastname@example.org) as a PDF by 11:59 p.m. ET on Dec. 11, 2020 and ask your faculty project advisors to submit their nomination letters by the same date.
Questions? Contact Trey Gowdy (email@example.com), Program Coordinator for the Energy Data Analytics Lab.
About the Fellows Program
The recent growth of energy-related data and evolution of data science techniques have created promising new opportunities for solving energy challenges. Capitalizing on these will require scholars with training in both data science and energy application domains. Yet traditional graduate education is limited in its ability to provide such dual expertise. In 2018, the Duke University Energy Initiative established the Energy Data Analytics Ph.D. Student Fellows program, preparing cohorts of next-generation scholars to deftly wield data in pursuit of accessible, affordable, reliable, and clean energy systems. This program is funded by a grant from the Alfred P. Sloan Foundation.
Each Ph.D. Student Fellow in the program conducts a related research project, working with faculty from multiple disciplines and receiving financial support for 3 months of summer support and $1,500 in research funds for computation and professional development. The fellows take part in regular mentorship and training workshops to improve their understanding of energy systems and data science tools and practices as well as to enhance their skills at collaborating and communicating across disciplines.
The first two cohorts of fellows included Duke University doctoral students from degree programs in civil and environmental engineering, computer science, earth and ocean sciences, electrical and computer engineering, and environmental policy. The program has since expanded to welcome applications from doctoral students at Duke University, North Carolina A&T State University, North Carolina State University, University of North Carolina at Chapel Hill, University of North Carolina at Charlotte, and University of North Carolina at Greensboro.
The program is affiliated with the Energy Data Analytics Lab, a collaborative effort of the Duke University Energy Initiative (which houses it), the Rhodes Information Initiative at Duke (Rhodes iiD), and the Social Science Research Institute (SSRI). (Note: Conclusions reached or positions taken by researchers or other grantees represent the views of the grantees themselves and not those of the Alfred P. Sloan Foundation or its trustees, officers, or staff).
Interested in Applying?
- Any Duke University, NC A&T State University, NC State University, UNC Chapel Hill, UNC Charlotte, or UNC Greensboro doctoral student currently enrolled full-time in their degree program is welcome to apply. Note: As Duke University is the host institution for this grant, approximately half of the Fellowships will go to Duke students each year.
- The student must be working with (or proposing to work with) two faculty members representing interdisciplinary expertise across both an energy application domain (e.g., energy technologies, systems, markets, and policies) and a data science field (e.g., statistics, machine learning, and other computational methods, especially as applied to “big data”). These faculty members can both be from the student’s home university or one from their home university and one from one of the eligible universities listed above.
- Doctoral student must show evidence of genuine interest in research on energy data analytics topics that incorporate data science methodologies/tools. It is preferable if the proposed work plays a role in their larger dissertation objectives.
- Applicants must be making successful academic progress in their home department.
Benefits for Successful Applicants
- Three months of 100% funding support for summer 2021 for student stipend and fringe, and 50% support for tuition remission – up to $10,712*. Details vary by home university. Note: No home-institution overhead will be compensated.
- Research support funding for data collection, software tools, equipment, conference participation, publication, or other research-related needs up to $1,500,
- Mentorship and training from interdisciplinary energy and data science scholars.
- Fellows’ work will be spotlighted on the Energy Data Analytics Ph.D. Student Fellows program webpage and at an Energy Data Analytics Symposium for eminent and emerging scholars in 2023.
*Financial support provided will cover up to 100% of stipend and fringe costs and 50% of tuition remission based on Duke University amounts. Amounts for non-Duke students may vary depending on university, and shall not exceed Duke University amounts.
- Devote 100% of their summer research effort over the fellowship performance period (three months) towards their proposed fellowship project.
- Complete their proposed research products, with one of those being a paper of some form, by December 1, 2021, and share copies of those deliverables and any other deliverables resulting from the project (including papers, code, datasets, presentations, etc.) with the staff of the fellowship program.
- Attend meetings hosted by the program, which includes two pre-fellowship meetings, seven summer meetings, and three to four post-fellowship workshops/events on disseminating project outcomes. It is the intent that these meetings may take place in-person at Duke University; however, this is subject to change.
- Provide a final presentation on their project that will be recorded and shared publicly.
- Provide acknowledgment of any work completed through the Fellowship with the line: “Support for this work was provided by the Alfred P. Sloan Foundation through the Duke University Energy Data Analytics Ph.D. Student Fellowship.”
- Fill out a pre- and post- fellowship survey for program evaluation.
December 11, 2020
Applications due by 11:59 p.m. ET.
Late January 2021
Ph.D. Student Fellowships will be announced.
February 2021 (exact date TBD)
Pre-Fellowship survey is due.
Mid-March and mid-April 2021 (exact dates TBD)
Prep meetings will include meeting faculty and other Fellows, developing project pitches, forming cohort pairs, learning about energy and data science content tailored to the cohort, and discussing project plans and goals.
May 15 – August 15, 2021
The summer 2021 performance period will include mentorship workshops on May 19, June 2, June 16, June 30, July 14, July 28, and August 11. These workshops will include Fellows’ research updates, energy applications, and data sources, as well as data science methodology content. Content to be delivered by program organizers, faculty advisors, and guest speakers.
September/October 2021 (exact dates TBD)
Fellows will take part in post-fellowship workshops on disseminating project outcomes.
November/December 2021 (exact dates TBD)
Fellows will share their work at panel presentation(s).
December 1, 2021
Fellows will complete their proposed research products, with one of those being a paper of some form. They will share copies of those deliverables (and any other deliverables resulting from the project) with the staff of the fellowship program.
December 2021 (exact date TBD)
Complete post-Fellowship survey,
Energy Data Analytics Symposium
Alina is a computer science Ph.D. student working with Professor Cynthia Rudin in the Prediction Analysis Lab. She is interested in identifying buildings with poor insulation to better inform civic planning as well as data concerning efficiency.
Project summary: “A poorly insulated building requires more energy to heat and cool than a well-insulated building. Using publicly available thermal satellite imagery and a super-resolution algorithm, estimates can be made about the energy efficiency of individual buildings. Super-resolution is the problem of finding a high-resolution image from a low-resolution image. The goal is to create high-resolution, accurate, realistic reconstructed images from low-resolution images to enhance image data and recover visual information. By identifying buildings with poor insulation (and therefore poor energy efficiency), policy can be informed by data, such as providing incentives to install new insulation. My goal is for data to detect in-need communities not only by region, but by specific household, to further direct policy and civic planning.”
You can contact Alina at firstname.lastname@example.org.
Bohao Huang is a Ph.D. student in electrical and computer engineering at the Pratt School of Engineering. Working in Duke’s Applied Machine Learning Lab, he is interested in leveraging advances in deep learning to develop algorithms that can automatically extract energy systems information from aerial imagery.
Project Summary: “Energy security is vital to the prosperity and sustainability of modern societies. Ensuring energy security relies upon effective decision-making and energy systems modeling, a crucial component of which is access to high quality energy systems information. Unfortunately, however, such information is often of limited availability, incomplete, or difficult to access because it is proprietary. Aerial imagery (e.g., color satellite imagery) is increasingly cheap and abundant, and may provide a rich source of energy systems information, however extracting useful information from such imagery is costly. I propose to leverage recent advances in deep learning to develop algorithms that can automatically extract useful energy systems information from large volumes of aerial imagery, potentially yielding a powerful and scalable new source of such information.”
You can contact Bohao at email@example.com.
Qingran Li is a Ph.D. student in the University Program in Environmental Policy (economics track) offered jointly by Duke's Nicholas School of the Environment and Sanford School of Public Policy. Her research includes using analytical tools to understand behavioral responses to policies and developing interdisciplinary solutions to energy and environmental issues.
Project summary: "Residential electricity consumption is an important indicator of household characteristics, but it is often held confidential by utilities and seldom reported by publicly available energy surveys. Missing such information significantly constrains our ability to answer important policy questions. My project targets a big question: How can we estimate residential electricity demand more precisely? Using the smart meter data set from an Irish CER trial project and the national time use survey, this project aims at correcting the estimation bias from behavioral and policy-related factors which are often overlooked in the conventional engineering and statistical models. A new algorithm will be developed to identify residential usage patterns with additional information provided by behavioral surveys so that information lost from inadequate load samplings can be compensated."
You can contact Qingran at firstname.lastname@example.org.
Jun is a Ph.D. student in earth and ocean sciences at the Nicholas School of the Environment. Her research models energy systems in the context of trade to better understand international energy security.
Project Summary: “Embodied energy is the sum of energy consumed to produce a commodity and is widely used to assess the total environmental impacts of a production process. My project uses a hybrid input-output approach to model embodied energy flows throughout the global economy. This approach deviates from the existing literature by addressing the feedbacks between energy and non-energy industries rather than simply the use of energy by non-energy industries. This tool will allow for examination of industry requirements for energy transformations, as well as the embodied energy in supply chains, of over 130 countries across 20 years (1995-2015). My goal is to then use machine learning techniques to simulate the model for future impacts.”
You can contact Jun at email@example.com.
Edgar Virguez is a student in the doctoral program in environment at Duke's Nicholas School of the Environment. He is interested in contributing to the understanding of market mechanisms that facilitate the integration of variable energy resources. He holds a BS in environmental engineering, a BS in chemical engineering and a MS in environmental engineering. During the last decade, he has worked with several institutions (e.g., Universidad de los Andes, World Bank, Inter-American Development Bank) promoting the adoption of cleaner fuels in transport and industry throughout Latin America.
Project summary: "My project aims to design quantitative tools supporting the process of assessing policy and market approaches, promoting an increased penetration of variable energy resources in the energy matrix. This assessment will be performed based on the economic, reliability, and environmental dimensions of the electric power system, accounting for the benefits of reduced fuel use and emissions, and for the increased capital costs of renewables and the necessary re-dispatching of conventional generators."
You can contact Edgar at firstname.lastname@example.org.
Tianyu is a Ph.D. student in the department of computer science at Duke. Before coming to Duke, he obtained a BS in mathematics and computer science from the Hong Kong University of Science and Technology. His general research interests are in machine learning and applications of machine learning algorithms.
Project summary: "With the accumulation of energy data, energy domain problems are in need of more sophisticated machine learning models such as neural networks. However, building neural networks of high quality requires heavy human effort, since different hyperparameter configurations lead to significantly different performances. My project will use a multi-armed bandit approach to efficiently design the architecture of neural networks for energy domain problems such as energy demand prediction."
You can contact Tianyu at email@example.com.
Tongshu Zheng is a Ph.D. student in civil and environmental engineering at Duke’s Pratt School of Engineering. He is interested in leveraging data-driven techniques to solve air pollution problems including developing a novel satellite-based remote sensing algorithm to cost-effectively and accurately assess the loss in solar energy production due to particulate matter air pollution.
Project Summary: “Atmospheric particulate matter (PM) can diminish solar energy production through ambient PM and PM deposited on solar panels. Solar energy loss is estimated to be as high as 25–35% in highly polluted areas. My project aims to assess and predict the loss in solar energy production in a low-cost and accurate manner by using image processing techniques and machine learning algorithms to automatically extract information from the global, 3m resolution satellite imagery. I hope to inform solar energy companies about their daily production loss due to PM pollution as well as help them strategize the optimal solar panel cleaning frequency. I want my research to catalyze the development of startup companies that specialize in providing solar production loss data.”
You can contact Tongshu at firstname.lastname@example.org.