About

Ram Rajagopal is an Associate Professor of Civil and Environmental Engineering at Stanford University, where he also holds appointments in Electrical Engineering and is a Senior Fellow at the Precourt Institute for Energy. He directs the Stanford Sustainable Systems Lab (S3L), which focuses on large-scale monitoring, data analytics, and stochastic control for infrastructure networks, particularly power networks. His current research interests in power systems include the integration of renewables, smart distribution systems, and demand-side data analytics. Dr. Rajagopal holds a Ph.D. in Electrical Engineering and Computer Sciences and an M.A. in Statistics, both from the University of California Berkeley, along with a Masters in Electrical and Computer Engineering from the University of Texas, Austin, and a Bachelor's in Electrical Engineering from the Federal University of Rio de Janeiro. He has received numerous awards, including the NSF CAREER Award, Powell Foundation Fellowship, Berkeley Regents Fellowship, and the Makhoul Conjecture Challenge award. With more than 30 patents and several best paper awards, he has advised or founded various companies in sensor networks, power systems, and data analytics.

Research topics

• Environmental economics
• Automotive engineering
• Economics
• Electrical engineering
• Engineering
• Business
• Waste management
• Environmental science

Selected publications

• Solar and battery can reduce energy costs and provide affordable outage backup for US households

  Nature Energy · 2025-08-01 · 8 citations

  articleSenior authorCorresponding
  PublisherDOI

• Large-Scale Network Utility Maximization via GPU-Accelerated Proximal Message Passing

  ArXiv.org · 2025-09-12

  preprintOpen accessSenior author

  We present a GPU-accelerated proximal message passing algorithm for large-scale network utility maximization (NUM). NUM is a fundamental problem in resource allocation, where resources are allocated across various streams in a network to maximize total utility while respecting link capacity constraints. Our method, a variant of ADMM, requires only sparse matrix-vector multiplies with the link-route matrix and element-wise proximal operator evaluations, enabling fully parallel updates across streams and links. It also supports heterogeneous utility types, including logarithmic utilities common in NUM, and does not assume strict concavity. We implement our method in PyTorch and demonstrate its performance on problems with tens of millions of variables and constraints, achieving 4x to 20x speedups over existing CPU and GPU solvers and solving problem sizes that exhaust the memory of baseline methods. Additionally, we show that our algorithm is robust to congestion and link-capacity degradation. Finally, using a time-expanded transit seat allocation case study, we illustrate how our approach yields interpretable allocations in realistic networks.

  PublisherOA PDFDOI

• Built environment disparities are amplified during extreme weather recovery

  Nature · 2025-12-03 · 4 citations

  articleOpen accessSenior authorCorresponding

  Extreme weather events such as hurricanes and floods cause increasing damage to communities, leading to substantial economic losses and displacement of populations1–6. Previous research suggests that there are disparities in the resilience capacity of neighbourhoods, predicting a recovery mechanism of either segmented withdrawal or reinforcement across different neighbourhood groups7–12. Assessing these hypotheses and investigating if—and to what extent—neighbourhood built environments recover at scale has been difficult because previous measures have relied on aggregated survey data1,7,9–14. Here we construct a building-level disaster recovery dataset covering 2,195 census tracts spanning 16 states and across 12 extreme weather events in the USA from 2007 to 2023 using historical street view imagery and multimodal machine learning. Our analysis shows that in the aftermath of extreme weather events, lower-income neighbourhoods are less likely to rebuild and do not return to their pre-disaster state, whereas higher-income areas rebuild and tend to improve compared with their pre-disaster state, highlighting increasing disparities in their built environments. We further investigate those disparities by examining the deployment of disaster recovery assistance and insurance policies, and identify a resource gap for lower-income neighbourhoods that may explain unequal community responses to extreme weather events. Our findings demonstrate the value of analysing neighbourhood recovery trajectories at a higher resolution and larger scale to inform responsive policy designs, and suggest the importance of restructuring the recovery financial assistance framework to promote more climate resilient communities. Higher-income neighbourhoods rebuild and improve after disasters while lower-income areas do not return to pre-disaster conditions.

  PublisherDOI

• Large language model enabled knowledge discovery of building-level electrification using permit data

  Energy and Buildings · 2025-05-22

  articleSenior authorCorresponding
  PublisherDOI

• Detection of cardiovascular diseases in ECG images using deep learning

  AIP conference proceedings · 2025-01-01 · 2 citations

  articleSenior author
  PublisherDOI

• Integrating AI in Organizational Management: Implications for Communication Strategies and Social Dynamics

  Journal of Information Systems Engineering & Management · 2025-05-07

  articleOpen access1st authorCorresponding

  Communication strategies, decision making, and social dynamics have alike been changed by the integration of Artificial Intelligence (AI) to organizational management. The intent of this research is to examine how AI driven technologies, particularly machine learning, natural language processing (NLP), social network analysis (SNA), predictive analytics influences workplace efficiency and leadership effectiveness. The study analyzed AI’s role in optimization of customer relationship management (CRM), human resource management (HRM) and knowledge collaboration through the use of four AI algorithms, Random Forest, Long Short-Term Memory (LSTM), Graph Neural Networks (GNNs) and Reinforcement Learning (RL). Experimental results show that 60% reduction in communication errors, 35 percent increase in customer satisfaction and 50 percent improvement in employee performance are achieved by the use of AI based decision support systems. Also, Social network analysis powered by AI reduces the time for project completion by 30%, while Team collaboration is improved by 40% through AI powered social network analysis. But there are challenges in the adoption of the ethical AI like the job and mental health concerns caused by the AI, so that an ethical AI adoption strategy is required. The analysis is confirmed in terms of AI and its capability to increase organizational agility, leadership decision making and market competitiveness with existing literature. These findings imply that a beneficial balance of interaction between the AI and the human will be necessary for the sustainable use of AI. Future research should be directed towards hybrid AI frameworks that enable ethical governance to compensate for employee well being in corporate environments.

  PublisherOA PDFDOI

• Cascading marginal emissions signals for green charging with growing electric vehicle adoption

  Nature Communications · 2025-11-19 · 7 citations

  articleOpen accessSenior author

  Shifting electric vehicle charging to use cleaner electricity can reduce carbon dioxide emissions. Grid emissions factors can inform when to shift demand, but key assumptions behind existing emissions factor methods fail for today’s grids and electric vehicle adoption levels. We combine real charging data with a Western U.S. grid model to test these methods under increasing electric vehicle adoption. We find that following existing average and marginal emissions factor methods to manage charging can inadvertently increase grid emissions when emissions factor signals are noisy, too many electric vehicles follow the same signal, or when high-emitting generators respond. We instead propose an alternative Cascading marginal emissions factor strategy that manages charging in smaller groups. We show that the Cascading strategy reduces added emissions by 10–28% across grid scenarios for at least 2 million electric vehicles. Our research reveals how demand response methods must change to reduce emissions and support the grid transition under wider electric vehicle adoption. By combining real charging data with a Western U.S. grid model, this study finds that a cascading managed charging strategy reduces added emissions by 10–28% across grid scenarios for at least 2 million electric vehicles.

  PublisherOA PDFDOI

• Solar and batteries are affordable options for US households

  Nature Energy · 2025-08-01 · 1 citations

  articleSenior authorCorresponding
  PublisherDOI

• Charging electrified commercial vehicle fleets with reduced grid capacity using low-capital-cost depot management strategies

  Applied Energy · 2025-08-19 · 1 citations

  articleSenior author
  PublisherDOI

• Gradient Methods for Bilevel Electricity Grid Expansion Planning

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

Recent grants

• CAREER:Open-Source Data Analytics for Distribution Systems Management and Operations

  NSF · $500k · 2016–2022

• Collaborative Research: Snowflake: Lightweight and Adaptive Communications for Dense Sensor Networks

  NSF · $170k · 2012–2016

• CPS: Synergy: Collaborative Research: Matching Parking Supply to Travel Demand towards Sustainability: a Cyber Physical Social System for Sensing Driven Parking

  NSF · $260k · 2015–2018

• CIF: Small: Collaborative Research: Generative Adversarial Privacy: A Data-driven Approach to Guaranteeing Privacy and Utility

  NSF · $200k · 2018–2021

• CIF: Small: Collaborative Research: Distributed Detection Algorithms and Stochastic Modeling for Large Monitoring Sensor Networks

  NSF · $235k · 2011–2016

Frequent coauthors

• Yang Weng

  Arizona State University

  75 shared

• Yingchen Zhang

  Wuhan University

  37 shared

• Kevin Chen

  Johns Hopkins University

  36 shared

• Tom Key

  36 shared

• Comed Power Zhao

  National Renewable Energy Laboratory

  36 shared

• Iso Ne

  National Renewable Energy Laboratory

  36 shared

• Francis Therrien

  36 shared

• Vassilis Kekatos

  Purdue University West Lafayette

  36 shared

Labs

• Stanford Sustainable Systems LabPI

Awards & honors

• NSF CAREER Award
• Powell Foundation Fellowship
• Berkeley Regents Fellowship
• Makhoul Conjecture Challenge award