In the push toward a clean energy future, the need to deploy solar power faster and more accurately is no longer just a technical challenge. It is a global priority. As climate change accelerates and energy demands rise, every hour lost in project delays can mean less renewable power on the grid. Yet even today, a surprising bottleneck still slows progress: the time it takes to measure how much sunlight is lost due to shading.
At DNV, one of the world’s leading energy consulting firms, Radhika Lampuse is tackling this issue head-on. Her work is helping solar developers make quicker, better-informed decisions, and it is making a visible difference across the renewable energy sector.
“Solar energy assessments are often viewed as routine technical steps,” Radhika said. “But they carry major consequences. If those assessments are slow or inaccurate, projects get delayed. Investors hesitate. Communities wait longer for clean energy.”
Radhika works as a Solar Energy Analyst, applying her background in data science and energy science engineering to improve how solar energy systems are planned. After several years in the renewable energy industry, she joined her current firm with a clear goal: bring speed and accuracy to the parts of the solar process that often go overlooked.
Her most notable contribution so far is the development of a standardized approach to shading analysis. The problem it addressed was simple but widespread. In traditional solar assessments, calculating how much energy is lost due to shadows from trees, buildings, or equipment could take up to six hours per site. The process relied heavily on manual modeling and subjective estimates.
This slow pace created a ripple effect. Longer assessments meant longer delays before projects could be approved, funded, or built. And any mistakes in those calculations could lead to misjudged financial models, overbuilt systems, or missed performance targets.
Radhika helped design a solution that turned this multi-hour task into something that can be completed in under two hours. Using a mix of linear regression and classification algorithms, along with pattern recognition techniques, she and her team developed a rubric that predicts shading losses with consistent accuracy. The approach also uses clustering techniques to sort different types of shading situations, making it easier for analysts to apply the model across a wide range of project types.
The result is not just a faster process but a more reliable one. Using this model, we conduct Solar Energy Assessments with faster turnarounds, providing solar developers with clearer insights into potential energy losses. This reduces risk, accelerates financing timelines, and enables companies to deploy solar panels more quickly.
“By improving how we analyze shading, we’re conducting faster Solar Energy Assessments for developers and engineers,” Radhika said. “Every project that moves forward more quickly because of these internal tools brings us one step closer to a cleaner energy system.”
This work aligns with a wider global trend. The International Energy Agency expects global solar capacity to more than triple by 2040. But as more projects are planned and proposed, the bottlenecks in permitting, modeling, and engineering have grown more visible. In this context, even small time savings can translate into larger benefits. Faster shade loss estimates do not just help internal workflows. They help entire communities gain access to solar power sooner.
Radhika’s contributions also extend beyond technical systems. At her current firm, she serves as a board member on the Asian American and Pacific Islander Employee Resource Group, where she helps lead mentoring programs and promote inclusive hiring practices. “Diversity in our field is not just a value, it directly improves how we solve problems,” she said. “Different perspectives help us design better systems that work for more people.”
Her involvement in team-wide process improvements has also been widely recognized within her current firm. She has led documentation efforts to support knowledge sharing across engineering teams, helped create internal training tools for new analysts, and regularly serves as a quality reviewer for project deliverables. By building checks and support systems into the work, she is helping ensure that her current firm maintains its reputation for technical accuracy across hundreds of client engagements.
It is this blend of technical skill and public-oriented thinking that makes Radhika’s work stand out. While machine learning and automation are often discussed in abstract terms, her contributions show how these tools can solve very specific, very human problems, like waiting six months for a solar project to be approved because a shade model took too long.
“Every hour we save can mean days off a project timeline. And every day we save means more renewable energy gets to the grid faster,” she said.
As governments around the world set more ambitious clean energy goals, the need for well-designed solar assessments will only increase. Her projects are showing that small internal changes, standardizing a workflow, introducing better models, shortening review cycles, can ripple outward to influence solar adoption at scale.
Radhika’s work points toward a future where clean energy is not just possible, but practical. It is a reminder that progress often begins not with massive inventions, but with thoughtful decisions made behind the scenes, by people who care deeply about getting it right.
