HomeAboutProjectsExperienceResumeContact

Project Overview

Carbon Twin

A digital twin exploration for sustainable infrastructure, connecting forecasting, simulation, and carbon awareness into one decision surface.

September 2024 - December 2024
01Why It Matters

Problem

Carbon and energy decisions are often split across separate tools: monitoring in one place, forecasting in another, and sustainability reporting somewhere else.

That separation makes it hard to understand tradeoffs. A user may know how much energy was produced, but not how a different behavior, schedule, or infrastructure decision could affect carbon impact.

  • Energy, forecasting, and carbon-awareness data need a shared context to become decision support.
  • Sustainability interfaces can become abstract if they only show totals without explaining operational causes.
  • The concept needed to connect simulation and monitoring without pretending to be a finished production platform.
02What I Did

Decision

I framed Carbon Twin as a digital twin concept for sustainable infrastructure, where monitoring, forecasting, simulation, and carbon visualization could live in one decision surface.

The work focused on product architecture and interface framing: what the platform should model, what it should predict, and how it should communicate uncertainty to a non-specialist user.

  • Designed the concept around household or facility energy systems that can be monitored and simulated over time.
  • Explored how AI forecasting models could feed dashboard states, scenario comparisons, and carbon-impact views.
  • Kept the concept modular so future work could separate data ingestion, forecasting, simulation, and presentation layers.
03What I Learned

Learning & Impact

Carbon Twin connected my renewable-energy interests with product design, forecasting systems, and responsible AI.

It gave me a clearer way to think about digital twins as more than visualization: they can become a practical layer for testing decisions before real-world changes are made.

  • Developed a stronger understanding of digital twin product architecture.
  • Connected carbon awareness with forecasting and infrastructure monitoring.
  • Helped define a longer-term direction around AI-powered sustainability systems.

Takeaway

The main challenge was product framing. I had to decide which signals should guide action, which details should stay behind the scenes, and how to avoid turning sustainability analytics into decorative data.

Stack & Links

Next.jsTypeScriptPythonAI Forecasting
Back To Projects