Faster, Smarter Climate Mitigation Using Python 🌳
summary
Claims that a six‑person team wrote a Python data pipeline and a Django app called BlocMaps app that models 125 million buildings nationwide, uses a retuned Oak Ridge National Lab energy model, a vectorized similarity matcher for messy records, and a knapsack optimization to design cost‑efficient retrofit incentive programs. The system produces budget, emissions reduction, beneficiary breakdowns and helped unlock hundreds of millions in public incentives; Terraform scripts for the scalable pipeline are slated for open source.
AI-written summary · about
chapters (10)
- 0:00Introduction to climate mitigation
- 1:10Climate sectors and investor decisions
- 7:31Python for data-driven investment
- 8:33Block Power’s Block Maps demo
- 11:46Knapsack problem in incentive design
- 15:22Energy use intensity modeling
- 17:32Scaling Python solutions nationwide
- 19:45Building tools for investor decisions
- 20:46Opportunities across sectors
- 21:28Q&A and closing remarks
related talks
28mPython for Planet Earth: Climate Modeling and Sustainability.. with Drishti Jain
43mPython at City Scale
49mMeteorology, Climate and Python: desperately trying to forget technical details
28mPython: The Architect's Secret Weapon
28mReduce the environmental footprint of your Python programs
31m"How we used Python to try and save lives"
42mInside Out - Creating a Python Ecosystem for Analysis and Better Government
30mEmpowered by Python - A success story