EcoSphere: A Decision-Support Tool for Automated Carbon Emission and Cost Optimization in Sustainable Urban Development
Siavash Ghorbany, Ming Hu, Siyuan Yao, Matthew Sisk, Chaoli Wang

TL;DR
EcoSphere is a software tool that integrates high-resolution urban data and AI techniques to help policymakers optimize carbon emissions and costs in city development, promoting sustainable urban growth.
Contribution
The paper introduces EcoSphere, a novel decision-support platform combining data-driven modeling and AI to evaluate and optimize urban carbon emissions and costs.
Findings
EcoSphere accurately categorizes building characteristics using computer vision and NLP.
The tool effectively simulates policy scenarios to predict environmental and financial impacts.
Case studies demonstrate EcoSphere's utility in guiding sustainable urban development.
Abstract
The construction industry is a major contributor to global greenhouse gas emissions, with embodied carbon being a key component. This study develops EcoSphere, an innovative software designed to evaluate and balance embodied and operational carbon emissions with construction and environmental costs in urban planning. Using high-resolution data from the National Structure Inventory, combined with computer vision and natural language processing applied to Google Street View and satellite imagery, EcoSphere categorizes buildings by structural and material characteristics with a bottom-up approach, creating a baseline emissions dataset. By simulating policy scenarios and mitigation strategies, EcoSphere provides policymakers and non-experts with actionable insights for sustainable development in cities and provide them with a vision of the environmental and financial results of their…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
