1 of 1

Project Challenge

​

Poorly maintained building envelopes increase building greenhouse gas emissions and cause quality of life problems. We propose a non-invasive integrated solution to locate moisture intrusion, thermal bridges, and air leaks. This solution will diagnose building envelope issues. The system identifies and quantifies common envelope defects. It applies long-wave radar and deep learning to detect hidden deep moisture penetration and other major envelope defects. With this system, it is possible to perform low-cost, targeted micro-retrofits to address envelope issues.

Full Building Scans for Targeted Micro-retrofits using Drones, Radars, and Deep Learning

Brooklyn, New York

​

NSF Award ID: 2228568

PI: Chen Feng, NYU Tandon

2022 Civic Innovation Challenge

Pilot Vision

​

• Finalize Technology Development and Transfer
• Scan and Analyze the Selected Buildings
• Micro-retrofit on the Detected Energy Defects
• Technical Comparisons and Social Evaluations (e.g., barriers to adoption)
• Building Inspection Workforce Training

Civic Partners:

• Building Diagnostic Robotics
• Archdiocese of New York
• RETI Center
• New York City Office of Technology and Innovation
• NYC 2030 District
• New York City Department of Citywide Administrative Services
• NARA

Research Partners:

• AI4CE Lab
• Diana Hernandez

Research Questions

​

• How effective is AI at finding building envelope issues using thermal and RGB imagery?
• Can self-supervised learning be used to isolate for moisture anomalies?
• How effective is AI at finding moisture in real world roof assemblies?
• How much can micro-retrofits improve occupant quality of life?