An Integrated Platform for LEED Certification Automation Using Computer Vision and LLM-RAG

TL;DR

This paper introduces an automated platform that combines computer vision and large language models to streamline LEED certification, significantly reducing manual effort and improving efficiency in documentation and compliance processes.

Contribution

The paper presents a novel integrated platform that automates LEED certification tasks using computer vision, LLMs, and RAG techniques, enhancing scalability and accuracy.

Findings

Achieved 82% automation coverage in pilot deployments.

Reduced documentation time by up to 70%.

Improved efficiency over manual workflows.

Abstract

The Leadership in Energy and Environmental Design (LEED) certification process is characterized by labor-intensive requirements for data handling, simulation, and documentation. This paper presents an automated platform designed to streamline key aspects of LEED certification. The platform integrates a PySide6-based user interface, a review Manager for process orchestration, and multiple analysis engines for credit compliance, energy modeling via EnergyPlus, and location-based evaluation. Key components include an OpenCV-based preprocessing pipeline for document analysis and a report generation module powered by the Gemma3 large language model with a retrieval-augmented generation framework. Implementation techniques - including computer vision for document analysis, structured LLM prompt design, and RAG-based report generation - are detailed. Initial results from pilot project deployment show improvements in efficiency and accuracy compared to traditional manual workflows, achieving 82% automation coverage and up to 70% reduction in documentation time. The platform demonstrates practical scalability for green building certification automation.