Multimodal Modular Chain of Thoughts in Energy Performance Certificate Assessment

TL;DR

This paper introduces a multimodal modular reasoning framework using Vision-Language models to improve automated energy performance assessments of buildings with limited visual data, demonstrating significant accuracy gains.

Contribution

It proposes the MMCoT architecture that decomposes EPC estimation into reasoning stages with structured prompts, advancing low-cost, data-efficient building energy evaluation methods.

Findings

MMCoT outperforms instruction-only prompting in EPC estimation

Captures the ordinal structure of EPC ratings effectively

Most errors occur between adjacent EPC classes

Abstract

Accurate evaluation of building energy performance remains challenging in regions where scalable Energy Performance Certificate (EPC) assessments are unavailable. This paper presents a cost-efficient framework that leverages Vision-Language models for automated EPC pre-assessment from limited visual information. The proposed Multimodal Modular Chain of Thoughts (MMCoT) architecture decomposes EPC estimation into intermediate reasoning stages and explicitly propagates inferred attributes across tasks using structured prompting. Experiments on a multimodal dataset of 81 residential properties in the United Kingdom show that MMCoT achieves statistically significant improvements over instruction-only prompting for EPC estimation. Analysis based on accuracy, recall, mean absolute error, and confusion matrices indicate that the proposed approach captures the ordinal structure of EPC ratings, with most errors occurring between adjacent classes. These results suggest that modular prompt-based reasoning offers a promising direction for low-cost EPC pre-assessment in data-scarce settings.