PulseAugur
LIVE 23:11:50
research · [2 sources] ·
0
research

AI model predicts building energy performance using multimodal data

Researchers have developed a gated multimodal model to predict energy performance scores for residential buildings, integrating tabular data, free text descriptions, and GIS spatial features. This approach aims to provide scalable assessments for decarbonizing buildings, which contribute significantly to UK and EU emissions. The model achieved strong predictive accuracy in a London case study and demonstrated that combining multiple data types enhances performance over single-modality approaches. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Provides a scalable framework for property-level energy efficiency assessment and retrofit planning, supporting net-zero housing transitions.

RANK_REASON The cluster contains an academic paper detailing a new multimodal learning model for property energy performance prediction.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Yunfei Bai, Aaron Tesfa Tsion, Raul Rosales, Barbara Shollock, Wei He ·

    Gated Multimodal Learning for Interpretable Property Energy Performance Prediction and Retrofit Scenario Analysis

    arXiv:2605.05088v1 Announce Type: new Abstract: Achieving resilient and sustainable cities requires scalable approaches to decarbonising residential buildings, which account for about 20% of UK greenhouse gas emissions and 25% of energy-related emissions in the European Union. En…

  2. arXiv cs.LG TIER_1 · Wei He ·

    Gated Multimodal Learning for Interpretable Property Energy Performance Prediction and Retrofit Scenario Analysis

    Achieving resilient and sustainable cities requires scalable approaches to decarbonising residential buildings, which account for about 20% of UK greenhouse gas emissions and 25% of energy-related emissions in the European Union. Energy Performance Certificates (EPCs) support reg…