Issue |
E3S Web Conf.
Volume 608, 2025
EU-CONEXUS EENVIRO Research Conference - The 9th Conference of the Sustainable Solutions for Energy and Environment (EENVIRO 2024)
|
|
---|---|---|
Article Number | 05001 | |
Number of page(s) | 10 | |
Section | Sustainable Development | |
DOI | https://doi.org/10.1051/e3sconf/202560805001 | |
Published online | 22 January 2025 |
Digital twins for green roofs and facade inspection using drones and multi-modal foundation models
AI for Sustainable Construction, University of Rostock, Justus-von-Liebig-Weg 2, 18059 Rostock, Germany
* Corresponding author: nils.krause@uni-rostock.de
Green roofs and facades are a nature-based way to improve the climate of buildings. However, they also add additional maintenance effort for keeping the plants healthy. We propose a novel automated digital twin approach to monitor the health of the plants using a combination of drones with Foundation Models to monitor and analyze the health of the plants. The process consists of three main components, a drone system for recording real-time data in an automated manner for different heights, a digital twin for storing and controlling the data, and a Multi-modal Foundation model (MMFM) for diagnosis of health issues and generating recommendations for solving the issues. This allows us to automatically identify and mitigate health issues of the plants and improve the maintenance of the miniature ecosystems of green roofs and facades to address climate change risk and the shortage of skilled workers.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.