Deep learning approach's effectiveness on sustainability improvement in the UK construction industry

Abstract

Purpose

The purpose of this paper is to investigate how a deep learning approach can impact the construction industry.

Design/methodology/approach

The objectives of this paper were to investigate: the awareness of people dealing with sustainability in their daily working environment; how much training and information construction industry workers have had in the topic of sustainability; and if a deep learning approach to sustainability teaching can make an impact on everyday practise in the industry. With these objectives, following a literature review, a questionnaire survey has been applied to 133 office and site‐based construction workers. In total, 50 office‐based workers and 50 site‐based workers participated.

Findings

The findings reveal that deep learning can be a possible opportunity and that the Government and the construction industry should explore it when training their staff. Although there are agencies which specifically deal with green issues, they are not widely embraced and workers currently just use them as a way to meet criteria and not to fully grasp the concept and incorporate it into their everyday practice. If deep learning can be embraced it can lead to a continuous improvement in green practice.

Originality/value

With the UK government recently setting new targets for sustainability, it is important that the construction industry takes actions to reduce its carbon footprint. The construction industry needs to improve its ability to train and teach its staff about the importance of green issues and environmentally‐friendly practices. This paper presents the results of research which may contribute to meeting the government targets and can be useful for practitioners and researchers.

Citation

Alkhaddar, R., Wooder, T., Sertyesilisik, B. and Tunstall, A. (2012), "Deep learning approach's effectiveness on sustainability improvement in the UK construction industry", Management of Environmental Quality, Vol. 23 No. 2, pp. 126-139. https://doi.org/10.1108/14777831211204886