The documentation of heritage buildings is the preliminary action to deal with any problem related to the built heritage. The procedure of documentation requires a very diverse range of data (quantitative and qualitative) to be obtained and investigated in order to produce an accurate digital representation of the building. This type of work of data capture and interpretation is often conducted in isolation by different stakeholders and for a range of purposes, leading to a lack of communication between different data types, repeated effort and incomplete documentation. Heritage Building Information Modelling (H-BIM) is set to play a key role in the digital documentation of heritage buildings, as it can combine quantitative and qualitative data and facilitate the integration of different stakeholders and specialised data into the digital management of the different phases of dealing with heritage buildings. This paper aims to review the multitude of data types that could be included in the documentation and investigation process of the built heritage, in order to assess the breadth and depth by which heritage buildings can be documented. Four main categories that span the whole documentation data areas are being suggested which vary from outer geometry surveys, to subsurface materials and structural integrity investigations, to data concerning the building performance, as well as the historic records concerning the building’s morphology over time, which can help to create a more in-depth knowledge about the heritage building’s status and performance and can create a solid base for any required restoration and retrofitting processes (Khalil and Stravoravdis 2019a).

Building occupancy profiles are critical in thermal and energy simulations. However, determining an accurate occupancy profile is difficult due to its stochastic nature. In most simulations, the occupant activities are usually represented by fixed yearly schedules, which are often derived from guides and other similar sources and may not represent the simulated building accurately. Therefore, an inaccuracy in defining occupancy profiles can be a source of error in building simulations. Over the past few years machine learning has become very popular due to its ability to reveal hidden patterns and relationships between data and this makes it suitable for investigating patterns in occupancy data. This study proposes a novel hybrid model combining the Graph Neural Network and the Long Short-term Memory neural network (LSTM) to predict the occupancy of individual rooms on a typical office floor. The proposed Graph LSTM model can produce high-resolution occupancy profiles of an office that are in good agreement with the reference occupancy profiles of the same office. The reference occupancy profiles for this office were derived from an agent-based model using AnyLogic and were not used in the training of the neural network. The proposed Graph LSTM model outperformed other neural networks tested such as the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU) and LSTM. When Graph LSTM is compared to the other neural networks tested, there is a range of improvement between 13.5 and 14.6% in the index of agreement, 38.3 and 46.8% in mean absolute error and 34.4 and 40.0% in root mean square error, when averaging the differences over the whole office.

The AEC industries as well as the heritage sector are facing a number of issues that relate to the management of building digital data. Two of the most prominent ones are the interoperability of data and data longevity. In order to better understand the extent of these issues for the general AEC industry and heritage buildings sectors, an online survey was designed to help quantify them and reveal the opinions of professionals and academics in the field. The online survey highlighted a clear latency in BIM adoption in the heritage sector as only 51% of the heritage participants use BIM in their projects compared to 63% of AEC participants. The reasons for this were further explored in the participants’ comments, as most of the reasons revolved around the issues of BIM data interoperability and longevity, considering the complex and interdisciplinary nature of heritage projects. The survey responses highlighted that data longevity is a crucial challenge for the heritage sector in particular as the need for future re-accessibility of digital data is clear in the results, showing that more than 82% of the heritage participants need to re-access their data in the future. The results also showed the prevalence of BIM interoperability issues and highlighted that the heritage sector is more prone to interoperability issues compared to the general AEC industry as 67% of heritage BIM participants and 50% of AEC BIM participant have faced some issues of BIM interoperability. In total, 72% of the standardised BIM participants agreed that standardised BIM formats could be a promising solution to mitigate the interoperability challenges, while only 57% thought that standardised BIM formats are reliable in their current status. Moreover, the online survey explored the variation in the needs of different disciplinary groups including rates of BIM adoption, use of standardised BIM formats, and needs for access to different heritage buildings data categories. Participants also presented their views on what would be an ideal medium for long-term storage of heritage buildings digital documentation data for future access, with some views being sceptical concerning BIM in its current status. This paper presents the findings of this extensive online survey.

Building Information Model for Existing Buildings for Facilities Management: RetroBIM Framework: 10.4018/IJ3DIM.2016010101: The use of Building information modelling for the design and construction phase of a building has been thoroughly looked into by researchers and practitioners