Building and Construction Authority

Three-dimensional (3D) geological model, as an effective tool for modelling the complex nature of underground geological conditions, has been used for the design and construction of underground facilities. The accuracy and reliability of the geological information reflected by the 3D model are critical for engineering practitioners to make sound judgement. It is important to consistently update the 3D geological model with new borehole or geophysical data for better assessment of the underground uncertainties. In this study, an application of the NTU-BCA 3D geological model to an undergoing subway project in Singapore has been investigated. The established 3D geological model was updated using the new borehole data obtained in the project. A comparison of the virtual boreholes generated in the 3D model with the real borehole data in terms of rockhead positions was made as a verification of the uncertainties of the model. The uncertainties analyses show that the standard deviations of the predicted errors for the rockhead are improved after the new borehole data was incorporated into the model. Predictions made by spatial statistical analyses are also presented and compared with the borehole data and the results from the 3D geological modeling. Through the study, an example for using newly obtained borehole data to update the existed 3D geological model to improve the accuracy was given.

The need for underground development has been expanded due to rapid urbanization and to reduce the negative impact on city living. In recent years, 3D geological modelling has been widely used by engineers and geo-scientists for desk study and has shown its capability of integrating geological and geotechnical information for better usage in building and civil engineering projects. To provide techniques and instruction(?), a 3D Geo-data Modelling and Management System (GeM2S) has been established to better understand the subsurface conditions in Singapore. However, the geological stratum between the existing boreholes is often not investigated, which brings the possibility of vital errors in underground design due to inaccurate interpretation of the ground conditions. It is desirable to utilize advanced machine learning methods to predict and update the 3D geo-models. Machine learning is regarded as a subset in the field of artificial intelligence, which has shown its rapid development recently. However, the accuracy of the model is one of the major concerns when the techniques are applied. In this study, four machine learning models are proposed to provide the solutions for stratigraphic classification, namely, Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (Catboost). The borehole data are located in the Bishan planning region in Singapore. The voxel-based input data for the models are spatial coordinates (X, Y, Z) and ground surface elevation. The prediction results demonstrate that LightGBM with optimization have produced the highest performance in this multi-classification problems. Finally, based on the prediction results of LightGBM, the voxel-based 3D geological models and the selected cross-sections are built for further analysis and comparison.

Building Information Modeling (BIM) and sustainable buildings are two future cornerstones of the Architectural, Engineering and Construction (AEC) industry. In Singapore’s context, the Green Mark (GM) scoring system is prevalently used to assess the sustainability index of green buildings. BIM provides the semantic and geometry information of buildings, which is proliferated as the technological and process backbone for the green building assessment. This research, through vast literature reviews, identified that the current procedure of achieving a Green Mark score is tedious and cumbersome, which hampers productivity, especially in the calculation of building envelope thermal performance. Furthermore, the project stakeholders work in silos, in a non-collaborative, manual and 2D-based environment for generating relevant documentation to achieve the requisite green mark score. To this end, a cloud-based BIM platform was developed, with the aim of encouraging project stakeholders to collaboratively generate the project’s green mark score digitally in accordance with the regulatory requirements. Through this research, the authors have validated the Envelope Thermal Transfer Value (ETTV) calculation, which is one of the prerequisite criteria to achieve a Green Mark score, through a case study using the developed cloud-based BIM platform. The results indicated that using the proposed platform enhances the productivity and accuracy as far as ETTV calculation is concerned. This study provides a basis for future research in implementing the proposed platform for other criteria under the Green Mark Scheme.

Shallow slope failures due to rainfall commonly occur in residual soil, especially in tropical areas like Singapore. Therefore, it is critical to understand the distribution of residual soil properties throughout Singapore Island. Proper procedures are required for selection of appropriate locations of soil sampling to obtain the representative soil properties. The aim of this study is to establish the necessary procedures and methods which are applicable to select suitable locations for soil sampling in Singapore. In this study, the Geographical Information System (GIS) with the incorporation of three layers: digital elevation model (DEM), slope angle, and the soil sampling locations from past studies were used to generate suitability map for determination of soil sampling locations in Singapore. Five suitability classes were implemented in each layer: very low, low, medium, high, and very high. Four types of spatial analyses such as "Analysis by weights", "Inference matrix method", "Fuzzy Overlay Gamma method", and "per-cell statistic maximum method (PCSM)" were assessed to identify the appropriate method for determination of the suitable locations for soil sampling in Singapore. These analyses were carried out using Spatial Analyst Tools in ArcGIS environment. The results of this study indicated that the spatial analysis by weights and Fuzzy Overlay Gamma are suitable for determination of soil sampling locations up to 100 data points. The spatial analysis using the inference matrix is suitable for determination of limited number of soil sampling locations. The spatial analysis using the PCSM method is suitable for determination of large number of soil sampling locations. The findings from this study will benefit the practical engineers in surveying as well as other related researchers for determination of suitable locations of soil sampling.

This paper studies the performance of a commercial solar water heating system (SWH) in Singapore. The objective is to perform a comprehensive audit of the selected SWH in order to understand the efficiency of various subsystems, identify the rationales behind the energy inefficiency within the SWH, and then develop control strategies to improve the energy efficiency of the SWH. To do so, first, we deploy a monitoring system using Internet of Things (IoT) to collect a large volume data of water flow, operational schedule, availability of solar, and electricity consumption. Second, we identify the efficiency of various sub-systems and determine the system performance. Finally, we develop the corresponding control strategies for various sub-systems to improve the efficiency of the overall system and to reduce the operational cost of the SWH. The effectiveness of the proposed control strategies is confirmed through experiments at the actual site of the considered SWH.