Search

The growth of densely populated urban areas has caused traditional cadastral registration systems to face many difficulties in representing complex and multilevel property situations on 2D maps. These challenges, combined with the rapid development of 3D technologies, have forced the research and progress of 3D cadastre systems. The aim of this study is to investigate how a Building Information Model (BIM) can be used as a data source for the Land Administration Domain Model (LADM) based 3D cadastre system, and how that process can be improved. The Industry Foundation Classes (IFC) format and the LADM-based model were selected because both are international open standards that have a significant impact in their own domain. The data sample for the 3D cadastre system was extracted from a BIM model. The paper proposes an IFC format extension which makes it possible to define 3D geometry according to the LADM standard. In order to demonstrate this extension, the West 65 residential and business complex, Belgrade, was selected as a case study. The IFC format extension presented here is a step towards data harmonization between BIM in the IFC format and 3D cadastre systems; it should provide more suitable data in the current IFC schema and enable easy data flow between BIM projects and 3D cadastral data.

3D cadastral systems are more complex than traditional cadastral systems and they require more complex technical solutions and innovative use of developing technologies. Regarding data integrity and data consistency, 3D cadastral data should be maintained by a Database Management System (DBMS). Furthermore, there are still challenges regarding visualization of 3D cadastral data. A prototype of the 3D cadastral system based on a NoSQL database and a JavaScript application for 3D visualization is designed and tested in order to investigate the possibilities of using new technical solutions. It is assumed that this approach, with further development, could be a good basis for the development of a modern 3D cadastral system. MongoDB database is used for storing data and Cesium JavaScript library is used for 3D visualization. The system uses an LADM (Land Administration Domain Model) based data model. Additionally, script languages, libraries, application programming interfaces (APIs), software and data formats are used for the system development. The case study is based on the real cadastral data. The underground object and building units located below and above the ground level are used to test the proposed data model and the system’s functionality. The proposed system needs further development in order to provide full support to a modern 3D cadastral system. However, it allows maintenance of 3D cadastral data and basic 3D visualization with the interactive approach.

The goal of this study is to analyse the predictive performance of the random forest machine learning technique in comparison to commonly used hedonic models based on multiple regression for the prediction of apartment prices. A data set that includes 7407 records of apartment transactions referring to real estate sales from 2008–2013 in the city of Ljubljana, the capital of Slovenia, was used in order to test and compare the predictive performances of both models. Apparent challenges faced during modelling included (1) the non-linear nature of the prediction assignment task; (2) input data being based on transactions occurring over a period of great price changes in Ljubljana whereby a 28% decline was noted in six consecutive testing years; and (3) the complex urban form of the case study area. Available explanatory variables, organised as a Geographic Information Systems (GIS) ready dataset, including the structural and age characteristics of the apartments as well as environmental and neighbourhood information were considered in the modelling procedure. All performance measures (R2 values, sales ratios, mean average percentage error (MAPE), coefficient of dispersion (COD)) revealed significantly better results for predictions obtained by the random forest method, which confirms the prospective of this machine learning technique on apartment price prediction.

The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.