作者: Kazuaki Miyamoto , Nao Sugiki , Noriko Otani , Varameth Vichiensan
DOI: 10.1007/978-3-642-37533-0_6
关键词: Function (engineering) 、 Computer science 、 Iterative proportional fitting 、 Microsimulation 、 Microsimulation model 、 Machine learning 、 Base (topology) 、 Population synthesis 、 Urban planning 、 Land use 、 Artificial intelligence
摘要: Land-use microsimulation is becoming an indispensable function in a planning support system for sustainable urban development because it provides the detailed information necessary decision making on emerging issues at household or firm level. In land-use microsimulations, there are two approaches estimating base-year micro-data: cell-based population synthesis, which generally uses iterative proportional fitting method, and agent-based methods. This chapter compares these methods qualitatively quantitatively. The qualitative comparison shows that neither one superior every aspect. method preferred when deals with data sufficiently simple, while accurate and/or numerous micro-data attributes demanded. Similarly, quantitative based goodness-of-fit evaluation does not show single all applications. These findings suggest way selecting better conditions of model purpose its application.