Using genetic algorithm to optimize land use development plan in Hong Kong

Optimization of land use development plan is important particularly in condition of heavy concentration of urban population such as in Hong Kong. With the growth of population in Hong Kong, there is a need to develop some new residential areas continuously and to decentralize population in the outlying areas such as the satellite towns and/or new towns. The land use planning consists of identifying and selecting potential development areas to meet the expected land requirements. The optimal land use development problem relates to the allocation of population with optimal objective function value. In this case the land production cost includes formation of new areas, construction of public works infrastructure, and provision of other utility services. The optimal land use development plan is chosen from a large number of potential development areas and potential population allocation. This problem can be formulated as a 0-1 programming problem mathematically. In this paper, the genetic algorithm is used to solve the 0-1 programming problem in which some new land use plans are identified in Hong Kong so as to minimise the total development and transportation cost. It is the first work to apply genetic algorithm for land use problem in practice. The developed model will advance this subject and help the authorities decide which new residential areas should be considered for detailed investigation. The Hong Kong 2006 planning data is used for case study.