• Journal of Geographical Sciences
  • Vol. 30, Issue 5, 05000794 (2020)
DERDOURI Ahmed1、* and MURAYAMA Yuji2
Author Affiliations
  • 1Division of Spatial Information Science, Graduate School of Life and Environmental Sciences, Uni-versity of Tsukuba, Tennodai, Tsukuba, Ibaraki, Japan
  • 2Faculty of Life and Environmental Sciences, University of Tsukuba, Tennodai, Tsukuba, Ibaraki, Japan
  • show less

    Abstract

    Finding accurate methods for estimating and mapping land prices at the macro-scale based on publicly accessible and low-cost spatial data is an essential step in producing a meaningful reference for regional planners. This asset would assist them in making economically justified decisions in favor of key investors for development projects and post-disaster recovery efforts. Since 2005, the Ministry of Land, Infrastructure, and Transport of Japan has made land price data open to the public in the form of observations at dispersed locations. Although this data is useful, it does not provide complete information at every site for all market participants. Therefore, estimating and mapping land prices based on sound statistical theories is required. This paper presents a comparative study of spatial prediction of land prices in 2015 in Fukushima prefecture based on geostatistical methods and machine learning algorithms. Land use, elevation, and socioeconomic factors, including population density and distance to railway stations, were used for modeling. Results show the superiority of the random forest algorithm. Overall, land prices are distributed unevenly across the prefecture with the most expensive land located in the western region characterized by flat topography and the availability of well-connected and highly dense economic hotspots.

    1 Introduction

    Maps depicting the spatial distribution of land prices are an essential reference in urban and regional planning during post-disaster recovery periods and beyond. Such maps are employed as one of the strategic assets for various purposes, such as optimally allocating land resources (Hu et al., 2016), developing special land policies for potential investors, and making economically justified planning decisions either by planning authorities or ordinary citizens (Cellmer et al., 2014). It is always critical for key investors and planners to investigate the economic value of land before starting any prospective project at the local and regional levels. However, it is more challenging to examine the variation in land prices in a wide area. This is due to the incredible budget- and time-consuming process behind extracting land price maps covering a whole region, which necessitates costly and lengthy field surveys. Furthermore, the available samples do not usually cover the entire study area in question as the data is collected from dispersed locations. For this reason, a specific spatial analysis is required to estimate land values at any given site.

    Copy Citation Text
    Ahmed DERDOURI, Yuji MURAYAMA. A comparative study of land price estimation and mapping using regression kriging and machine learning algorithms across Fukushima prefecture, Japan[J]. Journal of Geographical Sciences, 2020, 30(5): 794
    Download Citation
    Category: Research Articles
    Received: Feb. 19, 2019
    Accepted: Sep. 9, 2019
    Published Online: Sep. 30, 2020
    The Author Email: