A comparative study of land price estimation and mapping using regression kriging and machine learning algorithms across Fukushima prefecture, Japan

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.