최근 머신러닝은 빅데이터에 대한 분석방법으로서 학습을 통한 지능화된 문제해결 방안으로서 관심이 증가하고 있다. 본 논문은 LBSN 데이터와 머신러닝 방식을 이용하여 토지이용현황을 파악하는 분석을 시도하였다. 도시계획에 있어서 토지이용현황의 파악은 직접적인 현장 조사에 의존해 왔다. 최근 스마트폰 사용자가 증가하면서 등장하고 있는 위치기반 소셜미디어의 자료들 은 토지이용의 상황을 반영하는 빅데이터로서, 머신러닝 방법론은 이들에 대한 자동화된 분석을 할 수 있게 한다. 본 연구에서는 LBSN 자료와 머신러닝 기법을 이용하여 토지이용을 예측하는 모델을 개발하여 실제 토지이용현황 자료와의 비교분석을 수행하였다. 이러한 분석을 통해 LBSN자료를 이용한 토지이용현황의 자동화된 분석 방안에 대해 연구하였다.

In this study, the land use is analyzed by using the SWMM-LID (Low Impact Development) program to minimize the environmental damage caused by the development. In order to effectively utilize pre - development hydrological conditions, we analyzed the land use of existing industrial complex. The study areas selected were a completed industrial complex and an ongoing industrial complex in order to effectively identify the characteristics of the industrial complex and the water circulation system. Numerical simulation used SWMM-LID to enable quantitative hydrological impact assessment of penetration, storage facilities and LID planning elements. In the case of natural conditions, the infiltration amount was 16.3% and 1.5% of the total rainfall at B, C point, respectively. However, after applying the existing land use plan, the infiltration amount at point B was 12.1% and at point C was 3.9 %. In the case of point B, the amount of infiltration decreased due to the development of greenery as an impervious site. On the other hand, the amount of infiltration at point C increased as the existing industrial complex was replaced by greenery. Therefore, high infiltration amount can be secured when land use plan is redeveloped in green areas or parks in areas where the permeability coefficient is high according to the ground conditions in the complex. Two types of bio-polymer soil were developed to increase the LID effect and were tested to compare typical soil with these bio-polymer soils.

This study is to establish a planning methodology for rural area development with land suitability classification. Land suitability classification was carried out by introducing Geographic Information System. The planning methodology was applied to Sunheung district located in Youngpoong county, Kyongbuk Province, Korea. Land suitability classification by the GIS showed that only 29 % of present agricultural land were higher than class 2 and 71 % were in bad condition for agricultural land. Especially, 22.2 % of agricultural land were under class 5 as the lowest level and 265.2 ha of forest were possible to develop as an agricultural land. It was proved that GIS may be a powerful tool in rural planning process. In addition, it is thought that GIS can be applied to the fields of agricultural land management system in many ways.

For formulation of the rational land us2 plan in regional base, it is a basic and prior condition to categorize total planning area into some functional subregions by purposely-selected indicators. As one of quantitive approaches to the areal categorization in rural area, Principal Component Analysis(PCA) was introduced and testified its applicability through a case study on Sunheungdistrict(called as myun in Korea) area, Youngpoong-county, Kyungbuk-province, Korea. Areal analysis by PCA was carried out on rurality and urbanity of parish-level area(ri in Korea) respectively. By use of PCA analysis results, classifying matrix was made through categorization of both index scores. Among 18 ri's of the case study area, 12 was classified as rural-dominated areas, 2 as urban- dominated areas, and reamaining 3 as intermediate areas.