Open AccessDriving-factors identification of land-cover change in west java using binary logistic regression based on geospatial data
Author(s) -
Udjianna S. Pasaribu,
Riantini Virtriana,
Albertus Deliar,
Irawan Sumarto
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/500/1/012003
Subject(s) - logistic regression , land cover , geography , population , java , land use , regression analysis , geospatial analysis , physical geography , statistics , environmental resource management , environmental science , mathematics , computer science , cartography , demography , engineering , civil engineering , sociology , programming language
The Land is a fundamental factor in production activity. Accordingly, it is closely related to economic growth—which supports the living needs of human beings. In many cases, human activities related to land use are often uncontrollable, impacting many negative effects on the environment, both locally and globally. More broadly, these activities will lead to some changes in land cover and some other physical features such as climate. In order to understand the phenomenon of land cover changes, we approach them through modelling. To detect any changes in land cover in a region, it is necessary to identify the driving factors causing land-cover change. The relation between driving factors and response variables can be evaluated by using regression analysis techniques. In this case, land cover change is a dichotomous phenomenon, i.e., binary. Binary Logistic Regression (BLR) model is one of the regression analyses which can be used to describe the nature of dichotomy. From the results of this study, the driving factors causing land-cover change in West Java were found, those are: the distances to the central business districts in some certain areas such as Bandung City, Bekasi Regency, Bekasi City, Bogor Regency, Karawang Regency, and Sukabumi Regency; the distance to the the capital of the province; the distance to the main roads; the population numbers; and some physical features of the land such as slope, curvature, and height. This predictive model had an accuracy level of 49,79%, which equals to 1.827.217,44 ha area.