Land Allocation based on Physiological Needs and Land Suitability by Using the Combination of Ecological Footprint and SVM
Sitarani Safitri, Irawan Sumarto, Akhmad Riqqi, Albertus Deliar, Ketut Wikantika

Remote Sensing and Geographic Information Science Research Group, Department of Geodesy and Geomatics, Faculty of Earth Science and Technology, Bandung Institute of Technology, Bandung 40132, Indonesia

Abstract

Land can produce products in the form of goods and services (supply) to meet human needs (demand). Meeting human needs through development activities requires the allocation of land cover/land use. Land cover/land use should be allocated with regard to the land capability itself. The ability of land to meet human needs, particularly physiological needs as as basic survival needs. Based on existing developments, ecological footprint (EF) becomes a simple but comprehensive land allocation calculation method. The calculation of land allocation certainly needs to pay attention to its land suitability. The concept of land suitability aims for optimal and sustainable land use. This can be achieved by providing information on the relationship between land characteristics. Land suitability in this model is assessed using elevation, slope, water availability, type of ecoregion, rainfall, and temperature. In this study, land suitability model was conducted using Support Vector Machine (SVM) with the kernel trick. SVM is used to find the best hyperplane by maximizing the distance between classes. Hyperplane is a function that can be used to separate between classes. Overall Accuracy of land suitability modeling results, namely 87,728%. The kappa coefficient value is 0.812 with a significance value of 0.00. The results of land allocation modeling with EF show that agricultural, plantation, and pastures are in deficit. The EF-based allocation was then compared with the land suitability. The final results show that agricultural land, plantations and pastures are still experiencing deficits, but there are some reduction. The amount of deficit reduction for agricultural land reached 651,634.4202 ha, plantations 19,914.95913 ha, and pastures 1,695.578149 ha. The research results are expected to provide an overview for policy making related to land use planning.

Keywords: land allocation- ecological footprint- SVM- land suitability-

Topic: Environmental Science, Technology, and Education