Mufida Fauziah Faiz, Achmad Fauzan

UNVEILING SPATIAL PATTERNS OF LAND CONVERSION THROUGH MACHINE LEARNING AND SPATIAL DISTRIBUTION ANALYSIS

Introduction

Unveiling spatial patterns of land conversion through machine learning and spatial distribution analysis. Analyze spatial land conversion patterns in Kayu Agung (2019-2023) using ML & spatial analysis. Identifies clustered changes, environmental risks, informing sustainable urban planning.

Abstract

Kayu Agung District in Ogan Komering Ilir (OKI) Regency, South Sumatra, has undergone rapid population growth, resulting in notable land-use transformations. This study examines land-use change dynamics from 2019 to 2023 and identifies their spatial distribution using satellite imagery. Satellite imagery classification was performed using three machine learning algorithms—K-Nearest Neighbors (KNN), Naïve Bayes, and Logistic Regression—with KNN achieving the highest accuracy. Spatial analysis employing the Variance-to-Mean Ratio (VMR) revealed that land-use changes are spatially clustered, indicating concentrated land conversion in specific areas. These findings emphasize potential environmental risks, including declining green open spaces and increasing urban pressure. The study contributes by integrating machine learning and spatial statistical analysis (VMR) as a comprehensive framework for understanding land-use conversion, providing scientific insights to support adaptive spatial planning and the achievement of Sustainable Development Goal (SDG) 11: Sustainable Cities and Communities.

Full Text

Comments

You need to be logged in to post a comment.