Multi-Scale Remote Sensing Analysis for Oil Palm Plantation Mapping: Evaluating the Relative Importance of Spatial and Spectral Resolution
Muhammad Nizar Y.P. (a*), Yanuar A.N. (b) , Dika Dika A.J. (c)

a) Data Scientist, Professional Services, Esri Indonesia,
Jalan Gatot Subroto 6, Kota Jakarta Selatan 12710, Indonesia
*ypratama[at]esriindonesia.co.id
b) Product and Technology Lead, Solution Engineering, Esri Indonesia, Indonesia
c) Account Manager - Enterprise Sales, Esri Indonesia, Indonesia

Abstract

Accurate oil palm plantation mapping is essential for effective operational management, yet current capabilities remain insufficient. While industrial plantations follow regular patterns enabling straightforward detection, smallholder systems present significant challenges due to irregular shapes, fragmented distribution, mixed cropping systems, and rapid temporal changes, limiting comprehensive monitoring strategies. This study determines optimal remote sensing characteristics for comprehensive oil palm plantation mapping by systematically evaluating the relative importance of spatial and spectral resolution parameters in Southeast Asian tropical environments. We investigate which resolution type provides the most significant contribution to accurate detection of both industrial and smallholder plantation systems. We employ U-Net deep learning architecture to analyze multi-scale oil palm detection across diverse passive remote sensing platforms including drone RGB imagery, Planet/NICFI, Sentinel-2, and Landsat 8/9 datasets. The methodology systematically evaluates spatial resolution thresholds and spectral band combinations through comparative analysis of optical sensing approaches across multiple platforms. Results are expected to establish evidence-based guidelines for optimal pixel size thresholds and critical spectral bands for accurate oil palm mapping. The analysis will demonstrate differential sensitivity between plantation types to each resolution parameter, establishing practical recommendations for cost-effective passive remote sensing monitoring strategies.

Keywords: Oil Palm Mapping, Multi-Scale Analysis, Deep Learning, Spatial Resolution, Spectral Resolution

Topic: Topic B: Applications of Remote Sensing