Evaluation of SAR and Optical Image Fusion Methods in Oil Palm Crop Cover Classification Using the Random Forest Algorithm

Abstract

This paper presents an evaluation of land cover accuracy, particularly regarding oil palm crop cover, using optical/synthetic aperture radar (SAR) image fusion methods through the implementation of the random forest (RF) algorithm on cloud computing platforms using Sentinel-1 SAR and Sentinel-2 optical images. Among the fusion methods evaluated were Brovey (BR), high-frequency modulation (HFM), Gram–Schmidt (GS), and principal components (PC). This work was developed using a cloud computing environment employing R and Python for statistical analysis. It was found that an optical/SAR image stack resulted in the best overall accuracy with 82.14%, which was 11.66% higher than that of the SAR image, and 7.85% higher than that of the optical image. The high-frequency modulation (HFM) and Brovey (BR) image fusion methods showed overall accuracies higher than the Sentinel-2 optical image classification by 3.8% and 3.09%, respectively. This demonstrates the potential of integrating optical imagery with Sentinel SAR imagery to increase land cover classification accuracy. On the other hand, the SAR images obtained very high accuracy results in classifying oil palm crops and forests, reaching 94.29% and 90%, respectively. This demonstrates the ability of synthetic aperture radar (SAR) to provide more information when fused with an optical image to improve land cover classification.

Improving Land Use/Cover Classification Accuracy from Random Forest Feature Importance Selection Based on Synergistic Use of Sentinel Data and Digital Elevation Model in Agriculturally Dominated Landscape

“…The topography of the area is heterogeneous, and some of the classes are located in the floodplain, which is typically undulating compared to developed and agricultural areas. Several studies have shown the importance of elevation data to increase the accuracy of the classified map [11,26,40,58]. In the same vein, radar backscatter was found to improve model performance because it can normalize or reduce the effects of the atmosphere, topography, instrument noise, etc., to provide consistent spatial and temporal comparisons [59].…”

“…Still, it has not been adequately evaluated by the remote sensing community as compared to more traditional pattern recognition algorithms. In addition, there have been observations about how the importance of variables varies depending on the data and ecosystem in question, necessitating further exploration [23,25,26]. To assist decision-makers in a variety of spatial planning applications (e.g., cropland management, irrigated agriculture intensification, flood vulnerability assessment, water management, or human settlement/resettlement planning in floodplains), the thematic LULC classes were created to represent the local characteristics of the semi-arid region, in Nigeria.…”

Performance Evaluation of DL-based Models for LULC segmentation using SAR time series data of regions in Gujarat

“…Remote sensing is a science that investigates a variety of natural phenomena that occur on the surface of the Earth using sophisticated techniques to gather data from sensors mounted on various aerial platforms, from enormous satellites orbiting thousands of kilometers above the surface of the Earth to unmanned aerial vehicles (UAV) operating only a few meters above it. The electronic and technological advancements of both these platforms and their onboard sensors, as well as the numerous applications where remote sensing provides valuable information for decision-making, particularly in the determination of more precise land cover classifications, have seen significant advancements in recent years [24,25] Satellite images can now be obtained from a variety of platforms located across the globe [25]. The development of indicators to track and comprehend anthropogenic and natural processes necessitated using high-resolution and frequently updated land cover maps [26].…”

“…Electronic advancements in sensors and satellite platforms allow satellite spatial and temporal resolutions to continue to rise, reducing the time window for capturing information about a specific point on the Earth's surface and allowing for more continuous monitoring and analysis of the dynamics of various territories around the world. This temporal window is critical for agricultural area classification research, particularly for seasonal crops [25,27] Across the past 20 years, new opportunities for rapid mapping of land cover over vast areas have steadily emerged thanks to satellite photography with excellent spatial and temporal resolution [28]. The Copernicus Program, funded by the European Space Agency (ESA), now offers Sentinel, a global monitoring satellite platform that captures images of the entire Earth's surface every six days in various regions of the electromagnetic spectrum.…”

“…The Copernicus Program, funded by the European Space Agency (ESA), now offers Sentinel, a global monitoring satellite platform that captures images of the entire Earth's surface every six days in various regions of the electromagnetic spectrum. Sentinel-1 [29], equipped with a SAR-C sensor, measures in the microwave ranges of the electromagnetic spectrum with wavelengths ranging from 0.1 cm to 100 cm [25,30], and Sentinel-2 [31], equipped with a Multispectral Instrument (MSI), measures in the optical ranges of the electromagnetic spectrum with wavelengths ranging from 0.4 to 15 micrometers. [25].The ability of synthetic aperture radar (SAR) data to penetrate clouds, weather independent, and allow for day and night collecting has led to an increase in the usage of SAR data for Earth observation over the past few decades [32].…”