Using Sentinel-1 satellite imagery to quantify oil palm cultivation: A case study from Cameroon

Area of Science:

• Environmental Science
• Remote Sensing
• Agricultural Science

Background:

• Global tropical deforestation is rising, threatening ecosystems and services.
• High demand for palm oil drives agricultural expansion in tropical regions.
• Cameroon faces economic reliance on palm expansion, risking forest cover.

Purpose of the Study:

• To quantify the change in oil palm extent in Cameroon from 2015 to 2025.
• To assess the impact of oil palm expansion on forest cover.
• To evaluate the utility of Sentinel-1 SAR data and Random Forest for monitoring.

Main Methods:

• Utilized Sentinel-1 Synthetic Aperture Radar (SAR) satellite data.
• Employed the Random Forest machine learning algorithm for land cover classification.
• Focused analysis on key regions within Cameroon for detailed quantification.

Main Results:

• Oil palm cultivation increased by 13-55% in the analyzed areas between 2015 and 2025.
• The South Region exhibited the most substantial forest cover change due to oil palm expansion.
• Confirmed the effectiveness of Sentinel-1 and Random Forest for monitoring.

Conclusions:

• Oil palm expansion is a significant driver of deforestation in Cameroon.
• Remote sensing and machine learning are effective tools for tracking agricultural impacts.
• Sustainable land-use planning is crucial for mitigating deforestation in palm oil-producing regions.