Abstract
Coastal mangrove forests provide important ecosystem goods and services, including carbon sequestration, biodiversity conservation, and hazard mitigation. However, they are being destroyed at an alarming rate by human activities. To characterize mangrove forest changes, evaluate their impacts, and support relevant protection and restoration decision making, accurate and up-to-date mangrove extent mapping at large spatial scales is essential. Available large-scale mangrove extent data products use a single machine learning method commonly with 30 m Landsat imagery, and significant inconsistencies remain among these data products. With huge amounts of satellite data involved and the heterogeneity of land surface characteristics across large geographic areas, finding the most suitable method for large-scale high-resolution mangrove mapping is a challenge. The objective of this study is to evaluate the performance of a machine learning ensemble for mangrove forest mapping at 20 m spatial resolution across West Africa using Sentinel-2 (optical) and Sentinel-1 (radar) imagery. The machine learning ensemble integrates three commonly used machine learning methods in land cover and land use mapping, including Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network (NN). The cloud-based big geospatial data processing platform Google Earth Engine (GEE) was used for pre-processing Sentinel-2 and Sentinel-1 data. Extensive validation has demonstrated that the machine learning ensemble can generate mangrove extent maps at high accuracies for all study regions in West Africa (92%–99% Producer’s Accuracy, 98%–100% User’s Accuracy, 95%–99% Overall Accuracy). This is the first-time that mangrove extent has been mapped at a 20 m spatial resolution across West Africa. The machine learning ensemble has the potential to be applied to other regions of the world and is therefore capable of producing high-resolution mangrove extent maps at global scales periodically.
Highlights
Land cover classification using remotely sensed data is capable of generating information that can play an important role in forest resource inventory, agricultural monitoring, and environmental change (Zhan et al, 2002; Atzberger, 2013; White et al, 2016)
The objective of this study is to evaluate the performance of an ensemble of the commonly used machine learning methods, namely, Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network (NN) for mapping mangrove extent at 20 m resolution at a continental scale (West Africa) using a combination of Sentinel-2 and Sentinel-1 satellite data
Random Forest (RF) RF is a machine learning method using the results from many different models to calculate a response (Gislason et al, 2004; Pal, 2005; Horning, 2010; Na et al, 2010; Tian et al, 2016)
Summary
Land cover classification using remotely sensed data is capable of generating information that can play an important role in forest resource inventory, agricultural monitoring, and environmental change (Zhan et al, 2002; Atzberger, 2013; White et al, 2016). The use of complex machine learning algorithms in land cover remote sensing remains in its infancy and choosing the most suitable method for large-scale land cover mapping remains a challenge (Mondal et al, 2019; Zhang et al, 2020) This problem is exacerbated in the tropics where cloud cover inhibits optical imagery, in regions such as West Africa where persistent clouds can render large volumes of data unsuitable for land cover mapping. Within the West Africa region, mangroves cover an area of approximately 17,000 km, and range from relatively small lagoons and estuaries in Cote D’Ivoire, to vast deltas in Nigeria They have often been heavily impacted by human activities such as urban expansion and oil exploration in recent decades
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
