Multi-sensor decision tree machine learning algorithm for identifying mangrove ecosystem

¹ Faculty of Forestry and Environment, IPB-University, Road Lingkar Kampus IPB, Darmaga, Bogor, 16680, Indonesia
² Faculty of Forest Sciences and Forest Ecology, University of Göttingen, Büsgenweg 5, 37077 Göttingen, Germany

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

This paper compares the reliability of multi-spatial-resolution PlanetScope imagery in Tapanuli Tengah, Sentinel-2A imagery in Asahan Regency, and Landsat-8 imagery in Asahan Regency for detecting mangroves and their vegetation density using a decision tree machine learning (DT-ML) approach. Landsat 8 and Sentinel-2A were used to identify mangrove and non-mangrove classes, while high-resolution PlanetScope was specifically examined to detect mangrove density, i.e., dense, medium, and sparse. This study demonstrates that DT-ML achieves overall accuracies of 92.4% (Landsat 8), 93.0% (Sentinel-2A), 92.1% (PlanetScope Tapanuli Tengah Site), and 94.5% (PlanetScope Langkat Site). NDVI and substrate were found to be the most influential variables across all datasets, particularly in distinguishing mangrove from non-mangrove ecosystems, thereby reducing misclassification of non-mangrove classes. PlanetScope's high spatial resolution (3 m) delivers superior detail, enabling more accurate detection of canopy density. The Sentinel-2A Red Edge channel is crucial for distinguishing mangroves from other vegetation types. The Decision Tree algorithm has been successfully adapted to multi-resolution imagery, yielding a model with good interpretability and straightforward generalization. It is concluded that Decision Tree Machine Learning may provide higher accuracy and the ability to integrate spectral variables from satellite imagery with non-spectral socio-geo-biophysical variables.