Classification of Landscape Affected by Deforestation Using High-Resolution Remote Sensing Data and Deep-Learning Techniques

Abstract

Human-induced deforestation has a major impact on forest ecosystems and therefore its detection and analysis methods should be improved. This study classified landscape affected by human-induced deforestation efficiently using high-resolution remote sensing and deep-learning. The SegNet and U-Net algorithms were selected for application with high-resolution remote sensing data obtained by the Kompsat-3 satellite. Land and forest cover maps were used as base data to construct accurate deep-learning datasets of deforested areas at high spatial resolution, and digital maps and a softwood database were used as reference data. Sites were classified into forest and non-forest areas, and a total of 13 areas (2 forest and 11 non-forest) were selected for analysis. Overall, U-Net was more accurate than SegNet (74.8% vs. 63.3%). The U-Net algorithm was about 11.5% more accurate than the SegNet algorithm, although SegNet performed better for the hardwood and bare land classes. The SegNet algorithm misclassified many forest areas, but no non-forest area. There was reduced accuracy of the U-Net algorithm due to misclassification among sub-items, but U-Net performed very well at the forest/non-forest area classification level, with 98.4% accuracy for forest areas and 88.5% for non-forest areas. Thus, deep-learning modeling has great potential for estimating human-induced deforestation in mountain areas. The findings of this study will contribute to more efficient monitoring of damaged mountain forests and the determination of policy priorities for mountain area restoration.

Deforestation Detection in the Amazon Rainforest With Spatial and Channel Attention Mechanisms

“…Other works with similar approaches also reported remarkable results using DL methods for deforestation detection (Lee et al, 2020, Maretto et al, 2020. However, despite the positive results, current methods are still sensitive to pseudo-changes.…”

Forest Conservation with Deep Learning: A Deeper Understanding of Human Geography around the Betampona Nature Reserve, Madagascar

“…In a Fully Convolutional Neural Network (FCNN), the final fully connected dense layer within a CNN architecture is replaced with an up-sampling convolutional network. The architecture of the U-Net model (Figure 3) first implemented by [27] for biomedical image segmentation has been used in forest type and tree species mapping [17] as well as the delineation of human-induced deforestation [16].…”

“…Freely available imagery data from Landsat missions is a major data source for both large-and small-scale classification maps [15]. However, coarse resolution (10-100 m) images are not spatially detailed enough for forest conservation mapping projects [16] or the identification of individual tree species [17]. WorldView-3 (WV-3) has a high spatial resolution with a resolution of 1.2 m for visible bands (VNIR), 3.7 m for shortwave infrared (SWIR) bands, and 0.3 m in the panchromatic band.…”

Earth Observation from KOMPSAT Optical, Thermal, and Radar Satellite Images

“…Thus, six papers have been published. Two of the six papers dealt with topics related to optical images [7,8], two with radar image topics [9,10], and two with image fusion topics [11,12].…”

“…Kim and Lee [10] mapped the flooded area after the collapse of the Laos Xe-Pian Xe-Namnoy Dam located in Champasak Province, Laos. They used C-band Sentinel-1 SAR ground range detected (GRD) data.…”