Change Detection of Deforestation in the Brazilian Amazon Using Landsat Data and Convolutional Neural Networks

Abstract

Mapping deforestation is an essential step in the process of managing tropical rainforests. It lets us understand and monitor both legal and illegal deforestation and its implications, which include the effect deforestation may have on climate change through greenhouse gas emissions. Given that there is ample room for improvements when it comes to mapping deforestation using satellite imagery, in this study, we aimed to test and evaluate the use of algorithms belonging to the growing field of deep learning (DL), particularly convolutional neural networks (CNNs), to this end. Although studies have been using DL algorithms for a variety of remote sensing tasks for the past few years, they are still relatively unexplored for deforestation mapping. We attempted to map the deforestation between images approximately one year apart, specifically between 2017 and 2018 and between 2018 and 2019. Three CNN architectures that are available in the literature—SharpMask, U-Net, and ResUnet—were used to classify the change between years and were then compared to two classic machine learning (ML) algorithms—random forest (RF) and multilayer perceptron (MLP)—as points of reference. After validation, we found that the DL models were better in most performance metrics including the Kappa index, F1 score, and mean intersection over union (mIoU) measure, while the ResUnet model achieved the best overall results with a value of 0.94 in all three measures in both time sequences. Visually, the DL models also provided classifications with better defined deforestation patches and did not need any sort of post-processing to remove noise, unlike the ML models, which needed some noise removal to improve results.

Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2

“…Although spatial and spectral resolution offered by Landsat and MODIS is well-suited for analysis of the deforestation [13,27,30,60], its temporal resolution is not appropriate for high-frequency forest change detection. While the Landsat data were limited by annual and sub-annual frequency of observations, the Sentinel-2 mission [15] may provide the high-resolution (up to 10m) images every 5 days.…”

“…Most of these works are dedicated to the Amazonian rainforests -most cut down forest in the world [2,3,37]. In [13] the better performance of deep learning (SharpMask [47], U-Net, and ResUNet [61]) models in respect with classic machine learning (Random Forest [7], and Multilayer perceptron [25]) algorithms to track the change detection of deforestation in the Amazon using Landsat data are presented. Ortega et al [45] reviewed several deep learning methods like Early Fusion CNN model and Siamese CNN model [10] for deforestation detection in Amazon forests.…”

Instance Segmentation for Large, Multi-Channel Remote Sensing Imagery Using Mask-RCNN and a Mosaicking Approach

“…DL enables pattern recognition in different data abstraction levels, varying from low-level information (corners and edges), up to high-level information (full objects) [4]. This approach achieves state-of-the-art results in different applications in remote sensing digital image processing [5]: pan-sharpening [6][7][8][9]; image registration [10][11][12][13], change detection [14][15][16][17], object detection [18][19][20][21], semantic segmentation [22][23][24][25], and time series analysis [26][27][28][29]. The classification algorithms applied in remote sensing imagery uses spatial, spectral, and temporal information to extract characteristics from the targets, where a wide variety of targets show significant results: clouds [30][31][32][33], dust-related air pollutant [34][35][36][37] land-cover/land-use [38][39][40][41], urban features [42][43][44][45], and ocean [46][47]…”

“…This is a data limitation for optical Earth observation sensors that are generally multispectral, where the available channels provide complementary information that maximizes accuracy. In semantic segmentation, approaches to aggregate more information considered: (a) the use of image fusion techniques, where the three bands used are data integration products [84]; (b) input layer adequation to support a larger amount of channels, e.g., 14 channels [15] 12 channels [14], 7 channels [85], and 4 channels [86].…”

Stochastic spatial random forest (SS-RF) for interpolating probabilities of missing land cover data

“…In previous work [16] we developed a machine learning approach to spatial interpolation which is fast and accurate. Machine learning methods are popular and useful for remote sensing applications including for identifying clouds and cloud shadow as a preprocessing step to interpolation [11,17], and monitoring changes in forest cover [18]. Machine learning algorithms are also popular for important environmental monitoring beyond remote sensing applications including identifying deforestation [19] and landslide susceptibility [20].…”