Search

The availability of remote-sensing multisource data from optical-based satellite sensors has created new opportunities and challenges for forest monitoring in the Amazon Biome. In particular, change-detection analysis has emerged in recent decades to monitor forest-change dynamics, supporting some Brazilian governmental initiatives such as PRODES and DETER projects for biodiversity preservation in threatened areas. In recent years fully convolutional network architectures have witnessed numerous proposals adapted for the change-detection task. This paper comprehensively explores state-of-the-art fully convolutional networks such as U-Net, ResU-Net, SegNet, FC-DenseNet, and two DeepLabv3+ variants on monitoring deforestation in the Brazilian Amazon. The networks' performance is evaluated experimentally in terms of Precision, Recall, F 1 -score, and computational load using satellite images with different spatial and spectral resolution: Landsat-8 and Sentinel-2. We also include the results of an unprecedented auditing process performed by senior specialists to visually evaluate each deforestation polygon derived from the network with the highest accuracy results for both satellites. This assessment allowed estimation of the accuracy of these networks simulating a process "in nature" and faithful to the PRODES methodology. We conclude that the high resolution of Sentinel-2 images improves the segmentation of deforestation polygons both quantitatively (in terms of F 1 -score) and qualitatively. Moreover, the study also points to the potential of the operational use of Deep Learning (DL) mapping as products to be consumed in PRODES. [ABSTRACT FROM AUTHOR]

Remote sensing is widely used in the prediction of forest cover. Forest plays an important role in the balance of the ecosystem. It helps to maintain the balance between climate. We depend a lot on forests for wood, oxygen, and also for the control of soil erosion. Hence it is our duty to maintain the forest cover on earth. Remote sensing images provide us with lots of information regarding the different landforms and materials. It is also used to predict natural disasters like forest fires, floods, etc. The normalized difference vegetation index is a simple graphical indicator that is used to analyze remote sensing measurements, (eg. space platform) predicting whether the target is live green vegetation or not. However, we have found out that it cannot be used for accurate prediction of forest land cover. With the help of time series data on the Amazon forest, it has been observed that the NDVI index fails to determine some of the important changes in the landform. To rectify this problem, the deep learning model was used to give an accuracy of 100 percent. The deep learning model gives similar results as observed results, hence making it the best-preferred method for predicting forest cover. With the help of multispectral analysis of the data, the deep learning model gives the best results for the red band, and near-infrared bands. [ABSTRACT FROM AUTHOR]

Optical-based near-real time deforestation alert systems in the Brazilian Amazon are ineffective in the rainy season. This study identify clear-cut deforested areas through Neural Network (NN) algorithm based on C-band, VV- and VH-polarized, Sentinel-1 images. Statistical parameters of backscatter coefficients (mean, standard deviation, and the difference between maximum and minimum values – MMD) were computed from 30 Sentinel-1 images, from 2019, used as input parameters of the NN classifier. The samples were manually selected, including forested and deforested areas. After deforestation, mean backscatter signals decreased on the average of 2 dB for VV and 2.3 dB for VH from May to September–October. A Multi-Layer Perceptron (MLP) network was used for detecting near-real time forest disturbances larger than 2 ha. Case studies were performed for both polarizations considered the following input sets to the MLP: mean; mean and standard deviation; mean and MMD; and mean, standard deviation, and MMD. For the 2019 dataset, the latter showed the best performance of the NN algorithm with accuracy and F1 score of 99%. Automatic extraction using 2018 Sentinel-1 images reached accuracy and F1 score of 89% with the MapBiomas reference data and accuracy of 81% and F1 score of 79% with the PRODES reference data. [ABSTRACT FROM AUTHOR]