Search

This study addresses the challenge of estimating above-ground biomass (AGB) in the Amazon rainforest by developing a reference geographical database, which provides the ground truth, and comparing the relative importance of using Synthetic Aperture Radar (SAR) and optical remote sensing data to automatically infer AGB. In the experiments reported in this article, we assessed how those two remote sensing data sources impact the accuracy of AGB estimates produced by regression models built with Random Forest (RF) and Extreme Gradient Boosting (XGBoost). The research involved compiling a comprehensive database from many available forest inventories, integrating parcel- and tree-level data to enable precise biomass estimation. The methodology included setting up a spatial data analysis environment, standardizing data, and implementing an experimental protocol with feature selection and leave-one-out cross-validation. The results demonstrate that both kinds of data, i.e., SAR and optical, and their combination can be used for estimating AGB, providing valuable insights for forest management and climate change mitigation efforts. The reference database is available upon request to the corresponding authors.

This paper reports research that is part of a project to combat deforestation in the Brazilian Amazon rainforest by developing an online system designed to forecast deforestation risk over the short term, spanning 2 to 4 weeks. This online platform aims to empower stakeholders with timely data, facilitating proactive conservation and intervention strategies to safeguard the Amazon rainforest. We built a multitemporal database that compiles weekly deforestation alerts from the DETER project, forming our analysis’s backbone. Utilizing the XGBOOST regression algorithm, we have crafted a predictive model that identifies areas within the Amazon at imminent risk of more intensive deforestation. Preliminary results reveal an RMSE of 0.29 for predicting areas under deforestation risk, as validated against early alert data from 2020 to 2023. Our work advances environmental monitoring by focusing on a spatial resolution of 25 km × 25 km, providing accessible, near real-time information on deforestation risks.

Knowing the spatial distribution of endangered tree species in a forest ecosystem or forest remnants is a valuable information to support environmental conservation practices. The use of Unmanned Aerial Vehicles (UAVs) offers a suitable alternative for this task, providing very high-resolution images at low costs. In parallel, recent advances in the computer vision field have led to the development of effective deep learning techniques for end-to-end semantic image segmentation. In this scenario, the DeepLabv3+ is well established as the state-of-the-art deep learning method for semantic segmentation tasks. The present paper proposes and assesses the use of DeepLabv3+ for mapping the threatened Dipteryx alata Vogel tree, popularly also known as cumbaru. We also compare two backbone networks for feature extraction in the DeepLabv3+ architecture: the Xception and MobileNetv2. Experiments carried out on a dataset consisting of 225 UAV/RGB images of an urban area in Midwest Brazil demonstrated that DeepLabv3+ was able to achieve in mean overall accuracy and F1-score above 90%, and IoU above 80%. The experimental analysis also pointed out that the MobileNetv2 backbone overcame its counterpart by a wide margin due to its comparatively simpler architecture in view of the available training data.

Citrus producers need to monitor orchards frequently, and would benefit greatly from having automated tools to analyze aerial images acquired by drones over the plantations. However, analysing large aerial data sets to enable producers to take management decisions that would optimize productivity and sustainability over time and space remains challenging. Motivated by the success of deep learning in computer vision, this work proposes a novel approach based on Fully Convolutional Regression Networks and Multi-Task Learning to detect individual full-grown trees, tree seedlings, and tree gaps in citrus orchards for inventory tracking. We show that the proposal can identify eight-year-old orange trees with accuracy between 95–99% in high-density commercial plantations where adjacent crowns overlap. This quality of detection was achieved on RGB orthomosaics with a pixel size of about 9.5 cm and requires the nominal spacing between adjacent trees as a priori information. Our results also highlight that detecting tree seedlings and tree gaps remains a challenge. For these two categories, classification sensitivity (recall) was between 59–100% and 63–94%, respectively.

The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced feature extraction and classification methods. Different from the traditional feature extraction methods, that highly depend on user’s knowledge, the convolutional neural network (CNN)-based method can automatically learn and extract the spatial-related features layer by layer. However, in order to capture significant features of the data, the CNN classifier requires a large number of training samples, which are hardly available when dealing with tree species in tropical forests. This study investigated the following topics concerning the classification of 14 tree species in a subtropical forest area of Southern Brazil: i) the performance of the CNN method associated with a previous step to increase and balance the sample set (data augmentation) for tree species classification as compared to the conventional machine learning methods support vector machine (SVM) and random forest (RF) using the original training data; ii) the performance of the SVM and RF classifiers when associated with a data augmentation step and spatial features extracted from a CNN. Results showed that the CNN classifier outperformed the conventional SVM and RF classifiers, reaching an overall accuracy (OA) of 84.37% and Kappa of 0.82. The SVM and RF had a poor accuracy with the original spectral bands (OA 62.67% and 59.24%) but presented an increase between 14% and 21% in OA when associated with a data augmentation and spatial features extracted from a CNN.

The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. This study investigated the following topics concerning the classification of 16 tree species in two subtropical forest fragments of Southern Brazil: i) the potential integration of UAV-borne hyperspectral images with 3D information derived from their photogrammetric point cloud (PPC); ii) the performance of two machine learning methods (support vector machine – SVM and random forest – RF) when employing different datasets at a pixel and individual tree crown (ITC) levels; iii) the potential of two methods for dealing with the imbalanced sample set problem: a new weighted SVM (wSVM) approach, which attributes different weights to each sample and class, and a deep learning classifier (convolutional neural network – CNN), associated with a previous step to balance the sample set; and finally, iv) the potential of this last classifier for tree species classification as compared to the above mentioned machine learning methods. Results showed that the inclusion of the PPC features to the hyperspectral data provided a great accuracy increase in tree species classification results when conventional machine learning methods were applied, between 13 and 17% depending on the classifier and the study area characteristics. When using the PPC features and the canopy height model (CHM), associated with the majority vote (MV) rule, the SVM, wSVM and RF classifiers reached accuracies similar to the CNN, which outperformed these classifiers for both areas when considering the pixel-based classifications (overall accuracy of 84.4% in Area 1, and 74.95% in Area 2). The CNN was between 22% and 26% more accurate than the SVM and RF when only the hyperspectral bands were employed. The wSVM provided a slight increase in accuracy not only for some lesser represented classes, but also some major classes in Area 2. While conventional machine learning methods are faster, they demonstrated to be less stable to changes in datasets, depending on prior segmentation and hand-engineered features to reach similar accuracies to those attained by the CNN. To date, CNNs have been barely explored for the classification of tree species, and CNN-based classifications in the literature have not dealt with hyperspectral data specifically focusing on tropical environments. This paper thus presents innovative strategies for classifying tree species in subtropical forest areas at a refined legend level, integrating UAV-borne 2D hyperspectral and 3D photogrammetric data and relying on both deep and conventional machine learning approaches.