Mapping Atlantic rainforest degradation and regeneration history with indicator species using convolutional network

Spatial heterogeneity in climate change effects across Brazilian biomes

We present a methodology designed to study the spatial heterogeneity of climate change. Our approach involves decomposing the observed changes in temperature patterns into multiple trend, cycle, and seasonal components within a spatio-temporal model. We apply this method to test the hypothesis of a global long-term temperature trend against multiple trends in distinct biomes. Applying this methodology, we delve into the examination of heterogeneity of climate change in Brazil-a country characterized by a spectrum of climate zones. The findings challenge the notion of a global trend, revealing the presence of distinct trends in warming effects, and more accelerated trends for the Amazon and Cerrado biomes, indicating a composition between global warming and deforestation in determining changes in permanent temperature patterns.

Genetic Structuring of One of the Main Vectors of Sylvatic Yellow Fever: Haemagogus (Conopostegus) leucocelaenus (Diptera: Culicidae)

Genetic diversity and population structuring for the species Haemogogus leucocelaenus, a sylvatic vector of yellow fever virus, were found to vary with the degree of agricultural land use and isolation of fragments of Atlantic Forest in municipalities in the state of São Paulo where specimens were collected. Genotyping of 115 mitochondrial SNPs showed that the populations with the highest indices of genetic diversity (polymorphic loci and mean pairwise differences between the sequences) are found in areas with high levels of agricultural land use (northeast of the State). Most populations exhibited statistically significant negative values for the Tajima D and Fu FS neutrality tests, suggesting recent expansion. The results show an association between genetic diversity in this species and the degree of agricultural land use in the sampled sites, as well as signs of population expansion of this species in most areas, particularly those with the highest forest edge densities. A clear association between population structuring and the distance between the sampled fragments (isolation by distance) was observed: samples from a large fragment of Atlantic Forest extending along the coast of the state of São Paulo exhibited greater similarity with each other than with populations in the northwest of the state.

Mapping threatened canga ecosystems in the Brazilian savanna using U-Net deep learning segmentation and Sentinel-2 images: a first step toward conservation planning

Abstract Canga ecosystems are iron-rich habitats and pose a challenge for conservation and environmental governance in Brazil. They support high levels of biodiversity and endemism and, at the same time, have suffered intense losses and degradation due to large-scale iron ore mining. The Peixe Bravo River Valley in the Brazilian savanna is one of the last natural canga areas that has yet to face the irreversible impacts of mining. However, there are vast gaps in data on the vegetation cover, location, spatial distribution, and area of occurrence of this ecosystem. Therefore, more information is needed on the appropriate scale, without which it is difficult to establish conservation planning and strategies to prevent, mitigate or compensate for impacts on canga ecosystems. In this study, we provide the first map of canga ecosystems in Brazil using the U-Net deep learning model and Sentinel-2 images. In addition, we estimate the degree of direct threat faced by ecosystems due to the spatial overlap of the mapped cangas and the location of mining concession areas for iron ore exploitation. The deep learning algorithm identified and segmented 762 canga patches (overall accuracy of 98.5%) in an area of 30,000 ha in the Peixe Bravo River Valley, demonstrating the high predictive power of the mapping approach. We conclude that the direct threat to canga ecosystems is high since 99.6% of the observed canga patches are included in mining concession areas. We also highlight that the knowledge acquired about the distribution of cangas through the application of an effective method of artificial intelligence and the use of open-source satellite images is especially important for supporting conservation strategies and environmental public policies.

Automated mapping of Portulacaria afra canopies for restoration monitoring with convolutional neural networks and heterogeneous unmanned aerial vehicle imagery

Ecosystem restoration and reforestation often operate at large scales, whereas monitoring practices are usually limited to spatially restricted field measurements that are (i) time- and labour-intensive, and (ii) unable to accurately quantify restoration success over hundreds to thousands of hectares. Recent advances in remote sensing technologies paired with deep learning algorithms provide an unprecedented opportunity for monitoring changes in vegetation cover at spatial and temporal scales. Such data can feed directly into adaptive management practices and provide insights into restoration and regeneration dynamics. Here, we demonstrate that convolutional neural network (CNN) segmentation algorithms can accurately classify the canopy cover of Portulacaria afra Jacq. in imagery acquired using different models of unoccupied aerial vehicles (UAVs) and under variable light intensities. Portulacaria afra is the target species for the restoration of Albany Subtropical Thicket vegetation, endemic to South Africa, where canopy cover is challenging to measure due to the dense, tangled structure of this vegetation. The automated classification strategy presented here is widely transferable to restoration monitoring as its application does not require any knowledge of the CNN model or specialist training, and can be applied to imagery generated by a range of UAV models. This will reduce the sampling effort required to track restoration trajectories in space and time, contributing to more effective management of restoration sites, and promoting collaboration between scientists, practitioners and landowners.

Augmentation-Based Methodology for Enhancement of Trees Map Detalization on a Large Scale

Remote sensing tasks play a very important role in the domain of sensing and measuring, and can be very specific. Advances in computer vision techniques allow for the extraction of various information from remote sensing satellite imagery. This information is crucial in making quantitative and qualitative assessments for monitoring of forest clearing in protected areas for power lines, as well as for environmental analysis, in particular for making assessments of carbon footprint, which is a highly relevant task. Solving these problems requires precise segmentation of the forest mask. Although forest mask extraction from satellite data has been considered previously, no open-access applications are able to provide the high-detailed forest mask. Detailed forest masks are usually obtained using unmanned aerial vehicles (UAV) that set particular limitations such as cost and inapplicability for vast territories. In this study, we propose a novel neural network-based approach for high-detailed forest mask creation. We implement an object-based augmentation technique for a minimum amount of labeled high-detailed data. Using this augmented data we fine-tune the models, which are trained on a large forest dataset with less precise labeled masks. The provided algorithm is tested for multiple territories in Russia. The F1-score, for small details (such as individual trees) was improved to 0.929 compared to the baseline score of 0.856. The developed model is available in an SAAS platform. The developed model allows a detailed and precise forest mask to be easily created, which then be used for solving various applied problems.

Detection of Windthrown Tree Stems on UAV-Orthomosaics Using U-Net Convolutional Networks

The increasing number of severe storm events is threatening European forests. Besides the primary damages directly caused by storms, there are secondary damages such as bark beetle outbreaks and tertiary damages due to negative effects on the market. These subsequent damages can be minimized if a detailed overview of the affected area and the amount of damaged wood can be obtained quickly and included in the planning of clearance measures. The present work utilizes UAV-orthophotos and an adaptation of the U-Net architecture for the semantic segmentation and localization of windthrown stems. The network was pre-trained with generic datasets, randomly combining stems and background samples in a copy–paste augmentation, and afterwards trained with a specific dataset of a particular windthrow. The models pre-trained with generic datasets containing 10, 50 and 100 augmentations per annotated windthrown stems achieved F1-scores of 73.9% (S1Mod10), 74.3% (S1Mod50) and 75.6% (S1Mod100), outperforming the baseline model (F1-score 72.6%), which was not pre-trained. These results emphasize the applicability of the method to correctly identify windthrown trees and suggest the collection of training samples from other tree species and windthrow areas to improve the ability to generalize. Further enhancements of the network architecture are considered to improve the classification performance and to minimize the calculative costs.

The flowering of Atlantic Forest Pleroma trees

Mapping the spatial distribution of a plant is a current challenge in ecology. Here, a convolutional neural network (CNN) and 33,798 Sentinel-2 satellite images were used to detect and map forest stands dominated by trees of the genus Pleroma by their magenta-to-deep-purple blossoms in the entire Brazilian Atlantic Forest domain, from June 2016 to July 2020. The Pleroma genus, known for its pioneer behaviour, was detected in an area representing 10.8% of the Atlantic Forest, associated negatively with temperature and positively with elevation, slope, tree cover and precipitation. The detection of another genus by the model, 18% of all the detections contained only pink blooming Handroanthus trees, highlighted that botanical identification from space must be taken with caution, particularly outside the known distribution range of the species. The Pleroma blossom seasonality occurred over a period of ~5–6 months centered on the March equinox and populations with distinct blossom timings were found. Our results indicate that in the Atlantic Forest, the remaining natural forest is less diverse than expected but is at least recovering from degradation. Our study suggests a method to produce ecological-domain scale maps of tree genera and species based on their blossoms that could be used for tree studies and biodiversity assessments.

Land Use Land Cover Classification with U-Net: Advantages of Combining Sentinel-1 and Sentinel-2 Imagery

The U-net is nowadays among the most popular deep learning algorithms for land use/land cover (LULC) mapping; nevertheless, it has rarely been used with synthetic aperture radar (SAR) and multispectral (MS) imagery. On the other hand, the discrimination between plantations and forests in LULC maps has been emphasized, especially for tropical areas, due to their differences in biodiversity and ecosystem services provision. In this study, we trained a U-net using different imagery inputs from Sentinel-1 and Sentinel-2 satellites, MS, SAR and a combination of both (MS + SAR); while a random forests algorithm (RF) with the MS + SAR input was also trained to evaluate the difference in algorithm selection. The classification system included ten classes, including old-growth and secondary forests, as well as old-growth and young plantations. The most accurate results were obtained with the MS + SAR U-net, where the highest overall accuracy (0.76) and average F1-score (0.58) were achieved. Although MS + SAR and MS U-nets gave similar results for almost all of the classes, for old-growth plantations and secondary forest, the addition of the SAR band caused an F1-score increment of 0.08–0.11 (0.62 vs. 0.54 and 0.45 vs. 0.34, respectively). Consecutively, in comparison with the MS + SAR RF, the MS + SAR U-net obtained higher F1-scores for almost all the classes. Our results show that using the U-net with a combined input of SAR and MS images enabled a higher F1-score and accuracy for a detailed LULC map, in comparison with other evaluated methods.

Deep Convolutional Neural Network for Large-Scale Date Palm Tree Mapping from UAV-Based Images

Large-scale mapping of date palm trees is vital for their consistent monitoring and sustainable management, considering their substantial commercial, environmental, and cultural value. This study presents an automatic approach for the large-scale mapping of date palm trees from very-high-spatial-resolution (VHSR) unmanned aerial vehicle (UAV) datasets, based on a deep learning approach. A U-Shape convolutional neural network (U-Net), based on a deep residual learning framework, was developed for the semantic segmentation of date palm trees. A comprehensive set of labeled data was established to enable the training and evaluation of the proposed segmentation model and increase its generalization capability. The performance of the proposed approach was compared with those of various state-of-the-art fully convolutional networks (FCNs) with different encoder architectures, including U-Net (based on VGG-16 backbone), pyramid scene parsing network, and two variants of DeepLab V3+. Experimental results showed that the proposed model outperformed other FCNs in the validation and testing datasets. The generalizability evaluation of the proposed approach on a comprehensive and complex testing dataset exhibited higher classification accuracy and showed that date palm trees could be automatically mapped from VHSR UAV images with an F-score, mean intersection over union, precision, and recall of 91%, 85%, 0.91, and 0.92, respectively. The proposed approach provides an efficient deep learning architecture for the automatic mapping of date palm trees from VHSR UAV-based images.

Forest Restoration Monitoring Protocol with a Low-Cost Remotely Piloted Aircraft: Lessons Learned from a Case Study in the Brazilian Atlantic Forest

Traditional forest restoration (FR) monitoring methods employ spreadsheets and photos taken at the ground level. Since remotely piloted aircraft (RPA) generate a panoramic high resolution and georeferenced view of the entire area of interest, this technology has high potential to improve the traditional FR monitoring methods. This study evaluates how low-cost RPA data may contribute to FR monitoring of the Brazilian Atlantic Forest by the automatic remote measurement of Tree Density, Tree Height, Vegetation Cover (area covered by trees), and Grass Infestation. The point cloud data was processed to map the Tree Density, Tree Height, and Vegetation Cover parameters. The orthomosaic was used for a Random Forest classification that considered trees and grasses as a single land cover class. The Grass Infestation parameter was mapped by the difference between this land cover class (which considered trees and grasses) and the Vegetation Cover results (obtained by the point cloud data processing). Tree Density, Vegetation Cover, and Grass Infestation parameters presented F_scores of 0.92, 0.85, and 0.64, respectively. Tree Height accuracy was indicated by the Error Percentage considering the traditional fieldwork and the RPA results. The Error Percentage was equal to 0.13 and was considered accurate because it estimated a 13% shorter height for trees that averaged 1.93 m tall. Thus, this study showed that the FR structural parameters were accurately measured by the low-cost RPA, a technology that contributes to FR monitoring. Despite accurately measuring the structural parameters, this study reinforced the challenge of measuring the Biodiversity parameter via remote sensing because the classification of tree species was not possible. After all, the Brazilian Atlantic Forest is a biodiversity hotspot, and thus different species have similar spectral responses in the visible spectrum and similar geometric forms. Therefore, until improved automatic classification methods become available for tree species, traditional fieldwork remains necessary for a complete FR monitoring diagnostic.

Digital mapping of structural conservation practices in the Midwest U.S. croplands: Implementation and preliminary analysis

The application of best management practices is a long-term conservation effort in Midwest U.S. croplands, and many farmers have adopted structural conservation practices (SCPs) to reduce soil erosion and surface water runoff, such as terraces and grassed waterways. Despite that, the geographic distribution of these practices is barely known in the region, and mapping initiatives are required to develop timely and spatially explicit inventories of SCP areas. This study presents the first mapping of SCPs in the agricultural areas over 12 Midwest U.S. states. Semantic segmentation model (adapted U-Net) and National Agriculture Imagery Program 2018-2019 data were used to map the SCP areas at 2-m spatial resolution (490.2 billion pixels). In general, mapping results achieved 78.2% overall accuracy across 20 counties. Our results indicate that 52% of SCP areas are distributed over Iowa (26%), Illinois (15%), and Nebraska (11%). In contrast, the states with the lowest SCP areas are Michigan and North Dakota, with less than 4% of SCP areas. Since the SCP extent is also dependent on the number of cropland areas per state, the percentage of SCP per cropland area was calculated. Specifically, the average percentage of SCP area per cropland is ~1.19%, ranging from 0.8 (e.g., North Dakota and south Minnesota) to 5.5% (e.g., northeast Kansas and southwest Iowa). Interestingly, results also illustrate that regions with high soil erosion rates present the largest percentage of SCP areas in croplands, indicating conservation efforts by farmers. While this preliminary analysis shows some limitations in the mapping quality (mislabel, non-accurate location or discontinuity of SCP areas), the framework has a potential for operational conservation monitoring. The development of such mapping has positive implications for conservation programs, and this geospatial inventory is easily accessible information for the large-area evaluation of conservation practices across Midwest U.S. croplands.

Anticipation of common buzzard population patterns in the changing UK landscape

Harmonious coexistence between humans, other animals and ecosystem services they support is a complex issue, typically impacted by landscape change, which affects animal distribution and abundance. In the last 30 years, afforestation on grasslands across Great Britain has been increasing, motivated by socio-economic reasons and climate change mitigation. Beyond expected benefits, an obvious question is what are the consequences for wider biodiversity of this scale of landscape change. Here, we explore the impact of such change on the expanding population of common buzzards Buteo buteo, a raptor with a history of human-induced setbacks. Using Resource-Area-Dependence Analysis (RADA), with which we estimated individuals' resource needs using 10-day radio-tracking sessions and the 1990s Land Cover Map of GB, and agent-based modelling, we predict that buzzards in our study area in lowland UK had fully recovered (to 2.2 ind km^-2) by 1995. We also anticipate that the conversion of 30%, 60% and 90% of economically viable meadow into woodland would reduce buzzard abundance nonlinearly by 15%, 38% and 74%, respectively. The same approach used here could allow for cost-effective anticipation of other animals' population patterns in changing landscapes, thus helping to harmonize economy, landscape change and biodiversity.

Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images

Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ∼3000 km 2 of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees’ distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity.