Explore the vast range of titles available.

Mapping forest types and tree species at regional scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. Here, we assess the potential of a U‐net convolutional network, a recent deep learning algorithm, to identify and segment (1) natural forests and eucalyptus plantations, and (2) an indicator of forest disturbance, the tree species Cecropia hololeuca, in very high resolution images (0.3 m) from the WorldView‐3 satellite in the Brazilian Atlantic rainforest region. The networks for forest types and Cecropia trees were trained with 7611 and 1568 red‐green‐blue (RGB) images, respectively, and their dense labeled masks. Eighty per cent of the images were used for training and 20% for validation. The U‐net network segmented forest types with an overall accuracy >95% and an intersection over union (IoU) of 0.96. For C. hololeuca, the overall accuracy was 97% and the IoU was 0.86. The predictions were produced over a 1600 km2 region using WorldView‐3 RGB bands pan‐sharpened at 0.3 m. Natural and eucalyptus forests compose 79 and 21% of the region's total forest cover (82 250 ha). Cecropia crowns covered 1% of the natural forest canopy. An index to describe the level of disturbance of the natural forest fragments based on the spatial distribution of Cecropia trees was developed. Our work demonstrates how a deep learning algorithm can support applications such as vegetation, tree species distributions and disturbance mapping on a regional scale. In this paper, we have assessed the potential of a deep learning algorithm, the U‐net model, to identify and segment (1) natural forest and eucalyptus plantation, and (2) a tree species indicator of past forest disturbance (Cecropia hololeuca) using Red‐Green‐Blue WorldView‐3 images at 0.3 m of spatial resolution. The overall accuracies of both forest types and C. hololeuca segmentations were above 95%. The method was therefore used to map forest types and all individuals of C. hololeuca in a 1600 km² region of fragmented Atlantic Forest near São Paulo, Brazil. From the C. hololeuca occurrence and distribution in the fragments, we derived a new disturbance metric. Our results show that this method is very promising for applications such as tree species or vegetation mapping.

Recently, remote sensing image time series analysis has being widely used to investigate the dynamics of environments over time. Many studies have combined image time series analysis with machine learning methods to improve land use and cover change mapping. In order to support image time series analysis, analysis-ready data (ARD) image collections have been modeled and organized as multidimensional data cubes. Data cubes can be defined as sets of time series associated with spatially aligned pixels. Based on lessons learned in the research project e-Sensing, related to national demands for land use and cover monitoring and related to state-of-the-art studies on relevant topics, we define the requirements to build Earth observation data cubes for Brazil. This paper presents the methodology to generate ARD and multidimensional data cubes from remote sensing images for Brazil. We describe the computational infrastructure that we are developing in the Brazil Data Cube project, composed of software applications and Web services to create, integrate, discover, access, and process the data sets. We also present how we are producing land use and cover maps from data cubes using image time series analysis and machine learning techniques.

The Atlantic rainforest of Brazil is one of the global terrestrial hotspots of biodiversity. Despite having undergone large scale deforestation, forest cover has shown signs of increases in the last decades. Here, to understand the degradation and regeneration history of Atlantic rainforest remnants near São Paulo, we combine a unique dataset of very high resolution images from Worldview-2 and Worldview-3 (0.5 and 0.3m spatial resolution, respectively), georeferenced aerial photographs from 1962 and use a deep learning method called U-net to map (i) the forest cover and changes and (ii) two pioneer tree species, Cecropia hololeuca and Tibouchina pulchra. For Tibouchina pulchra, all the individuals were mapped in February, when the trees undergo mass-flowering with purple and pink blossoms. Additionally, elevation data at 30m spatial resolution from NASA Shuttle Radar Topography Mission (SRTM) and annual mean climate variables (Terraclimate datasets at ∼ 4km of spatial resolution) were used to analyse the forest and species distributions. We found that natural forests are currently more frequently found on south-facing slopes, likely because of geomorphology and past land use, and that Tibouchina is restricted to the wetter part of the region (southern part), which annually receives at least 1600 mm of precipitation. Tibouchina pulchra was found to clearly indicate forest regeneration as almost all individuals were found within or adjacent to forests regrown after 1962. By contrast, Cecropia hololeuca was found to indicate older disturbed forests, with all individuals almost exclusively found in forest fragments already present in 1962. At the regional scale, using the dominance maps of both species, we show that at least 4.3% of the current region's natural forests have regrown after 1962 (Tibouchina dominated, ∼ 4757 ha) and that ∼ 9% of the old natural forests have experienced significant disturbance (Cecropia dominated).

Our limited understanding of the climate controls on tropical forest seasonality is one of the biggest sources of uncertainty in modeling climate change impacts on terrestrial ecosystems. Combining leaf production, litterfall and climate observations from satellite and ground data in the Amazon forest, we show that seasonal variation in leaf production is largely triggered by climate signals, specifically, insolation increase (70.4% of the total area) and precipitation increase (29.6%). Increase of insolation drives leaf growth in the absence of water limitation. For these non-water-limited forests, the simultaneous leaf flush occurs in a sufficient proportion of the trees to be observed from space. While tropical cycles are generally defined in terms of dry or wet season, we show that for a large part of Amazonia the increase in insolation triggers the visible progress of leaf growth, just like during spring in temperate forests. The dependence of leaf growth initiation on climate seasonality may result in a higher sensitivity of these ecosystems to changes in climate than previously thought.

Atmospheric methane concentrations were nearly constant between 1999 and 2006, but have been rising since by an average of ~8 ppb per year. Increases in wetland emissions, the largest natural global methane source, may be partly responsible for this rise. The scarcity of in situ atmospheric methane observations in tropical regions may be one source of large disparities between top-down and bottom-up estimates. Here we present 590 lower-troposphere vertical profiles of methane concentration from four sites across Amazonia between 2010 and 2018. We find that Amazonia emits 46.2 ± 10.3 Tg of methane per year (~8% of global emissions) with no temporal trend. Based on carbon monoxide, 17% of the sources are from biomass burning with the remainder (83%) attributable mainly to wetlands. Northwest-central Amazon emissions are nearly aseasonal, consistent with weak precipitation seasonality, while southern emissions are strongly seasonal linked to soil water seasonality. We also find a distinct east-west contrast with large fluxes in the northeast, the cause of which is currently unclear.

Tropical forests regulate the global water and carbon cycles and also host most of the world’s biodiversity. Despite their importance, they are hard to survey due to their location, extent, and particularly, their cloud coverage. Clouds hinder the spatial and radiometric correction of satellite imagery and also diminishing the useful area on each image, making it difficult to monitor land change. For this reason, our purpose is to identify the cloud detection algorithm best suited for the Amazon rainforest on Sentinel–2 images. To achieve this, we tested four cloud detection algorithms on Sentinel–2 images spread in five areas of the Amazonia. Using more than eight thousand validation points, we compared four cloud detection methods: Fmask 4, MAJA, Sen2Cor, and s2cloudless. Our results point out that FMask 4 has the best overall accuracy on images of the Amazon region (90%), followed by Sen2Cor’s (79%), MAJA (69%), and S2cloudless (52%). We note the choice of method depends on the intended use. Since MAJA reduces the number of false positives by design, users that aim to improve the producer’s accuracy should consider its use.

Biomass burning (BB) emissions negatively impact the biosphere and human lives. Orbital remote sensing and modelling are used to estimate BB emissions on regional to global scales, but these estimates are subject to errors related to the parameters, data, and methods available. For example, emission factors (mass emitted by species during BB per mass of dry matter burned) are based on land use and land cover (LULC) classifications that vary considerably across products. In this work, we evaluate how BB emissions vary in the PREP-CHEM-SRC emission estimator tool (version 1.8.3) when it is run with original LULC data from MDC12Q1 (collection 5.1) and newer LULC data from MapBiomas (collection 6.0). We compare the results using both datasets in the Brazilian Amazon and Cerrado biomes during the 2002–2020 time series. A major reallocation of emissions occurs within Brazil when using the MapBiomas product, with emissions decreasing by 788 Gg (−1.91% year−1) in the Amazon and emissions increasing by 371 Gg (2.44% year−1) in the Cerrado. The differences identified are mostly associated with the better capture of the deforestation process in the Amazon and forest formations in Northern Cerrado with the MapBiomas product, as emissions in forest-related LULCs decreased by 5260 Gg in the Amazon biome and increased by 1676 Gg in the Cerrado biome. This is an important improvement to PREP-CHEM-SRC, which could be considered the tool to build South America’s official BB emission inventory and to provide a basis for setting emission reduction targets and assessing the effectiveness of mitigation strategies.

Aircraft atmospheric profiling is a valuable technique for determining greenhouse gas fluxes at regional scales (104–106 km2). Here, we describe a new, simple method for estimating the surface influence of air samples that uses backward trajectories based on the Lagrangian model Hybrid Single-Particle Lagrangian Integrated Trajectory Model (HYSPLIT). We determined “regions of influence” on a quarterly basis between 2010 and 2018 for four aircraft vertical profile sites: SAN and ALF in the eastern Amazon, and RBA and TAB or TEF in the western Amazon. We evaluated regions of influence in terms of their relative sensitivity to areas inside and outside the Amazon and their total area inside the Amazon. Regions of influence varied by quarter and less so by year. In the first and fourth quarters, the contribution of the region of influence inside the Amazon was 83–93% for all sites, while in the second and third quarters, it was 57–75%. The interquarter differences are more evident in the eastern than in the western Amazon. Our analysis indicates that atmospheric profiles from the western sites are sensitive to 42–52.2% of the Amazon. In contrast, eastern Amazon sites are sensitive to only 10.9–25.3%. These results may help to spatially resolve the response of greenhouse gas emissions to climate variability over Amazon.

This paper presents a dataset of yearly land use and land cover classification maps for Mato Grosso State, Brazil, from 2001 to 2017. Mato Grosso is one of the world’s fast moving agricultural frontiers. To ensure multi-year compatibility, the work uses MODIS sensor analysis-ready products and an innovative method that applies machine learning techniques to classify satellite image time series. The maps provide information about crop and pasture expansion over natural vegetation, as well as spatially explicit estimates of increases in agricultural productivity and trade-offs between crop and pasture expansion. Therefore, the dataset provides new and relevant information to understand the impact of environmental policies on the expansion of tropical agriculture in Brazil. Using such results, researchers can make informed assessments of the interplay between production and protection within Amazon, Cerrado, and Pantanal biomes. Measurement(s) land • land use Technology Type(s) computational modeling technique Factor Type(s) year • geographic location • land use and cover class Sample Characteristic - Environment land Sample Characteristic - Location Mato Grosso State Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.11440461

Land use and land cover (LULC) mapping initiatives are essential to support decision making related to the implementation of different policies. There is a need for timely and accurate LULC maps. However, building them is challenging. LULC changes affect natural areas and local biodiversity. When they cause landscape fragmentation, the mapping and monitoring of changes are affected. Due to this situation, improving the efforts for LULC mapping and monitoring in fragmented biomes and ecosystems is crucial, and the adequate separability of classes is a key factor in this process. We believe that combining multidimensional Earth observation (EO) data cubes and spectral vegetation indices (VIs) derived from the red edge, near-infrared, and shortwave infrared bands provided by the Sentinel-2/MultiSpectral Instrument (S2/MSI) mission reduces uncertainties in area estimation, leading toward more automated mappings. Here, we present a low-cost semi-automated classification scheme created to identify croplands, pasturelands, natural grasslands, and shrublands from EO data cubes and the Surface Reflectance to Vegetation Indexes (sr2vgi) tool to automate spectral index calculation, with both produced in the scope of the Brazil Data Cube (BDC) project. We used this combination of data and tools to improve LULC mapping in the Brazilian Cerrado biome during the 2018–2019 crop season. The overall accuracy (OA) of our results is 88%, indicating the potential of the proposed approach to provide timely and accurate LULC mapping from the detection of different vegetation patterns in time series.