Small dams and reservoirs disrupt hydrological connectivity and increase evaporative water loss across Brazil, yet most remain unmapped. Applying deep learning to Sentinel satellite data from 2021, we created a comprehensive map of 1.1 million small on-stream reservoirs (smaller than 50 ha). Their 7,597 km^2 cumulative surface area surpasses the combined area of Brazil’s three largest mega-dam impoundments. Especially concentrated in areas with high cattle herd densities and precipitation variability, 78% are found in headwater sub-basins, which are vital for downstream water quality and ecosystem health. The reservoirs lose an extra 4.2 km^3yr^-1 to surface evaporation—equivalent to 29% of total annual urban water use in Brazil. Our findings highlight the overlooked socio-environmental consequences of small reservoirs for land and water management.

The Amazon underwent a severe austral springtime drought attributed to the onset of El Ni & ntilde;o in 2023 and the warmer North Atlantic, Indian, and North Pacific Oceans. The Amazon rivers, lakes, small streams, wetlands, and reservoirs quickly lowered their water level below historical records due to decreased rainfall and warmth in the region. Based on satellite imagery, this study presents the first estimate of the water loss extent in the 4.2 million km2 of the Brazilian Amazon biome (similar to 62% of the Amazon total biome) in 2023. We estimated the loss of 3.3 million hectares of surface water relative to 2022, with an overall accuracy of 92%. The surface water losses were concentrated in the states of Amazonas (59.4%) and Par & aacute; (25.5), adding up to 2.8 million hectares. The warmer and drier climate in the region affected the main rivers in the Amazon. Among them, the Solim & otilde;es, Negro, Purus, Acre, and Branco suffered extreme drops in their levels in some regions, resulting in a high negative impact on the aquatic biodiversity, yet estimated only in local areas. A total of 1.14 million hectares of surface water loss (i.e. 35%) was detected within protected areas territories, affecting extractivist, indegenous, African-Brazilian, and fishing and traditional communities. Proximity analysis revealed that 75% of the 2023 surface water loss was within 25 km of small towns, 48% and 65.8% at 50 km from indigenous villages and urban areas, respectively. Our results reinforce people's vulnerability to climate change, anticipating a plausible adverse impact scenario in the Amazon region and urging solutions to adaptation and mitigation. Therefore, an integrated monitoring system based on climate and water dynamics from satellite and ground stations is necessary to improve understanding of the problem for timing response of climatic change negative impacts.

Forests play an important role in the Earth systems for carbon sequestration and climate change mitigation, yet they have been increasingly disturbed by deforestation and forest degradation at an unprecedented pace. The Brazilian Amazon, for instance, experienced a 140% rise in deforestation from 2012 to 2020, with a record loss of 13,200 km(2) between August 2020 and July 2021. Alarmingly, 87% of 2019 deforestation alerts occurred on private properties, with 61% in legally restricted areas. Existing deforestation monitoring systems, such as PRODES and the Global Forest Change dataset, use about 30m resolution satellite imagery, which is insufficient for operational validation at fine scales. The Deforestation Alert System by Imazon leverages highresolution PlanetScope data (3-4m) but faces challenges due to fewer spectral bands and variations in reflectance values across different satellite sensors and dates. As a result, current validation is based mainly on manual inspection which is highly timeconsuming. To address the challenges and automate the validation process, this work develops a system based on deep learning known for its ability to capture complex texture patterns in high-resolution images - to inspect and confirm new deforestation sites. Specifically, the system takes inputs from potential deforestation sites suggested by coarse-resolution products and uses a pair of PlanetScope images before and after the change at each site to determine new deforestation (excluding existing deforestation). Our results demonstrate that the new system achieves robust and high-quality accuracy under various test conditions.

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

por iniciativa da equipe da UFRPE, com participação de alunos e professores das demais associadas, vem realizando eventos temáticos.Tais eventos reúnem sínteses dos processos interdisciplinares decorrentes do diálogo entre as disciplinas, enriquecidos por momentos de reflexões sobre diferentes realidades que, ao integrarem teoria e prática, se materializam em imersões nos territórios pernambucanos.E é precisamente destes esforços coletivos de estudo e de diálogo com os sujeitos dos territórios que emergem os SEADET, que culminam ao final dos semestres letivos na socialização e aprofundamento de temas que são caros ao processo formativo do PPGADT, dada sua aderência à área de concentração e linhas de pesquisa do

The Brazilian Amazon land cover changes rapidly due to anthropogenic and climate drivers. Deforestation and forest disturbances associated with logging and fires, combined with extreme droughts, warmer air, and surface temperatures, have led to high tree mortality and harmful net carbon emissions in this region. Regional attempts to characterize land cover dynamics in this region focused on one or two anthropogenic drivers (i.e., deforestation and forest degradation). Land cover studies have also used a limited temporal scale (i.e., 10–15 years), focusing mainly on global and country-scale forest change. In this study, we propose a novel approach to characterize and measure land cover dynamics in the Amazon biome. First, we defined 10 fundamental land cover classes: forest, flooded forest, shrubland, natural grassland, pastureland, cropland, outcrop, bare and impervious, wetland, and water. Second, we mapped the land cover based on the compositional abundance of Landsat sub-pixel information that makes up these land cover classes: green vegetation (GV), non-photosynthetic vegetation, soil, and shade. Third, we processed all Landsat scenes with <50% cloud cover. Then, we applied a step-wise random forest machine learning algorithm and empirical decision rules to classify intra-annual and annual land cover classes between 1985 and 2022. Finally, we estimated the yearly land cover changes in forested and non-forested ecosystems and characterized the major change drivers. In 2022, forest covered 78.6% (331.9 Mha) of the Amazon biome, with 1.4% of secondary regrowth in more than 5 years. Total herbaceous covered 15.6% of the area, with the majority of pastureland (13.5%) and the remaining natural grassland. Water was the third largest land cover class with 2.4%, followed by cropland (1.2%) and shrubland (0.4%), with 89% overall accuracy. Most of the forest changes were driven by pasture and cropland conversion, and there are signs that climate change is the primary driver of the loss of aquatic ecosystems. Existing carbon emission models disregard the types of land cover changes presented in the studies. The twenty first century requires a more encompassing and integrated approach to monitoring anthropogenic and climate changes in the Amazon biome for better mitigation, adaptation, and conservation policies.

AbstractTropical forests are being disturbed by deforestation and forest degradation at an unprecedented pace (Hansen et al. in Science 342:850–853, 2013; Bullock et al. in Glob Change Biol 26:2956–2969, 2020). Deforestation completely removes the original forest cover and replaces it with another land cover type, such as pasture or agriculture fields. Generally speaking, forest degradation is a temporary or permanent disturbance, often caused by predatory logging, fires, or forest fragmentation, where the tree loss does not entirely change the land cover type. Forest degradation leads to a more complex environment with a mixture of vegetation, soil, tree trunks and branches, and fire ash. Defining a boundary between deforestation and forest degradation is not straightforward; at the time this chapter was written, there was no universally accepted definition for forest degradation (Aryal et al. in Remote Sens 13:2666, 2021). Furthermore, the signal of forest degradation often disappears within one to two years, making degraded forests spectrally similar to undisturbed forests. Due to these factors, detecting and mapping forest degradation with remotely sensed optical data is more challenging than mapping deforestation.

This study presents our efforts to automate the detection of unofficial roads (herein, roads) in the Brazilian Amazon using artificial intelligence (AI). In this region, roads are built by loggers, goldminers, and unauthorized land settlements from existing official roads, expanding over pristine forests and leading to new deforestation and fire hotspots. Previous research used visual interpretation, hand digitization, and vector editing techniques to create a thorough Amazon Road Dataset (ARD) from Landsat imagery. The ARD allowed assessment of the road dynamics and impacts on deforestation, landscape fragmentation, and fires and supported several scientific and societal applications. This research used the existing ARD to train and model a modified U-Net algorithm to detect rural roads in the Brazilian Amazon using Sentinel-2 imagery from 2020 in the Azure Planetary Computer platform. Moreover, we implemented a post-AI detection protocol to connect and vectorize the U-Net road detected to create a new ARD. We estimated the recall and precision accuracy using an independent ARD dataset, obtaining 65% and 71%, respectively. Visual interpretation of the road detected with the AI algorithm suggests that the accuracy is underestimated. The reference dataset does not include all roads that the AI algorithm can detect in the Sentinel-2 imagery. We found an astonishing footprint of roads in the Brazilian Legal Amazon, with 3.46 million km of roads mapped in 2020. Most roads are in private lands (~55%) and 25% are in open public lands under land grabbing pressure. The roads are also expanding over forested areas with 41% cut or within 10 km from the roads, leaving 59% of the 3.1 million km2 of the remaining original forest roadless. Our AI and post-AI models fully automated road detection in rural areas of the Brazilian Amazon, making it possible to operationalize road monitoring. We are using the AI road map to understand better rural roads’ impact on new deforestation, fires, and landscape fragmentation and to support societal and policy applications for forest conservation and regional planning.

Este capítulo examina las oportunidades y los enfoques sitio específicos para restaurar los sistemas terrestres y acuáticos, centrándose en las acciones locales y sus beneficios inmediatos. Las considera-ciones sobre el paisaje, la cuenca y el bioma se abordan en el Capítulo 29. Los enfoques de conserva-ción se abordan en el Capítulo 27.

Este capítulo discute as principais causas do desmatamento e da degradação florestal na Amazônia, especialmente a expansão agrícola, construção de estradas, exploração mineral e de petróleo e gás, queimadas, efeitos de borda, extração de madeira e caça. Também examina os impactos dessas atividades e das sinergias entre elas.

The fast retreat of the tropical Andean glaciers (TAGs) is considered an important indicator of climate change impact on the tropics, since the TAGs provide resources to highly vulnerable mountain populations. This study aims to reconstruct the glacier coverage of the TAGs, using Landsat time-series images from 1985 to 2020, by digitally processing and classifying satellite images in the Google Earth Engine platform. We used annual reductions of the Normalized Difference Snow Index (NDSI) and spectral bands to capture the pixels with minimum snow cover. We also implemented temporal and spatial filters to have comparable maps at a multitemporal level and reduce noise and temporal inconsistencies. The results of the multitemporal analysis of this study confirm the recent and dramatic recession of the TAGs in the last three decades, in base to physical and statistical significance. The TAGs reduced from 2429.38 km2 to 1409.11 km2 between 1990 and 2020, representing a loss of 42% of the total glacier area. In addition, the time-series analysis showed more significant losses at altitudes below 5000 masl, and differentiated changes by slope, latitude, and longitude. We found a more significant percentage loss of glacier areas in countries with less coverage. The multiannual validation showed accuracy values of 92.81%, 96.32%, 90.32%, 97.56%, and 88.54% for the metrics F1 score, accuracy, kappa, precision, and recall, respectively. The results are an essential contribution to understanding the TAGs and guiding policies to mitigate climate change and the potential negative impact of freshwater shortage on the inhabitants and food production in the Andean region.

Land cover maps are essential for characterizing the biophysical properties of the Earth’s land areas. Because land cover information synthesizes a rich array of information related to both the ecological condition of land areas and their exploitation by humans, they are widely used for basic and applied research that requires information related to land surface properties (e.g., terrestrial carbon models, water balance models, weather, and climate models) and are core inputs to models and analyses used by natural resource scientists and land managers. As the Earth’s global population has grown over the last several decades rates of land cover change have increased dramatically, with enormous impacts on ecosystem services (e.g., biodiversity, water supply, carbon sequestration, etc.). Hence, accurate information related to land cover is essential for both managing natural resources and for understanding society’s ecological, biophysical, and resource management footprint. To address the need for high-quality land cover information we are using the global record of Landsat observations to compile annual maps of global land cover from 2001 to 2020 at 30 m spatial resolution. To create these maps we use features derived from time series of Landsat imagery in combination with ancillary geospatial data and a large database of training sites to classify land cover at annual time step. The algorithm that we apply uses temporal segmentation to identify periods with stable land cover that are separated by breakpoints in the time series. Here we provide an overview of the methods and data sets we are using to create global maps of land cover. We describe the algorithms used to create these maps and the core land cover data sets that we are creating through this effort, and we summarize our approach to accuracy assessment. We also present a synthesis of early results and discuss the strengths and weaknesses of our early map products and the challenges that we have encountered in creating global land cover data sets from Landsat. Initial accuracy assessment for North America shows good overall accuracy (77.0 ± 2.0% correctly classified) and 79.8% agreement with the European Space Agency (ESA) WorldCover product. The land cover mapping results we report provide the foundation for robust, repeatable, and accurate mapping of global land cover and land cover change across multiple decades at 30 m spatial resolution from Landsat.

La restauración se puede aplicar en muchos contextos amazónicos diferentes, pero será más eficaz para aprovechar los beneficios ambientales y sociales cuando se priorice en toda la cuenca Amazónica y dentro de los paisajes y cuencas. Aquí describimos las consideraciones que son más relevantes para planificar y escalar la restauración.

As atividades humanas destroem a biodiversidade e perturbam o funcionamento dos ecossistemas aquáticos e terrestres em diferentes níveis. Este capítulo apresenta abordagens sustentáveis para lidar com algumas das maiores ameaças à biodiversidade e aos ecossistemas da Amazônia, ou seja, o desmatamento, o represamento de rios, a exploração de minérios, a caça, o comércio ilegal, a produção e tráfico de drogas, a extração ilegal de madeira, a pesca predatória e a expansão da infraestrutura. O papel da restauração é abordado nos Capítulos 28 e 29.

The Brazilian Amazon biome is undergoing a fast land cover change in the past 50 years. Most of these changes are associated with deforestation and forest disturbance caused by selective logging and fires, and recently to extreme climate change events. Deforestation monitoring from the INPE (National Institute for Space Research), based on Earth Observation (EO) sensors, is in place since the late 1980s. After 2000, new deforestation monitoring systems emerged driven by lower computational costs and free EO data, notably Landsat. The advent of the Google Earth Engine platform has broadened monitoring initiatives in the Amazon, allowing monitoring to expand beyond forest clearing by deforestation. Here, we present our efforts to develop and the results of annual multi-decadal land use and land cover (LULC) change for the Brazilian Amazon biome between 1985 to 2019. We processed 74,000 Landsat scenes available for this period with Cloud Cover less or equal to 50%, covering 201 path-rows. We then trained and validated a random forest classifier (RFC) using 35,000 independent random samples (10,000 for training and calibration and 25,000 accuracy assessment) for the entire Amazon biome generated by the LAPIGUFG research team. The input features were selected with the random forest package available in R Language because Google Earth Engine does not have specialized statistical libraries. The final feature space ended up with eight variables derived from a Spectral Mixture Analysis (SMA) model, including Green Vegetation (GV), Non-Photosynthetic Vegetation (NPV), Soil, Cloud, Green Vegetation Shade (GVS), Normalized Difference Fraction Index (NDFI), Shade and Canopy Shade Fraction (CSFI). The LULC classes included: Forest, Savanna, Grassland, Pasture, Agriculture, Water, and Non-Vegetated Area. Annual LULC maps were produced based on intra-annual post-classification rules applied to all available scenes in a given year. The SMA model fractional outputs were also used to map surface water and forest disturbances based on empirically defined thresholds, already tested and published in the scientific literature. Annual maps of surface water and forest disturbances were combined with the LULC yearly maps. Additionally, we estimated the extent of secondary vegetation (SV) based on pasture and agricultural transitions to forests. As the final step, we integrated annual LULC maps with forest disturbance, SV, and surface water maps to produce the most comprehensive land change information about the Amazon biome since 1985. The LULC final maps and intermediate map products are available in the MapBiomas platform, allowing multiple scientific and societal applications. As further steps, we will investigate our LULC maps' applications to improve deforestation and climate change risks and carbon emission modeling for the Amazon biome.

Human activities destroy biodiversity and disrupt the functioning of aquatic and terrestrial ecosystems at different levels. This chapter provides sustainable approaches to address some of the biggest threats to the Amazon’s biodiversity and ecosystems, i.e., deforestation, damming of rivers, mining, hunting, illegal trade, drug, production and trafficking, illegal logging, overfishing, and infrastructure expansion. The role of restoration is addressed in chapters 28 and 29.