Brazil's Rural Environmental Registry (CAR), established in 2012 under the Forest Code, is a mandatory environmental cadastral system based on self-declaration of property boundaries that plays a central role in environmental enforcement, rural credit allocation, and land-use monitoring. This study develops and applies a hierarchical conflict-resolution framework to systematically identify which portions of the CAR are procedurally reliable and analytically usable for deforestation attribution and regulatory enforcement. We analyzed 310,657 CAR registrations recorded in 2025 in Piaui, Brazil, integrating them with official tenure datasets through a sequence of hierarchical rules for the Cerrado-Caatinga transition, one of the most active agribusiness frontiers. The reconstructed tenure map, derived from the hierarchical framework representing the accumulated state of all property registrations and boundary rectifications, was applied to attribute deforestation recorded between 2013 and 2023. The primary findings indicate that intra-CAR spatial overlaps were detected nearly one-third of the registered area, with boundary conflicts concentrated among larger properties along the Cerrado agribusiness frontier. In terms of deforestation, 94.20% of vegetation loss (1236,100 ha) can be attributable to identifiable actors, of which 86.60% is associated with private properties registered in CAR and official tenure datasets. The top 1% of properties ranked by cumulative deforestation account for 71.50% of total vegetation loss between 2013 and 2023, indicating a pronounced concentration of clearing among a numerically small set of landowners. Of the deforestation associated with private properties, 73.40% is classified as illegal under the Forest Code mandates applied in this analysis, with Legal Forest Reserve deficit violations representing the dominant source of non-compliance. Although over 13 million ha of native vegetation remains on private lands, Legal Reserve deficits are concentrated among large properties in the Cerrado biome, while small properties show the largest number of individual deficit records. These results demonstrate that a hierarchical analytical framework can extract procedurally reliable information from a self-declared registry, providing a scalable basis for spatially targeted enforcement, deforestation attribution, and Forest Code compliance monitoring at the subnational level.

The openEO initiative provides a standardized interface for Earth Observation (EO) analytics, enabling workflows to be executed across different computational backends. Although openEO supports multiple client languages, integrating R-based analytical methods in cloud environments remains limited. Existing solutions, such as OpenEOcubes, offer partial support but do not provide a general mechanism for exposing the broader range of geospatial, statistical, and machine learning tools available in R as openEO processes. This paper presents OpenEOcraft, a framework that integrates R-based EO workflows into the openEO ecosystem through a three-layer design comprising an execution engine, a process translation layer, and a RESTful API. The framework allows analytical functions from established R libraries to be made available as openEO-compliant processes with limited development effort. Two use cases illustrate its capabilities: time-series-based land cover classification and machine learning model reuse supported by its metadata, both of which are reproducible across R, Python, and the openEO Web Editor. OpenEOcraft extends the range of R methods available in openEO and supports reproducible EO analytics across heterogeneous clients.

A key component of remote-sensing image analysis is image classification, which aims to categorize images into different classes using machine-learning methods. In many applications, machine-learning classifiers assign class probabilities to each pixel. These class probabilities serve as input for post-processing techniques that aim to improve the results of machine-learning algorithms. This paper proposes a new post-processing algorithm based on an empirical Bayes approach. We employ non-isotropic neighborhood definitions to capture the impact of borders between land classes in the statistical model. By incorporating expert knowledge, the algorithm improves the consistency of the classified map. This technique has proven its efficacy for large-scale data processing using image time-series analysis. The proposed method is a key component of a time-first, space-based approach for big Earth-observation data processing. It is available as open source as part of the R package sits.

This study examines how land tenure constrains Brazil’s ability to meet its deforestation control and forest restoration goals in its Amazonia biome. Our findings are based on an updated assessment of land tenure and land use in the region. Between 2019 and 2021, 44% of deforestation in Amazonia occurred in private lands, while forest removal in settlements ranged from 31% to 27% of the total. Deforestation in undesignated public lands increased from 11% in 2008 to 18% in 2021. Deforestation is highly concentrated, with 1% of properties accounting for 82.5% of forest cuts in 2021. In Amazonia, there is considerable non-compliance with the legal reserve provisions set by Brazil’s Forest Code. Legal reserve deficits in private lands sum up to 18.17 Mha (million hectares), compared with 12.49 Mha of legal reserve surpluses. Even if all forest surpluses are offered in the forest credits market set in the Forest Code, farmers still need to restore 5.67 Mha to comply with the law. Large-scale cattle ranchers have a legal reserve deficit of 10.35 Mha (34% of their area). Most crop farming occurs in medium and large properties (4.63 Mha) with a large proportion of legal reserve deficits (45%). Given the political power and financial resources of large ranchers and crop producers, Brazil faces major challenges in inducing these farmers to meet their legal obligations. Therefore, Brazil needs to combine robust command-and-control strategies with market-based policies to achieve its deforestation and forest restoration goals. The government should tailor forest protection and restoration policies to the needs of different landowners, considering their land use practices, technical capacity, and financial resources.

Segmentation methods are a valuable tool for exploring spatial data by identifying objects based on images' features. However, proper segmentation assessment is critical for obtaining high-quality results and running well-tuned segmentation algorithms Usually, various metrics are used to inform different types of errors that dominate the results. We describe a new R package, segmetric, for assessing and analyzing the geospatial segmentation of satellite images. This package unifies code and knowledge spread across different software implementations and research papers to provide a variety of supervised segmentation metrics available in the literature. It also allows users to create their own metrics to evaluate the accuracy of segmented objects based on reference polygons. We hope this package helps to fulfill some of the needs of the R community that works with Earth Observation data.

In Brazil, conservation priority zones, in spite of their key role in preserving natural vegetation and its environmental resources are frequently located outside the country’s public network of protected areas (PAs). Here we present the first study on land-use impacts inside Brazil’s unprotected (i.e. outside PAs) Cost-Effective conservation priority Zones (CEZs), for the period 2020–2050. CEZs are conservation priority zones that had experienced low levels of human impact in 2020. In this study, we consider various governance scenarios, including different deforestation control and native vegetation restoration policies. To this end, a land-use change model is combined with a downscaling method to generate natural vegetation cover projections at a 0.01 ∘ resolution. Results, which include the effects of climate change on the expansion of the Brazilian agriculture, project native vegetation losses (through deforestation) or gains (through restoration) inside unprotected CEZs. If the current pattern of disregard for the environment persists, our results indicate that a large share of the native vegetation inside Brazil’s CEZs is likely to disappear, with negative impacts on biodiversity preservation, green-house gas emissions and ecosystem services in general. Moreover, even if fully implemented and enforced, Brazil’s current Forest Code is insufficient to adequately protect CEZs from anthropization, especially in the Cerrado biome. We expect that this study can help improving the conservation and restoration of CEZs in Brazil.

In its Nationally Determined Contribution (NDC) to the United Nations Framework Convention on Climate Change, Brazil committed to reducing greenhouse gas emissions and restoring its forests. This study examines the challenges of fulfilling these commitments in Brazilian Amazonia. We carry out a detailed assessment of the current status of land tenure in the region and its relation to deforestation. After dealing with conflicts and overlaps between data from various sources, we produce a new map of public and private land tenure in Amazonia. Combining this map with Brazil's official data on deforestation, we find out how much natural vegetation has been preserved in each public or private area. The result is used to estimate how much deforestation is illegal. We also establish how much deforestation is associated with each land tenure type. Our results show that most deforestation inside rural properties is done by a few landowners, a finding that has important consequences for law enforcement. We then assess the challenges for reforestation in detail. To do so, we consider how much forest needs to be rehabilitated according to Brazil's Forest Code. Our analysis provides a comprehensive appraisal of the potential opportunity costs for forest restoration in the biome, considering farm size and land use. This analysis provides insights into targeted land use policies that can meet Brazil’s forest restoration goals.

Information on land use and land cover (LULC) is essential to support governments in making decisions about the impact of human activities on the environment, planning the use of natural resources, conserving biodiversity, and monitoring climate change. Nowadays, different initiatives systematically produce information on LULC dynamics, on global, national, and regional scales. Examples of open and global LULC data products are Global Land-cover Classification with a Fine Classification System, Copernicus Global Land Service, and Global Land Cover by European Space Agency (ESA). At the national and regional level in Brazil, we can cite the data sets produced by PRODES, TerraClass, MapBiomas, and IBGE. Although these initiatives provide rich collections of open LULC maps, there is still a gap in tools that facilitate the integration of these data sets. The integrated analysis of these collections requires considerable effort by researchers who have to download, organize and harmonize them in their local computers, facing with different spatiotemporal resolutions and classification systems containing distinct class numbers, names and meanings. Besides that, these collections are distributed in different data formats through files or web services. To minimize these efforts, we propose a platform that allows users to access LULC collections from distinct sources, map their distinct classification systems, and retrieve LULC trajectories associated with spatial locations by integrating these collections. Besides the platform architecture description, this paper presents a case study that demonstrates its use in the integration and analysis.

The development of analytical software for big Earth observation data faces several challenges. Designers need to balance between conflicting factors. Solutions that are efficient for specific hardware architectures can not be used in other environments. Packages that work on generic hardware and open standards will not have the same performance as dedicated solutions. Software that assumes that its users are computer programmers are flexible but may be difficult to learn for a wide audience. This paper describes sits, an open-source R package for satellite image time series analysis using machine learning. To allow experts to use satellite imagery to the fullest extent, sits adopts a time-first, space-later approach. It supports the complete cycle of data analysis for land classification. Its API provides a simple but powerful set of functions. The software works in different cloud computing environments. Satellite image time series are input to machine learning classifiers, and the results are post-processed using spatial smoothing. Since machine learning methods need accurate training data, sits includes methods for quality assessment of training samples. The software also provides methods for validation and accuracy measurement. The package thus comprises a production environment for big EO data analysis. We show that this approach produces high accuracy for land use and land cover maps through a case study in the Cerrado biome, one of the world's fast moving agricultural frontiers for the year 2018.

Every day, several Earth observation satellites produce images from around the world. Cloud computing is becoming the main location where all these satellite images are being stored and distributed. This document features an R-package that implements a SpatioTemporal Assets Catalog API client that allows querying and access to a growing set of global satellite imagery providers.

Methods for crop phenology detection using time series analysis have provided accurate information for large agricultural areas in shorter processing times, which can be useful for agronomic management and supply chain monitoring. Given the crop dynamics in the Brazilian Cerrado, with alternating crop type plantings, crop successions, and crop rotations, as well as climate and crop practices variation between harvest periods, these methods can be useful for detecting subtle land use and land cover changes at farm and crop field scales, improving thematic classifications and the near real-time crop monitoring. In this study, the Time-Weighted Dynamic Time Warping method was applied to recognize patterns in Moderate Resolution Imaging Spectroradiometer (MODIS) time series for land use and cover classification, identifying crop successions and rotations at crop field level in a large-scale agro-industrial agglomerate of farms located at Brazilian Cerrado. We detected and analyzed temporal cropping patterns in training samples to classify the MODIS time series and images, using a robust ground truth data set for validation. The method distinguished Cotton-fallow, Soybean-cotton, Soybean-maize, and Soybean-millet cropping patterns with an overall accuracy above 85% for all evaluated harvest periods. Seasonal variations in the crop fields, caused by interannual succession and rotation, were detected. The method demonstrated the benefit of creating a spatial vector data set for supporting decision-making in several crop management contexts, improving crop and supply chain monitoring.

In their recent study, Sanchez et al. compared various cloud detection methods applied to Sentinel-2, specifically on images acquired over the Amazonian region, known for its frequent cloud cover. Comparison of cloud screening methods for optical satellite images is a complex task, which must take several parameters into account, such as the definition of a cloud, which can differ according to the methods, the different coding of the cloud and shadow masks, the possible dilation of masks, and also the way the method must be used to perform in nominal conditions. We found that the otherwise serious and useful comparison of cloud masks by Sanchez et al. is not fair to the real performances of MAJA cloud detection, for two reasons: (i) two thirds of the images used in the comparison were acquired before the launch of Sentinel-2B satellite, when the revisit of the Sentinel-2 mission was 20 days instead of five days for the nominal conditions of the mission, and (ii) there is an error in the understanding of how MAJA cloud masks are coded which also probably artificially degraded the results of MAJA as compared to the other methods.

The extensive amount of Earth observation satellite images available brings opportunities and challenges for land mapping in global and regional scales. These large datasets have motivated the use of satellite image time series analysis coupled with machine learning techniques to produce land use and cover class maps. To be successful, these methods need good quality training samples, which are the most important factor for determining the accuracy of the results. For this reason, training samples need methods for quality control of class noise. In this paper, we propose a method to assess and improve the quality of satellite image time series training data. The method uses self-organizing maps (SOM) to produce clusters of time series and Bayesian inference to assess intra-cluster and inter-cluster similarity. Consistent samples of a class will be part of a neighborhood of clusters in the SOM map. Noisy samples will appear as outliers in the SOM. Using Bayesian inference in the SOM neighborhoods, we can infer which samples are noisy. To illustrate the methods, we present a case study in a large training set of land use and cover classes in the Cerrado biome, Brazil. The results prove that the method is efficient to reduce class noise and to assess the spatio-temporal variation of satellite image time series training samples.

The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with this vast amount of images, novel technologies have been proposed and developed based on cloud computing and big data systems. This paper describes the INPE's initiatives in using remote sensing images and cloud services of the Amazon Web Services (AWS) infrastructure to improve land use and cover monitoring.

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.

Currently, the overwhelming amount of Earth Observation data demands new solutions regarding processing and storage. To reduce the amount of time spent in searching, downloading and pre-processing data, the remote Sensing community is coming to an agreement on the minimum amount of corrections satellite images must convey in order to reach the broadest range of applications. Satellite imagery meeting such criteria (which usually include atmospheric, radiometric and topographic corrections) are generically called Analysis Ready Data (ARD). Furthermore, ARD is being assembled into multidimensional data cubes, minimising preprocessing tasks and allowing scientists and users in general to focus on analysis. A particular instance of this is the Brazil Data Cube (BDC) project, which is processing remote sensing images of medium spatial resolution into ARD datasets and assembling them as multidimensional cubes of the Brazilian territory. For example, BDC users are released from performing tasks such as image co-registration , aerosol interference correction. This work presents a BDC proof of concept, by analysing a BDC data cube made with images from the fourth China-Brazil Earth Resources Satellite (CBERS-4) of one of the largest biodiversity hotspot in the world, the Cerrado biome. It also shows how to map and monitor land use and land cover using the CBERS data cube. We demonstrate that the CBERS data cube is effective in resolving land use and and land cover issues to meet local and national needs related to the landscape dynamics, including deforestation, carbon emissions, and public policies.