Gilberto Câmara

Implements the Simple Non-Iterative Clustering algorithm for superpixel segmentation of multi-band images, as introduced by Achanta and Susstrunk (2017) . Supports both standard image arrays and geospatial raster objects, with a design that can be extended to other spatial data frameworks. The algorithm groups adjacent pixels into compact, coherent regions based on spectral similarity and spatial proximity. A high-performance implementation supports images with arbitrary spectral bands.

Earth Observation (EO) data are widely used in agricultural statistics production. However, the accuracy of EO-based land use classification is limited because of the limitations of using in situ census or survey data as training sets for EO applications. In this work, we provide recommendations for National Statistical Offices (NSO) to design in situ data collection campaigns that benefit both conventional statistics and EO-based assessments. Our recommendations are supported by a case study done by Chile's NSO (Instituto Nacional de Estadistica). The case study describes two methods for quality control of training samples used in EO image classification for agricultural statistics. The study describes methods for improving training samples for EO-based machine learning classification, which combines self-organised maps (SOM) with the sample balancing method SMOTE. Using the proposed method, the accuracy of the classification model increased from 95.2% to 98.5%, while the F1-scores for most classes also saw substantial improvements. The results suggest that combining multisensor EO data and advanced machine learning should be the focus of future research to enhance complex agricultural landscape classification.

What factors have been most important for protecting the two-thirds of tropical forests that remain standing? Qualitative factors like politics and governance are challenging to assess using existing statistical methods. To address this gap, we conducted a Delphi study with 36 experts to identify factors that contributed to forest protection in the Brazilian Amazon and Indonesia. Our results unpacked the complex dynamics affecting forest protection in both regions and highlighted the importance of political will, advocacy by civil society, and intergovernmental diplomacy, as well as shifts in factors' importance over time. Our analysis in Brazil emphasised the central importance of the state, while our findings in Indonesia revealed a complex and evolving mix of public, private and civil society factors. These results shed new light on the critical intersections of international advocacy and local policy contexts to generate enabling conditions for conservation.

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.

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.

A Contribuição Nacionalmente Determinada (NDC) brasileira estabeleceu metas ambiciosas de redução de emissões de gases de efeito estufa. Este artigo avalia os desafios para cumprimento da NDC na redução do desmatamento e restauração florestal no bioma Amazônia. O diagnóstico inédito considera a extensão do desmatamento ilegal e os déficits e excedentes de reserva legal por tamanho de propriedade e tipo de uso da terra.

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.

Meeting Brazil’s ambitious national commitments on both climate change mitigation and biodiversity conservation depends on securing its reserves of forest carbon and biodiversity. Brazil’s ‘Forest Code’ is a key tool to reconcile environmental preservation and agricultural production; it limits deforestation and requires forest restoration in illegally deforested areas. However, not all provisions of the law’s 2012 revision have yet been implemented and some are facing new challenges. Using modelled land use change projections for the whole of the country, we show that full implementation and enforcement of the law has the potential to contribute to conserving biodiversity. Biodiversity outcomes will be especially positive if (i) deforested areas are restored in ways that support recolonization by native species and (ii) additional measures are implemented to protect native vegetation in areas like Caatinga dry forests and Cerrado savannas, which may experience added pressure displaced from other regions by Forest Code implementation.

In their comments about our paper, the authors remark on two issues regarding our results relating to the MACCS-ATCOR Joint Algorithm (MAJA). The first relates to the sub-optimal performance of this algorithm under the conditions of our tests, while the second corresponds to an error in our interpretation of MAJA’s bit mask. To answer the first issue, we acknowledge MAJA’s capacity to improve its performance as the number of images increases with time. However, in our paper, we used the images we had available at the time we wrote our paper. Regarding the second issue, we misread the MAJA’s bit mask and mistakenly labelled shadows as clouds. We regret our error and here we present the updated tables and images. We corrected our estimation and, consequently, there is an increment in MAJA’s accuracy in the detection of clouds and cloud shadows. However, these increments are not enough to change the conclusion of our original paper.