We examine the changing characteristics of drought and aridification in the drylands of Northeast Brazil (NEB), a region marked by significant vulnerability to water scarcity and climate extremes. Globally, drylands make up a substantial portion of developing countries, and South America’s drylands cover ∼31% of the continent, with NEB representing one of the most densely populated semi-arid regions. The review distinguishes between aridity, a persistent climatic state defined by low precipitation and high evaporative demand, and drought, an episodic event characterized by prolonged below-normal water availability. Both phenomena drive agroecological patterns, affecting plant physiology, structure, diversity, and ecosystem functioning. Recent climate shifts and unsustainable human activities are pushing the boundaries of arid and semi-arid zones beyond their traditional limits, raising concerns about the expansion of desertification and intensified water scarcity. Drought events in Brazil have increased in frequency and severity, especially in NEB, with impacts exacerbated by concurrent climate stressors such as heatwaves. Vegetation responses in NEB indicate worsening water limitation, with consequences for agroecosystem resilience and productivity. This review highlights the urgent need for integrated strategies to address both drought and aridification in the NEB, given their expanding influence under climate change and their profound effects on societal and agroecological systems.

This study aims to evaluate an automated approach for mapping areas affected by land use and land cover change using Sentinel-1 SAR imagery time series and machine learning models trained through a novel pseudo-labeling framework. The proposed framework automatically identifies reliable pseudo-labeled samples for training classifiers and represents an evolution of a previously proposed strategy developed for the same purpose. Different algorithms and attribute configurations were tested to automate the distinction between stable areas and regions subject to spatiotemporal changes. Two case studies were conducted in regions with distinct characteristics, located in Novo Progresso (Brazil) and Istanbul (Turkey), allowing a broad evaluation of the proposed method. The results indicate that the choice of classifier, the configuration of attributes, and regional characteristics influence the mapping performance. In Novo Progresso, the best results were obtained with SVM-Linear (kappa: 0.749; F1-Score: 0.842), followed by RF and RBFNet, while AdaBoost performed the worst. In Istanbul, RBFNet demonstrated higher accuracy (kappa: 0.759; F1-score: 0.852), confirming the effectiveness of the approach in detecting changes across different contexts.

Accurate detection of land-cover changes is crucial for environmental conservation and sustainable land management. This study proposes a fully unsupervised change detection model based on pseudo-labels, applied to multitemporal satellite imagery. The model was tested in two regions of the Brazilian Amazon, one predominantly forested area with minimal agricultural activity, and another with extensive agricultural practices and dynamic land-use changes.Using spectral indices and an optimized thresholding process,the model's performance was compared to the Wavelet Energy Correlation Screening (WECS) method.The proposed model significantly outperformed WECS in both areas. The results demonstrate the model's robustness and adaptability, achieving accuracy values of up to 80% across various environmental contexts. This makes it an effective tool for monitoring land-cover changes in the Amazon.

Land-use and land-cover change detection is critical for monitoring deforestation and urban expansion. In this study, we propose an unsupervised change detection approach that leverages multi-temporal satellite imagery combined with a classic machine learning algorithm trained on automatically generated pseudo-labels. Four distinct study areas were analyzed: a tropical forest region in the Brazilian Amazon, an agricultural frontier in the Amazon, a Brazilian Savanna area undergoing transformation, and a rapidly expanding urban zone around the new Istanbul Airport, in Türkiye. The performance of the proposed approach was evaluated and compared with modern unsupervised change detection methods, including the Wavelet Energy Correlation Screening and the Temporal Convolutional Autoencoder methods. The results demonstrate that the proposed framework achieved consistently high accuracy across all four study areas, with F1-scores of approximately 0.92 in dense forest, 0.87 in an agricultural frontier, 0.91 in the savanna area, and 0.89 in an urban expansion zone. Overall, the model outperformed or matched the performance of the baseline methods, attesting to its adaptability and generalization capability in diverse environmental contexts worldwide.