The estimation of vegetation parameters, such as above-ground biomass, with high accuracy using remote sensing data, represents a promising approach. The present study develops models to estimate and map above-ground biomass of Mediterranean Quercus rotundifolia stands using one QuickBird satellite image in pan-sharpened mode, with four multispectral bands (blue, green, red and near infrared) and a spatial resolution of 0.70 m. The satellite image was orthorectified, geometrically and radiometrically corrected. Object-oriented classification methods and multi-resolution segmentation were used to derive a vegetation mask per forest species. Data from forest inventory (24 plots) and vegetation indices (NDVI, EVI, SR and SAVI) derived from high spatial resolution satellite images were used for an area of 133 km², in southern Portugal. The statistical analysis included correlation, variance analysis and linear regression. The linear regression models fitted included the arithmetic mean and the median values of the vegetation indices per inventory plot as explanatory variables. The overall results of the fitted models show a trend of better performance for those with the median value of the vegetation index as the explanatory variable. The best fitted model (R² = 75.3) was associated with the Simple Ratio (SR) median value as an explanatory variable. A Quercus rotundifolia above-ground biomass map was produced.

The advancement of technology associated with the field, especially the use of unmanned aerial vehicles (UAV) coupled with multispectral cameras, allows us to monitor the condition of crops in real time and contribute to the field of machine learning. The objective of this study was to estimate both productivity and above-ground biomass (AGB) for the corn crop by applying different vegetation indices (VIs) via high-resolution aerial imagery. Among the indices tested, strong correlations were obtained between productivity and the normalized difference vegetation index (NDVI) with a significance level of p < 0.05 (0.719), as well as for the normalized difference red edge (NDRE), or green normalized difference vegetation index (GNDVI) with crop productivity (p < 0.01), respectively 0.809 and 0.859. The AGB results align with those obtained previously; GNDVI and NDRE showed high correlations, but now with a significance level of p < 0.05 (0.758 and 0.695). Both GNDVI and NDRE indices showed coefficients of determination for productivity and AGB estimation with 0.738 and 0.654, and 0.701 and 0.632, respectively. The use of the GNDVI and NDRE indices shows excellent results for estimating productivity as well as AGB for the corn crop, both at the spatial and numerical levels. The possibility of predicting crop productivity is an essential tool for producers, since it allows them to make timely decisions to correct any deficit present in their agricultural plots, and further contributes to AI integration for drone digital optimization.

Climate—Madeira Strategy (CMS) foresees two models to describe the climate scenarios for the Madeira region in 2050 and 2070. These scenarios anticipate an average temperature rise of 1.4 to 3.7 °C and a decrease in precipitation by 30 to 40%. Consequently, Madeira’s agriculture will suffer the impacts of climate change. To understand these impacts, a baseline of major agrosystem components needs to be established, with the ultimate goal to monitor its consequences in its functioning. CASBio project used the 1961–1991 and 2010–2020 meteorological data series to modulate climate conditions and characterize and monitor six agrosystems for 2 years. One of them was a vineyard, Quinta das Vinhas, representing a typical agrosystem in the Mediterranean climate. The annual and seasonal variation in climatic parameters, soil conditions, microbiological communities, floristic and insect diversity, and crop production was assessed, using a total of 50 parameters. The results were used to establish a baseline of the agrosystem components and their seasonal and annual variation. The major findings are: (i) winter and summer extreme events show a trend in temperature and precipitation supporting a fast change in climate; (ii) a critical imbalance between nitrogen-fixing and denitrifying bacteria was identified, especially in summer, that could be determined by the rise in temperature and drought; (iii) among floristic diversity, the therophytes and geophytes confirm to be the most suitable indicators for the rise in temperature and reduction in precipitation in the agrosystems; (iv) an imbalance in favor of C. capitata plague was observed, associated with the summer rise in temperature and decrease in precipitation; (v) despite an increase in most of the grape varieties production, the Madeiran wine local varieties were shown to be less stable in productivity under observed climate conditions. The agrosystem baseline is a starting point for long-term monitoring and allows for further quantifying the influence of climate change on agrosystem productivity, resilience, and sustainability.

This study aimed to detect weeds in vineyards throughout the crop cycle using pixel-based classification of RGB imagery captured by unmanned aerial vehicles (UAVs). Five vegetation indices (NGRDI, NDVI, GLI, NDRE, and GNDVI) and three supervised classifiers (SVM, RT, and KNN) were evaluated during four flight campaigns. Classification performance was assessed using precision, recall, and F1-Score, supported by descriptive statistics (mean, standard deviation, and 95% confidence interval), inferential tests (Shapiro–Wilk, ANOVA, and Kruskal–Wallis), and visual map inspection. Statistical analyses, both descriptive and inferential, did not indicate significant differences between classification methods. NGRDI consistently showed strong performance, especially for vine and soil classes, and effectively detected weeds, with F1-Scores above 0.78 in some campaigns, occasionally outperforming the supervised classifiers. GLI displayed variable results and a higher sensitivity to noise, whereas NDVI showed limitations when applied to RGB data, particularly in sparsely vegetated areas. Among the classifiers, the SVM achieved the highest F1-Score for vine (0.9330) and soil (0.9231), whereas KNN produced balanced results and visually coherent maps. RT showed lower accuracy and greater variability, particularly in the weed class. Despite the lack of statistically significant differences, visual analysis favored NGRDI and SVM for generating cleaner classification outputs. Study limitations include lighting variability, reduced spatial coverage owing to low flight altitude, and a lack of spatial context in pixel-based methods. Future research should explore object-based approaches and advanced classifiers (e.g., Random Forest and Convolutional Neural Networks) to enhance robustness and generalization. Overall, RGB-based indices, particularly NGRDI, are cost-effective and reliable tools for weed detection, thereby supporting scalable precision in viticulture.

Drosophila suzukii is one of the main pests that attack soft-skinned fruits and cause significant economic damage worldwide. Madeira Island (Portugal) is already affected by this pest. The present work aimed to investigate the potential distribution of D. suzukii on Madeira Island to better understand the limits of its geographical distribution on the island using the Maximum Entropy modeling (MaxEnt). The resultant model provided by MaxEnt was rated as regular discrimination with the area under the curve (AUC, 0.7–0.8). Upon scrutinizing the environmental variables with the greatest impact on the distribution of D. suzukii, altitude emerged as the dominant contributor, with the highest percentage (71.2%). Additionally, elevations ranging from 0 to 500 m were identified as appropriate for the species distribution. With the results of the model, it becomes possible to understand/predict which locations will be most suitable for the establishment of the analyzed pest and could be further applied not only for D. suzukii but also for other species that hold the potential for substantial economic losses in this insular region.

Todos os dias os centros urbanos sofrem com o aumento da temperatura. Diante do aquecimento global, a degradação desses ambientes, traz riscos à saúde da população, desde o desconforto térmico até a ocorrência de doenças causadas pelo calor. Devido ao processo de urbanização, essa mudança na paisagem favorece a ocorrência do fenômeno da ilha de calor urbana (ICU), áreas urbanas com temperaturas mais elevadas que as áreas rurais vizinhas. Este fenômeno é realidade não em grandes municípios, mas também ocorre em cidades pequenas. O objetivo deste trabalho foi analisar a ocorrência de ICU em Ilha Solteira - SP, através do uso de dados de sensoriamento remoto, visando associar uma temperatura superficial com diferentes classes de uso e cobertura da terra. Para o propósito deste trabalho, utilizou-se uma imagem de satélite capturada na região do infravermelho (TIRS / Landsat-8) como classes de uso e ocupação do solo nas áreas de temperaturas mais altas, baseadas em imagens de alta resolução, no satélite Plêiades. Dado que as diferentes classes de uso e ocupação do solo influenciam diretamente a temperatura da superfície, observando-se a pavimentação asfáltica e o telhado cerâmico como valores mais altos de temperatura, nas áreas de ICU das pequenas cidades. Palavras-chave: Geotecnologia; Aquecimento Global; Infravermelho Termal.