In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available.

The Santa Catarina Southern Plateau is located in Southern Brazil and is a region that has gained considerable attention due to the rapid conversion of the typical landscape of natural grasslands and wetlands into agriculture, reforestation, pasture, and more recently, wind farms. This study’s main goal was to characterize the polarimetric attributes of the experimental quad-polarization acquisition mode of the Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR-2) for mapping seven land cover classes. The polarimetric attributes were evaluated alone and combined with SENTINEL-2A using a supervised classification method based on the Support Vector Machine (SVM) algorithm. The results showed that the intensity backscattering alone reached an overall classification accuracy of 37.48% and a Kappa index of 0.26. Interestingly, the addition of polarimetric features increased to 71.35% and 0.66, respectively. It shows that the use of polarimetric decomposition features was relatively efficient in discriminating land cover classes. SENTINEL-2A data alone performed better and achieved a weighted overall accuracy and Kappa index of 85.56% and 0.82. This increase was also significant for the Z-test. However, the addition of ALOS/PALSAR-2 derived features to SENTINEL-2A slightly improved accuracy and was marginally significant at a 95% confidence level only when all features were considered. Possible implications for that performance are the accumulated precipitation prior to SAR data acquisition, which coincides with the rainy season period. The experimental quad-polarization mode of ALOS/PALSAR- 2 shall be evaluated in the near future over different seasonal conditions to confirm results. Alternatively, further studies are then suggested by focusing on additional features derived from SAR data such as texture and interferometric coherence to increase classification accuracy. These measures would be an interesting data source for monitoring specific land cover classes such as the threatened grasslands and wetlands during periods of frequent cloud coverage. Future investigations could also address multitemporal approaches employing either single or multifrequency SAR.

A Agricultura de Precisão (AP) provê ferramenta útil para avaliação de risco agrícola em frutíferas e programação racional de suas práticas. Este trabalho objetivou avaliar o comportamento espacial do peso de frutos por planta (PP), número de frutos por planta (NF), peso médio de frutos por planta (PMF), em dois anos de observações, safras 2004 e 2005. A 'Fuji' foi selecionada em uma fazenda de produção comercial no Município de São Joaquim-SC. Os dados foram importados para o sistema de informação geográfica (SIG) SPRING, onde se efetuaram krigagens para a obtenção dos mapas de variabilidade espacial. Para a safra de 2005, ocorreu um período de estiagem que influenciou na produção, havendo uma redução nos valores médios de PP e NF em relação ao ano anterior. Já PMF apresentou um acréscimo. Em 2005, a variação dos valores de PP e NF demonstrou correlação inversa com o relevo. A análise geoestatística possibilitou modelar o comportamento espacial das variáveis analisadas na área experimental. O SIG utilizado mostrou-se satisfatório para as análises efetuadas.

O fenômeno denominado Ilhas de Calor começou a ser percebido após o século XIX devido às grandes mudanças nas interações do homem com a superfície. Estudos relacionados à climatologia foram aprimorados com o avanço geotecnológico, possibilitando a análise de diversas áreas através do uso de métodos variados. Dessa forma, o objetivo deste estudo consiste na identificação de ilhas de calor urbanas por meio de técnicas de sensoriamento remoto, em diferentes localidades do estado catarinense: Joinville, Criciúma e Lages. Para melhor compreensão das superfícies urbanas dessas cidades, utilizaram-se os seguintes índices radiométricos: Normalized Density Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI) e Built-up Index (BU), além da Temperatura da Superfície. Através da análise dos resultados obtidos, identificou-se que as ilhas de calor se formam em áreas que apresentam valores elevados de BU e reduzidos de NDVI. As ilhas formadas em Joinville e Criciúma ocorreram de forma semelhante, na porção central das cidades, devido à elevada densidade de elementos urbanísticos, enquanto na cidade de Lages, o fenômeno também se concentrou em fragmentos de solo exposto, afastados da malha urbana, devido ao predomínio da agricultura e silvicultura.

Precise estimates of dendrometric and morphometric variables are indispensable for effective forest resource conservation and sustainable utilization. This study focuses on modeling the relationships between shape (morphometric), dimension (dendrometric) and density (N) to assess the sustainability of forest resources. It sheds light on the current state of site characteristics, reproduction, and the structure of Araucaria angustifolia trees at selected forest remnants across multiple sites in Santa Catarina, Southern Brazil. Individual trees and their dendrometric variables, such as the diameter at breast height (d), height (h), crown base height (cbh), annual periodic increment (API) in growth rings, and morphometric variables, including four radii of the crown in cardinal directions, were evaluated. These measurements allowed us to calculate various morphometric indices and crown efficiency, enabling the assessment of both vertical and horizontal structural conditions. Statistical analysis confirmed a positive relationship of the crown volume (cv) and crown surface area (csa) with the crown length (cl). Conversely, the crown efficiency, density, increment rate, and reproductive structure production declined. These morphometric relationships emphasize the complex dynamics within these forest ecosystems, irrespective of the chosen site, indicating that horizontal and vertical forest structures have stagnated and have been characterized by limited change in the last ten years. Such results raise concerns about sustainability, highlighting the need for proper conservation measures and sustainable forest management practices. Our findings underscore the need for substantial adjustments in the structure and dynamics of the forest, particularly on selected rural properties where this tree species is abundant, to ensure long-term sustainability.