Precipitation estimation is a challenging task, especially in regions where its spatial distribution is irregular and highly variable. This study evaluated the spatial distribution of annual rainfall in a semiarid Brazilian basin under different regimes and its impact on land use and land cover dynamics. Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) records and observed data from 40 weather stations over a time series of 55 years were used, in addition to the Standardized Precipitation Index. Spatiotemporal analysis was carried out based on geostatistics. Remote sensing images were also interpreted for different rainfall regimes using the Normalized Difference Vegetation Index and Modified Normalized Difference Water Index. The Gaussian semivariogram model best represented the rainfall spatial structure, showing strong spatial dependence. Results indicated that rainfall amount in the basin significantly increases with elevation, as expected. There is high variation in the dynamics of water storage that can threaten water security in the region. Our findings point out that the application of geostatistics for mapping both the annual precipitation and the Standardized Precipitation Index provides a powerful framework to support hydrological analysis, as well as land use and land cover management in semiarid regions.

The Intergovernmental Panel on Climate Change (IPCC) has pointed out the high vulnerability of developing countries to climate change, which is expected to impact food and income security. Sheep farming is one of the main animal productions among the families located in the most vulnerable regions of the semiarid region of Pernambuco state, a Brazilian territory known for its high temperatures, low relative humidity, and high net solar radiation. Therefore, the objective of this study was to identify different regions of Pernambuco that may be more suitable for different breeds of sheep, based on non-parametric statistics and kriging maps of the temperature and humidity index (THI). THI values were determined based on mean annual temperature and wind speed extracted from the TerraClimate remote sensing database. Pernambuco state presented THI values ranging from 66 to 79, with the hair breeds having a high potential for exploitation in almost all territories, including the main meat-producing breeds. The East Friesian breed, a high milk producer, would be well suited to the Agreste mesoregion, a territory that, like the Pajeú and Moxotó microregions, also proved favorable for the introduction of three wool breeds (Suffolk, Poll Dorset, and Texel) known as major meat producers. The kriging maps of the THI values successfully allowed the identification of strategic development regions of Pernambuco state with high potential for sheep breeding.

Precision agriculture requires accurate methods for classifying crops and soil cover in agricultural production areas. The study aims to evaluate three machine learning-based classifiers to identify intercropped forage cactus cultivation in irrigated areas using Unmanned Aerial Vehicles (UAV). It conducted a comparative analysis between multispectral and visible Red-Green-Blue (RGB) sampling, followed by the efficiency analysis of Gaussian Mixture Model (GMM), K-Nearest Neighbors (KNN), and Random Forest (RF) algorithms. The classification targets included exposed soil, mulching soil cover, developed and undeveloped forage cactus, moringa, and gliricidia in the Brazilian semiarid. The results indicated that the KNN and RF algorithms outperformed other methods, showing no significant differences according to the kappa index for both Multispectral and RGB sample spaces. In contrast, the GMM showed lower performance, with kappa index values of 0.82 and 0.78, compared to RF 0.86 and 0.82, and KNN 0.86 and 0.82. The KNN and RF algorithms performed well, with individual accuracy rates above 85% for both sample spaces. Overall, the KNN algorithm demonstrated superiority for the RGB sample space, whereas the RF algorithm excelled for the multispectral sample space. Even with the better performance of multispectral images, machine learning algorithms applied to RGB samples produced promising results for crop classification.

The study aimed to characterize the spatial structure of variability of biophysical indexes of vegetation through images obtained by Unmanned Aerial Vehicles under strong heterogeneity and anisotropy, using geostatistical procedures. Plots with different types and densities of culture were evaluated in a didactic vegetable garden. Five vegetation indexes obtained from aerial multispectral camera images were evaluated parallel with geostatistical analysis and anisotropy investigation for multiscale spatial modeling. For the studied domain, geometric anisotropy was identified for the biometric indexes. The spherical model presented a better fit when anisotropy was not considered, whereas the exponential model had the best performance in the anisotropic analysis. Contrasting targets were better identified in multispectral images and considering anisotropy. The Soil-Adjusted Vegetation Index is recommended for similar applications.

This article presents a study on the spatiotemporal dynamics of land cover and use, vegetation indices, and water content in the semiarid region of Pernambuco, Brazil. This study is based on an analysis of satellite images from the years 2016, 2018, and 2019 using the MapBiomas platform. The results show changes in the predominant land cover classes over time, with an increase in the caatinga area and a decrease in the pasture area. An analysis of the vegetation indices (NDVI and LAI) indicated low vegetation cover and biomass in the study area, with a slight increase in the NDVI in 2018. An analysis of the Modified Normalized Difference Water Index (MNDWI) showed that the water content in the study area was generally low, with no significant variations over time. An increase in the water bodies, mainly due to the construction of a reservoir, was noted. The results of this study have provided important information for natural resource management in the region, including the development of strategies for the sustainable use and management of natural resources, particularly water resources, vegetation cover, and soil conservation.

ESTIMATIVA DA EVAPOTRANSPIRAÇÃO REAL E MAPEAMENTO DE ÁREAS CULTIVADAS EM UMA BACIA DO PROJETO DE INTEGRAÇÃO DO SÃO FRANCISCO (PISF), SEMIÁRIDO PERNAMBUCANO LIZANDRA DE BARROS DE SOUSA1; ABELARDO ANTÔNIO DE ASSUNÇÃO MONTENEGRO1; THIERES GEORGE FREIRE DA SILVA2; AILTON ALVES DE CARVALHO1 E MOISÉS ALVES DA SILVA NETO3 1 Departamento de Engenharia Agrícola (DEAGRI). Programa de Pós-Graduação em Engenharia Agrícola (PGEA). Universidade Federal Rural de Pernambuco (UFRPE). Rua Dom Manuel de Medeiros, S/N, Dois Irmãos, CEP: 52171-900, Recife/PE, Brasil. E-mail: lizandradebarros@gmail.com; montenegro.ufrpe@gmail.com; Ailtonalvesst@gmail.com. 2 Unidade Acadêmica de Serra Talhada (UAST). Universidade Federal Rural de Pernambuco (UFRPE). Avenida Gregório Ferraz Nogueira, S/N, José Tomé de Souza Ramos, CEP: 56909-535, Serra Talhada/PE, Brasil. E-mail: thigeoprofissional@hotmail.com. 3 Departamento de Engenharia Agrícola (DEAGRI). Universidade Federal Rural de Pernambuco (UFRPE). Rua Dom Manuel de Medeiros, S/N, Dois Irmãos, CEP: 52171-900, Recife/PE, Brasil. E-mail: moisesneto179@gmail.com. 1 RESUMO A região semiárida brasileira apresenta limitada disponibilidade de recursos hídricos, além disso, profundas alterações no uso e ocupação do solo estão previstas para ocorrer nas bacias hidrográficas de Pernambuco. Objetivou-se avaliar a evapotranspiração real e mapear áreas cultivadas por meio de sensoriamento remoto, utilizando, respectivamente, os modelos SAFER (Simple Algorithm for Evapotranspiration Retrieving) e SUREAL (Surface Resistance Algorithm), na Bacia do rio Terra Nova, em trecho perenizado. Imagens do satélite Landsat-8, de 2015 a 2020, foram selecionadas. Calculou-se: Índice de Vegetação da Diferença Normalizada (NDVI), albedo, temperatura de superfície, evapotranspiração de referência e evapotranspiração real. As imagens foram processadas no Google Earth Engine (GEE) e no software QGIS 3.16. Notou-se aumento no índice de cobertura vegetal. Regiões com maiores valores de evapotranspiração real estão ligadas àquelas com temperaturas mais baixas. Observou-se uma menor quantidade de áreas cultivadas no trecho do Rio Terra Nova nas imagens de 2015. Verificou-se o aumento da agricultura na região às margens desse rio, em seu trecho perenizado, de 29,5; 15,2; 7,7; 7,6; e 12,9 km² em 18/07/2016, 22/06/2018, 28/10/2018, 13/11/2018, e 20/12/2020, respectivamente. Além da intensidade de precipitação, a liberação das águas do PISF pode ter contribuído para o aumento de áreas irrigadas na região. Palavras-chave: sensoriamento remoto, agricultura irrigada, SAFER, SUREAL. SOUSA, L. B.; MONTENEGRO, A. A. A.; SILVA, T. G. F.; CARVALHO, A. A.; SILVA NETO, M. A. ESTIMATION OF ACTUAL EVAPOTRANSPIRATION AND MAPPING OF CULTIVATED AREAS IN A BASIN OF THE SÃO FRANCISCO INTEGRATION PROJECT (PISF), SEMIARID OF PERNAMBUCO STATE 2 ABSTRACT The Brazilian semi-arid region has limited availability of water resources, in addition, profound changes in land use and occupation are expected to occur in the river basins of Pernambuco. The objective was to evaluate the actual evapotranspiration and to map cultivated areas through remote sensing, using, respectively, the SAFER (Simple Algorithm for Evapotranspiration Retrieving) and SUREAL (Surface Resistance Algorithm) models, in the Terra Nova River Basin, in a perennial stretch. Landsat-8 satellite images from 2015 to 2020 were selected. The Normalized Difference Vegetation Index (NDVI), albedo, surface temperature, reference evapotranspiration, and actual evapotranspiration were calculated. Images were processed using the Google Earth Engine (GEE) platform and QGIS 3.16 software. There was an increase in the vegetation cover index. Regions with higher actual evapotranspiration values ​​are linked to those with lower temperatures. It was observed a smaller number of cultivated areas in the Terra Nova River stretch in the 2015 images. Also, it was verified an increase in agriculture in the riverside region along this, in its perennial stretch, of 29.5; 15.2; 7.7; 7.6; and 12.9 km² on 07/18/2016, 06/22/2018, 10/28/2018, 11/13/2018, and 12/20/2020, respectively. In addition to the intensity of precipitation, the release of PISF waters may have contributed to the increase in irrigated areas in the region. Keywords: remote sensing, irrigated agriculture, SAFER, SUREAL.