The dry forests of northern Peru, in the regions of Piura, Tumbes, Lambayeque, and La Libertad, have experienced significant changes as a result of deforestation and changes in land use, leading to the loss of biodiversity and resources. This work analyzed for the first time the changes in vegetation cover and land use of the Pómac Forest Historical Sanctuary (PFHS), located in the department of Lambayeque (northern Peru). The employed approach was the random forest algorithm and visually interpreted Landsat satellite images for the periods 2000–2002, 2002–2004, and 2004–2008. Gain and loss rates were computed for each period, and the recovery process was assessed using the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI). Results indicate an expansion of agricultural land during each period, resulting in the deforestation of 102.6 hectares of dense dry forest and 739.9 hectares of open dry forest between 2000 and 2008. The degree of reforestation in the cleared areas was measured using the NDVI and EVI indices, revealing an improvement from 0.22 in NDVI in 2009 to 0.36 in 2022, and from 0.14 to 0.21 in EVI over the same period. This study is expected to pave the way for executing land management plans, as well as the use and conservation of natural resources in the PFHS in a sustainable manner.

In view of the growing scarcity of water for agriculture, the increase in food demand and future drought scenarios posed by climate change, it is essential to design new technologies that contribute to lower water consumption. In this research, high-resolution images have been used to estimate evapotranspiration in rice fields by applying the METRICTM (Mapping Evapotranspiration at High Resolution using Internalized Calibration) energy balance model. For this purpose, 5900 m2 of crop were monitored under continuous flood irrigation (CF) and 2600 m2 under alternate wetting and drying irrigation (AWD), in addition to some plots with lateral filtration. Ten flights were conducted between tillering and flowering phases, five flights with a Matrice 210 UAV equipped with a Parrot Sequoia multispectral camera, and five flights with a Matrice 300 RTK equipped with a H20T thermal camera. Field data were collected from vegetation indices (NDVI and LAI), and readings from a radiometer, to adjust information from multispectral and thermal images, respectively, and to obtain the components of the surface energy balance. Mean values for crop evapotranspiration (ETc) of 6.34 ± 1.49 and 5.84 ± 0.41 mm d-1 were obtained for IC irrigation and AWD irrigation, respectively, obtaining a water saving of 42% with a yield reduction of 14%, providing a guide for proper irrigation management, however, it is suggested to use the model to optimize yield by obtaining critical thresholds for optimal application of AWD in the face of water resource scarcity.

INFLUENCE OF ORGANIC FERTIZATION ON THE FRUIT MORPHOLOGY AND PRODUCTION OF MANGO (Mangifera indica L.) VAR. KENT

The Prosopis sp. individuals known as carob trees are key species in the development of dry forest and recovery of degraded areas in the northern coast of Peru. The evaluation of plantations, calculation of aboveground forest biomass (AFB) and carbon stock represent an important role in forest management and climate change mitigation. This study evaluates monitoring methodologies using multispectral and LiDAR images coupled to a UAV, to validate them and generate models to estimate carbon stocks. Seven species of Prosopis sp. were evaluated with the conventional methodology and significant differences were found between species for dasometric characteristics and vegetation indices, as well as in the comparison with the data obtained with LiDAR. Models were selected to determine BAF and the association between the aerial carbon obtained with the models constituted by LiDAR data and vegetation indexes that presented significant correlations (p < 0.05), seven models were built for carbon prediction and the model that has as regressor variables the total height and crown area obtained from LiDAR, as well as the indexes CIgreen, GNDVI, RECI, LCI and NDVI (R² = 0.77) stands out. This confirms that the use of the LiDAR methodology with the vegetation indices allows a more practical estimation of the carbon stored in the plantation.

The dry forests of northern Peru are home to extensive populations of algarrobo (Neltuma spp.). Its fruit serves as feed for goats and is used in various agro-industrial products. However, the nutritional quality can be influenced by the physicochemical properties of the soil and vegetation coverage. The objective of this study was to understand and predict the concentration of protein and ether extracts of carob and evaluate its relationship with soil properties and vegetation indices. Principal component analysis (PCA) and correlation analyses were conducted. The prediction of protein and ether extract was carried out using the Eureqa-Formulize software 1.24.0. In the PCA, protein showed a positive relationship with ash and ether extract but a negative relationship with moisture. Likewise, moderate correlations were observed between protein and ash content (0.51). Protein also showed positive correlations with pH (r = 0.19), BI (r = 0.22), and NDSI (r = 0.22). Additionally, the ether extract exhibited correlations with sand content (r = 0.22), Ca²⁺ (r = −0.26), Cu (r = −0.20), S5 (r = 0.26), and Si (r = 0.24). Protein predictions showed moderate performance (CC = 0.73 and R² = 0.53), as did ether extracts (CC = 0.68 and R² = 0.46). These findings contribute to a better understanding of the factors that influence the nutritional quality of carob and can be used for the development of sustainable management strategies in the dry forests of northern Peru.

Maize (Zea mays L.) is a fundamental cereal in global food security, but its vulnerability to water stress compromises its productivity and threatens food availability. This study analyzed the relationship between the crop water stress index (CWSI), obtained from thermal images captured by the Zenmuse H20T camera, and various vegetation indices derived from the MicaSense RedEdge-MX Dual. The analysis included machine learning (ML) models such as random forest (RF), k-nearest neighbors (KNN), and gradient boosting regression (GBR). The results showed that RF was the most accurate model for predicting CWSI in maize, with a coefficient of determination (R²) of 0.80, a root mean square error (RMSE) of 0.13, and a mean absolute error (MAE) of 0.09. KNN achieved an R² of 0.78, an RMSE of 0.13, and an MAE of 0.09, while GBR reached an R² of 0.79, an RMSE of 0.14, and an MAE of 0.10. The red band (668 nm) played a crucial role in RF (70.69%) and GBR (50.92%), whereas in KNN, the simple ratio (SR) index showed the highest importance (36.40%). These findings confirm the superiority of ML models over traditional regression approaches for estimating CWSI in maize. Despite the satisfactory results, the algorithms underestimated CWSI values derived from thermal images, which highlights the need to refine these models to improve their accuracy in future agricultural applications.