The change climate processes have called attention of science in recent decades; situations such as desertification and drought are issues of great importance. Where it was the interest to study the soil salinity and the Normalized Difference Vegetation Index (NDVI) from images of the ETM + and TM sensors, these images were processed using the software ENVI 4.5 and IDL programming language. For this purpose, we implemented an artificial neural network with error back propagation architecture, for classifying soil salinity, using as input data of images NDVI and data soil electrical conductivity for the training. The areas studies were the commission irrigation Muy Finca and the districts of Morrope and Lambayeque belonging to the region Lambayeque-Peru. For the neural network architecture using 2 hidden layers presenting a training error of 0.27, these results were evaluated using the co...

En el presente trabajo, utilizamos la ciencia de la teledetección por ser una herramienta particularmente valiosa para obtener datos relevantes sobre el Suelo. El objetivo de este trabajo es estimar la salinidad del suelo con el uso de imágenes de satélite y su validación con los datos in-situ de conductividad eléctrica (CE) del suelo. Las áreas de estudio en este trabajo fueron cuatro: San Antero, La Viña, Saltur y Ucupe ubicadas en el distrito de Cayalti, Nueva Arica y Zaña, respectivamente. Estas áreas de estudio se encuentran en la cuenca de Zaña de la provincia de Chiclayo en la región de Lambayeque. En este trabajo se usaron imágenes de satélite procedente de los sensores ASTER, TM y ETM+ que fueron procesados y analizados usando el software de procesamiento de imágenes ENVI 4.5 y el lenguaje de programación IDL 7.0. Se determinó los componentes principales, el índ...

We quantified the influence of sea surface temperature (SST) in the Niño 1+2 region and precipitation on the NDVI dynamics of the dry forest along Peru’s northern coast during 2003–2023. We used monthly series from MODIS (NDVI), CHIRPS (precipitation), and NOAA SST, seasonally standardized (z-score). We applied a 36-month rolling correlation, time–frequency analysis (XWT/WTC), and autoregressive models with exogenous regressors (ARX). Cross-correlation showed that NDVI responds with a positive one-month lag to both SST and precipitation, with correlation coefficients of 0.764 and 0.613, respectively. Among four AR(2) models evaluated, the ARX with lagged SST provided the best fit (AIC = 295.35), slightly outperforming the combined SST+precipitation model (AIC = 295.46). Akaike weights favored the former on grounds of parsimony. The results indicate a positive sensitivity of NDVI t...