The vegetation fraction (VF) monitoring in a specific area is a very important parameter for precision agriculture. Until a few years ago, high-cost flights on aeroplanes and satellite imagery were the only option to acquire data to estimate VF remotely. Recently, Unmanned Aerial Vehicles (UAVs) have emerged as a novel and economic tool to supply high-resolution images useful to estimate VF. VF is usually estimated by spectral indices using red-green-blue (RGB) and near-infrared (NIR) bands data. For this study, a UAV equipped with both kinds of sensors (RGB and NIR) was used to obtain high-resolution imagery over a maize field in progressive dates along the mid-season and the senescence development stages. The early-season stage was also monitored using only RGB spectral indices. Flights were performed at 52 m over the terrain, obtaining RGB images of 1.25 cm pixel⁻¹ and multispectral images of 2.10 cm pixel⁻¹. Three spectral indices in the visible region, Excess Green (ExG), Colour Index of Vegetation (CIVE), and Vegetation Index Green (VIg), and three NIR-based vegetation indices, Normalized Difference Vegetation Index (NDVI), Green NDVI (GNDVI), and Normalized Green (NG), were evaluated for VF estimation. Otsu’s method was applied to automatically determine the threshold value to classify the vegetation coverage. Results show that ExG presents the higher mean accuracy (85.66%) among all the visible indices, with values ranging from 72.54% to 99.53%, having its best performance in the earlier development stage. Nevertheless, GNDVI mean accuracy (97.09%) overcomes all the indices (visible and multispectral), ranging in value from 92.71% to 99.36%. This allowed comparing the accuracy difference gained by using a NIR sensor, with a higher economic cost than required using a simple RGB sensor. The results suggest that ExG can be a very suitable option to monitor VF in the early-season growth stage of the crop, while later stages could require NIR-based indices. Thus, the selection of the index will depend on the objectives of the study and the equipment capacity.

Landsat images combined with the METRIC model have been used in applications such as EEFlux to estimate actual evapotranspiration ($E{T}_a$) in irrigated areas, with uncertainty as to whether the results are sufficiently accurate at local scales. This work compares temporally and spatially $E{T}_a$ estimates using Landsat imagery and the METRIC model with LOCAL measured weather data and EEFlux for an irrigated area in northern Sinaloa, Mexico, from 1995 to 2018. A regression analysis and error metrics such as coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE) and slope were used to compare both models. The temporal analysis results confirm that $E{T}_a$ differences are closely related to crop growth and that the daily mean absolute error was 1.17 mm/day. Spatial analysis showed that when using only cropland pixels without non-cropland pixels in EEFlux, the R² increases from 0.36 to 0.73, and the RMSE decreases from 2.52 to 1.98 mm/day. Therefore, EEFlux should be limited to cropland areas, and it is suggested to exclude Landsat images close to the planting and harvesting season to reduce the differences.

El agua de riego resulta ser un factor esencial en la actividad agrícola, por lo que es necesario hacer un uso eficiente del recurso. En México, las eficiencias de conducción de las zonas de riego son bajas, lo que está asociado al nivel y parcialización de la tecnificación. En este escenario, es importante determinar con precisión los requerimientos de riego netos (RR) de los cultivos agrícolas, a fin de cuantificar los volúmenes que se requieren para satisfacer la demanda hídrica de los cultivos que se establecen en las distintas regiones agrícolas del país. Entre estas regiones destaca el estado de Guanajuato, México, que dedica más del 30 % de la superficie agrícola al riego. Por lo anterior, el presente trabajo determina los RR de los principales cultivos agrícolas en el estado de Guanajuato, generando mapas con la distribución de los RR por medio del software QGIS y el método de interpolación espacial de la distancia inversa ponderada (IDW) elegido por la simplicidad que presenta, sobre todo, en la cuestión de datos de entrada del software QGIS, lo que permitió obtener una superficie visible y ligeramente continua en la distribución espacial de los valores interpolados. Los cultivos modelados fueron alfalfa, cebada, maíz, sorgo y trigo. Para determinar los RR se utilizaron tres variables: la evapotranspiración de referencia (ETo), la Precipitación Efectiva (Pe) y la evapotranspiración de cultivo (ET). La ETo fue calculada por medio del programa Cropwat 8.0 y la metodología de Penman-Monteith, la Pe fue calculada con el método de la USDA, mientras que la ET se calculó con la ETo y el coeficiente único del cultivo (Kc). El estado de Guanajuato cuenta con 104 estaciones climatológicas registrando la temperatura máxima, temperatura mínima y precipitación en el periodo 1981-2010, información que fue utilizada en este trabajo. El resultado fue la obtención de mapas que permiten visualizar los volúmenes de agua, expresados en láminas de riego, con los cuales es posible determinar, entre varias aplicaciones, los escenarios posibles para contabilizar el uso de agua que se le da a la agricultura y coadyuvar a la toma correcta de decisiones en el riego agrícola.

Groundwater overexploitation is a global problem. In Mexico, 653 aquifers provide 39.1% of water for consumptive use. The National Water Commission manages this resource, but predicting aquifer availability is challenging, and the number of aquifers in deficit has increased. Physical models can address this issue but require extensive resources, whereas supervised learning algorithms offer a less resource-demanding alternative. This study evaluates four machine learning techniques for groundwater availability prediction: support vector machine regression, M5' model trees, random forests (RFR), and artificial neural networks. The models were trained using climatological, land use, and concession data from 1997 to 2015 and tested with data from 2018 and 2020. Random forests performed the best, showing a high correlation coefficient and low RMSE errors. The prediction accuracy for the availability state was 81.24% for 2018 and 76.79% for 2020. Thus, RFR can effectively predict short-term water availability, aiding sustainable aquifer management.