Agriculture is an area that currently benefits from the use of new technologies and techniques, such as artificial intelligence, to improve production in crop fields. Zacatecas is one of the states producing the most onions in the northeast region of Mexico. Identifying and determining vegetation, soil, and humidity zones could help solve problems such as irrigation demands or excesses, identify spaces with different levels of soil homogeneity, and estimate the yield or health of the crop. This study examines the application of artificial intelligence through the use of deep learning, specifically convolutional neural networks, to identify the patterns that can be found in a crop field, in this case, vegetation, soil, and humidity zones. To extract the mentioned patterns, the K-nearest neighbor algorithm was used to pre-process images taken using unmanned aerial vehicles and form a dataset composed of 3672 images of vegetation, soil, and humidity (1224 for each class). A total of six convolutional neural network models were used to identify and classify the patterns, namely Alexnet, DenseNet, VGG16, SqueezeNet, MobileNetV2, and Res-Net18. Each model was evaluated with the following validation metrics: accuracy, F1-score, precision, and recall. The results showed a variation in performance between 90% and almost 100%. Alexnet obtained the highest metrics with an accuracy of 99.92%, while MobileNetV2 had the lowest accuracy of 90.85%. Other models, such as DenseNet, VGG16, SqueezeNet, and ResNet18, showed an accuracy of between 92.02% and 98.78%. Furthermore, our study highlights the importance of adopting artificial intelligence in agriculture, particularly in the management of onion fields in Zacatecas, Mexico. The findings can help farmers and agronomists make more informed and efficient decisions, which can lead to greater production and sustainability in local agriculture.

In this study, daily historical records from Mexican weather stations across the country were classified according to corresponding Moon phases at the time of rainfall occurrence: New Moon, Waxing Crescent, First Quarter, Waxing Gibbous, Full Moon, Waning Gibbous, Last Quarter, and Waning Crescent. Out of the 5839 Mexican weather stations analyzed, 2412 met the specified data quality standards, which included a historical daily record period ranging from 30 to 51 years (1960–2011) and a maximum tolerance of 20% missing data. Correlation behavior between Moon phases and historical cumulative rainfall in Mexico was identified at two levels: general and particular. At the general level, the total historical cumulative rainfall by Moon phase was quantified. At the particular level, the correlation patterns between the Moon phases and the highest and lowest historical cumulative rainfall were identified. The results showed that the historical cumulative rainfall was highest at 17.24% during the New Moon and lowest at about 10.01% on average during the Waxing Crescent, First Quarter, and Waning Crescent phases (with 9.64% as the lowest value). During the Waxing Gibbous, Full Moon, and Waning Gibbous phases, rainfall remained at average values of approximately 13.18%. At 89.09% of the weather stations, the rainiest Moon phase was New Moon, and at 56.05%, the least rainy was Waning Crescent. In a few geographical areas, there are clearly defined patterns, which is atypical, given that in other geographical areas, the patterns are typically not so evident. This work demonstrates remarkable and strong correlation behavior between Moon phases and historical cumulative rainfall in Mexico.