Francisco Marcelo Lara-Viveros

La agricultura enfrenta desafíos significativos, como el uso excesivo de insecticidas que afecta la calidad de los productos y la optimización de la producción. La agricultura de precisión, impulsada por inteligencia artificial (IA), es una alternativa para mejorar la eficiencia, reduciendo el impacto ambiental y aumentando la productividad. Esta tecnología permite la medición precisa de variables facilitando la toma de decisiones en tiempo real. El monitoreo de plagas es crucial, ya que su presencia puede reducir el rendimiento de los cultivos. La detección temprana mediante sistemas automatizados de monitoreo resulta una alternativa esencial para prevenir daños. La IA y el aprendizaje automático (ML) son fundamentales para el análisis de datos y la identificación de plagas de manera precisa y en tiempo real, lo que optimiza la toma de decisiones. Los sistemas automatizados de monitoreo, como los basados en imágenes, ofrecen ventajas en comparación con los métodos manuales tradicionales, permitiendo la detección de plagas con alta precisión. Estas tecnologías mejoran la eficiencia de la producción agrícola y promueven prácticas más sostenibles al reducir la intervención humana.

Los hongos fitopatógenos representan una amenaza considerable para el cultivo de cucurbitáceas, por lo que la detección temprana y cuantificación precisa de enfermedades resulta esencial para reducir pérdidas en la producción. En este estudio se desarrolló una metodología para estimar cuantitativamente el daño provocado por Podosphaera xanthii en hojas de pepino, mediante el uso de imágenes digitales y técnicas de aprendizaje automático. Se emplearon redes neuronales convolucionales para clasificar visualmente el grado de severidad en seis categorías predefinidas, utilizando secciones de hojas con síntomas evidentes del hongo. Adicionalmente, se entrenaron y compararon cuatro algoritmos de clasificación supervisada: K-NN, árboles de decisión, bosques aleatorios y redes neuronales. El modelo que obtuvo el mejor desempeño fue el de bosques aleatorios, con una precisión del 90%, mientras que K-NN alcanzó el valor más bajo (79%). Estos resultados posicionan al modelo como una herramienta útil para el monitoreo automatizado de enfermedades en campo, facilitando la toma de decisiones fitosanitarias. Además, la metodología ofrece una base sólida para investigadores interesados en diseñar e implementar sistemas automáticos de clasificación de enfermedades en plantas, brindando información clara sobre el rendimiento de distintas arquitecturas de clasificación. El algoritmo desarrollado en R permite adaptar y escalar esta solución a diferentes condiciones de cultivo y tipos de enfermedades foliares.

A greenhouse pot experiment was conducted to evaluate the zinc (Zn) accumulation potential of Lupinus uncinatus Schldl. The effects of varying Zn concentrations on plant dry matter yield, metal tolerance, and Zn accumulation and distribution in roots, stems, and leaves were investigated. Zn was applied as ZnCl2 at rates of, 200, 400, and 600 mg/kg. One-way analysis of variance followed by Tukey’s multiple comparison test (p<0.05) revealed significant effects of Zn on root dry weight, Zn uptake in roots, stems, and leaves, and the shoot-to-root Zn ratio. Root dry weight was significantly reduced, with the highest Zn treatment (600 mg/kg) causing a 57% reduction compared to control plants. However, no significant differences were observed in overall plant dry matter yield. Metal tolerance declined with increasing Zn stress. Zn accumulation in leaves reached 9,632 mg/kg and 14,771 mg/kg at soil Zn application rates of 400 mg/kg and 600 mg/kg, respectively. The shoot-to-root Zn ratio exceeded one, and more than 64% of the total Zn absorbed by L. uncinatus was translocated to the shoots at 600 mg/kg. These results position L. uncinatus as a promising species for Zn phytoremediation, encouraging future studies under field conditions and with other toxic metals.

La pudrición de corona es la enfermedad poscosecha más importante en banano en todo el mundo. Se determinó la actividad antifúngica del silicato de potasio (SP) en poscosecha contra la pudrición de la corona (PC) del banano inoculado con Colletotrichum musae (Cm). Se probaron tratamientos con SP (30 a 160 mM) mediante experimentos in vitro e in vivo (70 a 300 mM). La concentración preliminar in vivo de 90 mM de SP, se usó en los experimentos de la influencia de la temperatura de baños, en la efectividad del SP. Tratamientos de baños curativos de SP a 90 mM a 40 °C durante 20 min aplicados solo o combinados con bajas dosis de tiabendazol (TBZ) se evaluaron sobre la PC, así como también el efecto del SP sobre la calidad del banano. El SP a 90 mM inhibió totalmente el crecimiento micelial de Cm, y redujo significativamente la severidad de la PC tanto en tratamientos preventivos (51,1 %) como curativos (59,5 %) en experimentos primarios in vivo. Entre los baños con SP a 90 mM durante 20 min probados a diferentes temperaturas, el baño a 40 °C curativo fue seleccionado como el más efectivo. El tratamiento combinado de baño curativo, SP+TBZ, mejoró el control contra PC con una reducción de incidencia de 91,6 %. El SP no afectó la calidad de fruto de banano.

Contamination by heavy metals resulting from irrigation with wastewater is an important global concern, as it can lead to crop contamination, posing serious threats to human health. Despite the advances in bioremediation of soils, sustainable strategies that use beneficial microorganisms to reduce the accumulation of heavy metals in contaminated crops remain underexplored. The aim of this study was to evaluate the potential reduction of heavy metal concentration in different structures of bean plants cultivated in soils irrigated with untreated wastewater on an agricultural land located in Hidalgo, Mexico, through the inoculation of a ubiquitous soil fungus. Bean plants were inoculated with three Trichoderma spp. and distributed across eight treatments, with an additional untreated control group, following a random full design. The percentage of root colonization and concentration of heavy metals in the leaves, pods, grains, and soil were determined. The results revealed that root colonization exceeded 75%. The treatments T. harzianum + T. asperellum and T. harzianum with 3 × 10⁶ spores ml⁻¹ showed the greatest decrease in Cd (64.7%) and Pb (66.1%) concentrations in the grains. T. viride with 2 × 10⁶ spores ml⁻¹ was the most effective treatment for copper reduction (72.9%) in grains; T. harzianum with 3 × 10⁶ spores ml⁻¹ showed the best performance for chromium reduction (75.7%), which was below the detection limit in leaves. In conclusion, inoculation of bean plants with Trichoderma spp. effectively reduced the accumulation of heavy metals. Future research in this area could contribute to the development of sustainable strategies to mitigate heavy metal contamination in agricultural ecosystems, thereby promoting food and environmental safety.

In traditional pest monitoring, specimens are manually inspected, identified, and counted. These techniques can lead to poor data quality and hinder effective pest management decisions due to operational and economic limitations. This study aimed to develop an automatic detection and early warning system using the European Pepper Moth, Duponchelia fovealis (Lepidoptera: Crambidae), as a study model. A prototype water trap equipped with an infrared digital camera controlled using a microprocessor served as the attraction and capture device. Images captured by the system in the laboratory were processed to detect objects. Subsequently, these objects were labeled, and size and shape features were extracted. A machine learning model was then trained to identify the number of insects present in the trap. The model achieved 99% accuracy in identifying target insects during validation with 30% of the data. Finally, the prototype with the trained model was deployed in the field for result confirmation.

Use of Computer Vision Techniques for Recognition of Diseases and Pests in Tomato Plants

The use of trace elements such as iodine and selenium in agriculture is gaining great importance due to the benefits in plants before different types of biotic or abiotic stress. This research aimed to evaluate the seedling root priming with Na2SeO3 (0, 0,5, 1, 2, 3 mg L-1) and KIO3 (0, 100, 150, 200, 250 mg L-1) on the antioxidant compounds of tomato (Solanum lycopersicum L.) fruits and leaves. The crop was established under greenhouse conditions in 10-L polyethylene containers containing peat moss and perlite 1:1 (v/v), in a randomized complete block experimental design with a 52 factorial arrangement. In the fruits, the Na2SeO3 influenced the GHS, flavonoids, lycopene and β-carotene contents, while the KIO3 influenced the GHS, vitamin C and lycopene contents. The KIO3-Na2SeO3 interactions affected the GSH, phenols, flavonoids, lycopene and β-carotene contents in fruits. In the leaves the GHS content increased with the Na2SeO3, while the GSH, flavonoids, and chlorophyll contents increased with the KIO3 factor and KIO3-Na2SeO3 interactions. The evaluated enzymes in fruits and leaves decreased with the both the KIO3 and Na2SeO3 concentrations. The Na2SeO3 influenced the hydrophilic compounds by ABTS and DPPH, while the KIO3 influenced the hydrophilic compounds by ABTS. In the leaves, the KIO3 influenced the lipophilic compounds by ABTS. The KIO3-Na2SeO3 interactions influenced the hydrophilic compounds by ABTS in both the fruits and leaves. Seedling root imbibition in KIO3 and Na2SeO3 is a method that implemented in the tomato crop presents interesting aspects in the increase of the antioxidant capacity and the non-enzymatic compounds, such as vitamin C, phenols, flavonoids and GSH contents. However, this method presented an inhibition in the antioxidant enzymes.

The use of unmanned aerial vehicles (UAVs) in precision agriculture has proven to be a useful tool for crop monitoring. The use of this technology in irrigation water management represents a significant improvement opportunity compared to the tools commonly used. This study aimed to estimate the water content in corn plants using images captured by a drone, evaluating the effect that the flying height has on the accuracy of the estimation of this indicator. For this purpose, water potential (WP) was measured in corn plant leaves, which allows us to infer the presence of water stress, and indicates the need for irrigation in the plant. Aerial images of the crop were captured under three treatments based on irrigation levels (40%, 70%, and 100% water applied, compensating for evapotranspiration) to induce gradients of moisture content in the plants. Seven drone flights were carried out at different dates at 30, 50 and 70 m height. The water potential of the leaves was correlated with radiometrically calibrated multispectral images (R, G, B, red-edge, and near-infrared). Three models were developed: a multiple linear regression (LM), neural networks (NN), and a random forest (RF). The LM and NN models showed similar error metrics, with the RF model showing the best results, with an average root mean square error (RMSE) and coefficient of determination (R²) of 1.26 and 0.9, respectively, with the training dataset. The flying height, which affected the resolution of the images, was not significant in the estimation of WP in this height range.

The use of trace elements in agriculture as a complement to crop fertilization programs is a practice that is gaining importance and relevance worldwide. Iodine and selenium perform essential functions in human health, related to the proper functioning of the thyroid gland, acting as antioxidants and antiproliferatives, and their limited intake through food consumption can cause malnutrition, reflected in the abnormal development and growth of humans. This research aimed to evaluate the nutraceutical quality of tomato (Solanum lycopersicum L.) in response to seed priming based on KIO₃ (0, 100, 150, 200, 250 mg L⁻¹) and Na₂SeO₃ (0, 0.5, 1, 2, 3 mg L⁻¹), performed by interaction from a 5²-factorial design and by independent factors in a 24-h imbibition time. The tomato crop was established under greenhouse conditions in 10-L polyethylene containers containing peat moss and perlite 1:1 (v/v). Regarding non-enzymatic antioxidant compounds, lycopene, β-carotene and flavonoid contents in tomato fruits significantly increased with KIO₃ and Na₂SeO₃ treatments; however, vitamin C content was negatively affected. KIO₃ increased the phenol and chlorophyll-a contents of leaves. In relation to enzymatic activity, KIO₃ positively influenced GSH content and PAL activity in tomato fruits. KIO₃ also positively influenced GSH content in leaves while negatively affecting PAL and APX activities. Na₂SeO₃ favored GSH content and GPX activity in tomato fruits and leaves. Na₂SeO₃ negatively affected the antioxidant capacity of hydrophilic compounds by ABTS in fruits and leaves and favored hydrophilic compounds by DPPH in leaves. Seed imbibition based on KIO₃ and Na₂SeO₃ is a method that is implemented in the tomato crop and presents interesting aspects that favor the nutraceutical quality of tomato fruits, which may contribute to increasing the intake of these minerals in humans through tomato consumption.