La Agricultura 4.0 es la nueva revolución de la agricultura para hacer frente a los actuales retos que esta enfrenta, principalmente debido al crecimiento demográfico, la escasez de recursos naturales, el cambio climático y el desperdicio de alimentos. Un invernadero normalmente produce más rendimiento por metro cuadrado en comparación con el cultivo en campo abierto, ya que las condiciones ambientales que determinan el rendimiento de los cultivos son controladas, ya sea de manera manual o automática. Sin embargo, existen recursos, como el agua y los fertilizantes, que no se dosifican eficientemente, ya que su aplicación se realiza en forma empírica. En este trabajo se presenta el diseño y la implementación de un sistema de control automático de lazo cerrado a partir del paradigma de la Agricultura 4.0. De acuerdo con la información de diversos sensores, de manera automática se controla la irrigación y la fertilización de un cultivo de lechuga en invernadero. La información de las principales variables que influyen en el cultivo se digitaliza y envía a la nube (servidor remoto) para su almacenamiento y análisis en línea. El estado de los diversos sensores y actuadores puede ser consultado en cualquier momento mediante una aplicación móvil, desarrollada especialmente para este sistema. Para probar el desempeño del sistema de control se diseñó una configuración experimental en cuatro tratamientos con solución fertilizante Steiner en concentraciones de 50%, 75% y 100%, cada uno con cuatro repeticiones, y uno más sólo con agua. El desempeño global del sistema demostró ser eficiente, independientemente del tratamiento.

A variable seed rate system was integrated and evaluated using Trimble technology. Laboratory tests were conducted to assess system performance on a seeder test bench, with seed delivery rates ranging from 180 to 800 seeds per minute. The system was tested using two corn seed plates: a 30-cell Precision Planting plate (PP) and a 40-cell John Deere (JD) plate. The laboratory results showed a cell fill rate of 98.6% for the PP plate and 104.5% for the JD plate. Field performance was evaluated at four sowing densities (100,000; 80,000; 60,000; and 40,000 seeds·ha ⁻¹ ) and three travel speeds (6, 8, and 10 km·h ⁻¹ ). Results showed no significant differences in dosing uniformity due to sowing density otr speed. The system achieved 100% dose uniformity with a coefficient of variation (CV) of just 1.36%, demonstrating high operational reliability. Regarding seed delivery uniformity, an analysis of variance of seed fall timing revealed a significant difference between the plates. The PP plate outperformed the JD plate, with a CV of 10.82% compared to 14.387%, respectively. The system‘s response time to changes in seeding density ranged from 43 milliseconds (from 100,000 to 80,000 seeds·ha ⁻¹ at 10 km·h ⁻¹ ) to 232 milliseconds (from 40,000 to 100,000 seeds·ha ⁻¹ at 6 km·h ⁻¹ ). In conclusion, the integrated variable seed rate system demonstrated high operational reliability. However, an average variability of 12.5% in planter performance was observed, highlighting an opportunity for further optimisation and system improvement.

The transition toward Agriculture 4.0 requires soil sampling strategies that really characterize spatial heterogeneity. This study compared conventional five-point composite (5P) and zigzag (ZZ) sampling methods with multispectral image-guided sampling (MI) using a DJI Mavic 3 unmanned aerial vehicle (UAV) (SZ DJI Technology Co., Ltd.), Shenzhen, Guangdong, China) in a semi-arid agroecosystem of northeastern Mexico. In situ measurements included penetration resistance (PR), volumetric water content (VWC), and apparent electrical conductivity (ECa), while laboratory analyses included bulk density (ρ_b) and soil pH (H₂O). Statistical analyses revealed significant differences among sampling strategies for penetration resistance and volumetric water content (p < 0.05). The MI approach captured greater spatial contrasts in penetration resistance within the 10–20 cm depth interval, with PR values reaching up to 5076 kPa, whereas conventional methods recorded substantially lower PR values. UAV-guided sampling identified sampling locations associated with contrasting VWC and PR measurements relative to conventional composite sampling strategies. Soil pH (H₂O) and ECa remained stable among sampling methods; however, highlighting the need for methodological standardization and local calibration. Multispectral image-guided sampling facilitates spatial stratification and the characterization of within-field variability in dynamic soil physical properties, supporting stratified soil management and more efficient resource use in semi-arid agricultural systems.