Pea (Pisum sativum L.) is an important source of food and feed and contributes to soil improvement through its association with nitrogen-fixing bacteria. By enabling higher yields and selection of tolerant genotypes, controlled environment agriculture (CEA) could meet increasing nutritional needs despite adverse conditions. The main objective of this study was to investigate the effects of drought stress on the development of vegetable pea genotypes under controlled vertical farming conditions. Plants were grown in CEA and exposed to drought stress at different developmental stages, after flowering and after pod formation. Drought significantly reduced pod and seed numbers, showing a stronger effect than genotype. For example, genotype Favorit produced 7.67 and 9.00 seeds per plant under control conditions, compared with only 2.00 and 2.67 seeds per plant under drought treatments. Pod length, seed number, and seed weight were also lower under stress, highlighting the importance of water availability during seed setting and filling. Fresh and dry biomass were mainly influenced by genotype, indicating differences in stress adaptability. The results also demonstrate that CEA can be used for reproducible abiotic stress experiments relevant to plant breeding and crop production.

Summary: The main lever of precision agriculture is technology that provides a better understanding of the agro-ecological conditions, enables decision-making based on facts and natural laws, and facilitates precise implementation of practices based on local specificities. One of the key elements of plant production is nitrogen (N), which is traditionally applied as mineral fertilizer in large quantities. Optimizing nitrogen input is one of the priorities in precision agriculture, not only for its importance in the plant food chain but also for its environmental impact. This study investigated the potential of two optical sensors, GreenSeeker and Plant-O-Meter, in predicting nitrogen supply during the 2021-2022 growing season. The experimental material in this study included two wheat varieties, subjected to different nitrogen application rates. The objective was to estimate the potential of using NDVI (Normalized Difference Vegetation Index) measurements of wheat canopy, which are indicators of plant status, and to analyze correlations between these values and final wheat yield. GreenSeeker and Plant-O-Meter sensors, which emit light at precise wavelengths and measure plant reflectance, were used for monitoring plant status and NDVI measurements. The results showed a strong correlation between the NDVI values measured by both sensors. However, this relationship decreased during the fully ripe stage due to physiological changes in the wheat plants. The correlation between NDVI values and grain yield differed significantly between the evaluated sensors. Additional correlation analyses between NDVI measurements and yield indicated differences associated with wheat varieties, indicating that the varieties responded differently to environmental conditions. This study aligns with current agricultural approaches and contributes to more efficient and environmentally friendly agricultural practices.

Agriculture, as a basis of sustainable development, faces increasing pressure to meet rising global food demands while confronting the increasing impacts of climate change. Precision agriculture offers a data-driven approach to address these challenges by optimizing input use, improving productivity, and reducing environmental impacts. Sensor technologies play a critical role in smart and precision agriculture, offering high-resolution spatial and temporal insights into soil conditions, plant development and environmental conditions. This review highlights the current state and future potential of various sensor and imaging systems, particularly their role in monitoring soil properties, crop nutrition, plant health and detecting biotic and abiotic stressors. Special attention is given to accessible paper-based and printed electrochemical devices for on-site soil and plant analysis, as well as active handheld multispectral sensors designed for real-time canopy assessment. The integration of sensor-derived data with predictive models, IoT networks and decision-support tools enables more precise, site-specific management, improves input efficiency and supports climate-resilient agricultural practices. By examining the capabilities, limitations and future potential of these sensing platforms, this review highlights their growing importance in advancing sustainable intensification and strengthening crop production.

Soybean (Glycine max L.) is one of the leading cultivated crops globally. Although the region of Vojvodina is favorable for soybean production, the climate, especially high temperatures and uneven distribution of precipitation, represents a major limiting factor. The aim of this study is to investigate the correlation between soybean yield, water stress levels, and vegetation indices obtained using a handheld multispectral sensor and a drone under natural moisture conditions on a test plot in Čenej, Vojvodina. The results showed a significant correlation between vegetation indices with evapotranspiration, soil moisture changes, and soybean yield. During the intensive growth phase (V4), NDVI-UAV, EVI-UAV, and GNDVI-UAV showed highly significant positive correlations with yield (r=0.96**, r=0.94**, r=0.86*). During the flowering phase (R1), GNDVI-POM had significant positive correlations with all analyzed parameters, while GNDVI-UAV had significant correlations with evapotranspiration and soil moisture. During the pod formation phase (R3), GNDVI-UAV again showed a significant correlation with yield (r=0.86*), while NDVI-POM had significant correlations with evapotranspiration and soil moisture. During the pod filling phase (R4), EVI-UAV showed highly significant positive correlations with evapotranspiration, soil moisture, and yield (r=0.94**, r=0.96**, r=0.89**). These results are useful for the application of multispectral sensors in detecting soybean water availability and improving production under natural moisture conditions

Aim of study: The aim of this research was to examine the effects of salinity-based seed priming on the growth, reproduction, and yield of pea (Pisum sativum L.) to determine its potential for enhancing drought resilience. Area of study: The field experiments were conducted over two vegetative seasons in Idvor, South Banat, Republic of Serbia. Material and methods: Pea seeds were subjected to pre-sowing salinity priming treatments using two concentrations of NaCl (40 mM and 80 mM), alongside a non-primed control group. The study assessed plant height, biomass, root growth, pod formation, and final yield. Data were analyzed using analysis of variance (ANOVA) to determine the influence of salinity levels and seasonal variations. Main results: Moderate salinity priming (40 mM NaCl) significantly enhanced plant height, biomass, and pod formation, suggesting that mild stress-induced adaptive mechanisms can improve performance. Conversely, high salinity (80 mM NaCl) inhibited germination and root development, leading to a complete loss of yield due to ion toxicity. ANOVA revealed that salinity concentration was the dominant factor influencing all examined traits, while seasonal variations had a significantly lesser impact. Research highlights: Optimizing salinity concentrations in seed priming is crucial for balancing stress adaptation; while 40 mM NaCl improves pea growth traits, concentrations as high as 80 mM are detrimental and lead to total reproductive failure.

Variation in maize performance under different nitrogen fertilization regimes depends on genotype response, environmental conditions, and their interaction. This study evaluated three commercial maize hybrids contrasting maturity groups (G1–P9537, G2–P9911 and G3–P0412, representing early, medium, and late FAO maturity groups, respectively) across two growing seasons and five nitrogen treatments (0, 50, 100, 150, and 200 kg N ha⁻¹) using the Additive main effects and multiplicative interaction (AMMI) model. Analysis of variance revealed significant genotype and environment effects on grain yield, whereas genotype by environment interaction (GEI) was not significant. However, decomposition of the GEI using the AMMI model indicated that the first interaction principal component (IPCA1) was statistically significant and accounted for 90.6% of the GEI sum of squares, indicating that the interaction component was predominantly described by a single multiplicative axis. Genotype G3 achieved the highest mean grain yield and low IPCA1 score, demonstrating relatively stable performance across the evaluated nitrogen environments in this study. In contrast, G2 exhibited narrower adaptation and was more closely associated with control and low-nitrogen environments, while G1 had the lowest mean yield but exhibited a low interaction IPCA score. These findings provide useful information for hybrid evaluation under various nitrogen environments and may contribute to improved nitrogen management and hybrid selection under conditions similar to those investigated in this study.