Precision agricultural (PrA) technology relies on the utilization of special equipment to access real time observations on plant health status, chlorophyll, nitrogen content, and soil moisture content. In this research new PrA technology (i.e., SPAD (Soil Plant Analysis Development), and UAV-based NDVI (Unmanned Aerial Vehicle-based Normalized Difference Vegetation Index) were used to monitor maize yield based on different filed trials in eastern part of Hungary. Our study aimed to examine the utilization of PrA technology specifically SPAD and UAV-based NDVI measurements for monitoring maize GY under irrigated and rainfed experimental setups in Hungary with varied nitrogen treatment for the year 2022. The results showed that the SPAD increased in all treatments (14.7 %; p < 0.05) from V6–V8 in the rainfed treatments, decreased significantly (p < 0.05) by 13.9 % (R1) and 30.6 % (R3). However, implementation of irrigation significantly increased the SPAD values in majority of treatments. Also, results reveal that, under irrigated and rainfed conditions the highest UAV-based NDVI value (0.703, 0.642) was obtained in V12 (A120 treatment) and highest NDVI value (0.728, 0.662) was obtained in Vn (A120 treatment). Remarekedly, irrigation led to significant differences (p < 0.05) of UAV-based NDVI values compared with none irrigated. On the other hand, implementation of 120 kg N ha⁻¹ before sowing led to highest GY, especially under irrigated conditions (8.649 Mg ha⁻¹). The overall mean GY under rainfed treatment was 6.256 Mg ha⁻¹, while under irrigated treatment it increased by 37.2 % and reached 8.581 Mg ha⁻¹ (p < 0.05). In conclusion, PrA technology will support farmers in making informed decisions regarding fertilization strategies and timing, which will in turn maximize yield and minimize risk.

The Modified Fournier Index (MFI) is one of the indices that can assess the erosivity of rainfall. However, the implementation of the artificial neural network (ANN) for the prediction of the MFI is still rare. In this research, climate data (monthly and yearly precipitation (pi, Ptotal) (mm), daily maximum precipitation (Pd-max) (mm), monthly mean temperature (Tavg) (°C), daily maximum mean temperature (Td-max) (°C), and daily minimum mean temperature (Td-min) (°C)) were collected from three stations in Hungary (Budapest, Debrecen, and Pécs) between 1901 and 2020. The MFI was calculated, and then, the performance of two ANNs (multilayer perceptron (MLP) and radial basis function (RBF)) in predicting the MFI was evaluated under four scenarios. The average MFI values were between 66.30 ± 15.40 (low erosivity) in Debrecen and 75.39 ± 15.39 (low erosivity) in Pecs. The prediction of the MFI by using MLP was good (NSEBudapest(SC3) = 0.71, NSEPécs(SC2) = 0.69). Additionally, the performance of RBF was accurate (NSEDebrecen(SC4) = 0.68, NSEPécs(SC3) = 0.73). However, the correlation coefficient between the observed MFI and the predicted one ranged between 0.83 (Budapest (SC2-MLP)) and 0.86 (Pécs (SC3-RBF)). Interestingly, the statistical analyses promoted SC2 (Pd-max + pi + Ptotal) and SC4 (Ptotal + Tavg + Td-max + Td-min) as the best scenarios for predicting MFI by using the ANN–MLP and ANN–RBF, respectively. However, the sensitivity analysis highlighted that Ptotal, pi, and Td-min had the highest relative importance in the prediction process. The output of this research promoted the ANN (MLP and RBF) as an effective tool for predicting rainfall erosivity in Central Europe.

Drought is a natural hazard which affects ecosystems in the eastern Mediterranean. However, limited historical data for drought monitoring and forecasting are available in the eastern Mediterranean. Thus, implementing machine learning (ML) algorithms could allow for the prediction of future drought events. In this context, the main goals of this research were to capture agricultural and hydrological drought trends by using the Standardized Precipitation Index (SPI) and to assess the applicability of four ML algorithms (bagging (BG), random subspace (RSS), random tree (RT), and random forest (RF)) in predicting drought events in the eastern Mediterranean based on SPI-3 and SPI-12. The results reveal that hydrological drought (SPI-12, −24) was more severe over the study area, where most stations showed a significant (p < 0.05) negative trend. The accuracy of ML algorithms in drought prediction varied in relation to the implementation stage. In the training stage, RT outperformed the other algorithms (Root mean square error (RMSE) = 0.3, Correlation Coefficient (r) = 0.97); the performance of the algorithms can be ranked as follows: RT > RF > BG > RSS for both SPI-3 and SPI-12. In the testing stage, both the BG and RF algorithms had the highest correlation r (observed vs. predicted) (0.58–0.64) and lowest RMSE (0.68–0.88). In contrast, the lowest correlation r (observed vs. predicted) (0.3–0.41) and highest RMSE (0.94–1.10) was calculated for the RT algorithm. However, BG was more dynamic in drought capturing, with the lowest RMSE and highest correlation. In the validation stage, the BG performance was satisfactory (RMSE = 0.62–0.83, r = 0.58–0.79). The output of this research will help decision-makers with drought mitigation plans by using the new four machine learning algorithms.

In the last few decades, agricultural drought (Ag.D) has seriously affected crop production and food security worldwide. In Hungary, little research has been carried out to assess the impacts of climate change, particularly regarding droughts and crop production, and especially on regional scales. Thus, the main aim of this study was to evaluate the impact of agricultural drought on sunflower production across Hungary. Drought data for the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) were collected from the CAR-BATCLIM database (1961–2010), whereas sunflower production was collected from the Hungarian national statistical center (KSH) on regional and national scales. To address the impact of Ag.D on sunflower production, the sequence of standardized yield residuals (SSYR) and yield losses YlossAD was applied. Additionally, sunflower resilience to Ag.D (SRAg.D) was assessed on a regional scale. The results showed that Ag.D is more severe in the western regions of Hungary, with a significantly positive trend. Interestingly, drought events were more frequent between 1990 and 2010. Moreover, the lowest SSYR values were reported as −3.20 in the Hajdu-Bihar region (2010). In this sense, during the sunflower growing cycle, the relationship between SSYR and Ag.D revealed that the highest correlations were recorded in the central and western regions of Hungary. However, 75% of the regions showed that the plantation of sunflower is not resilient to drought where SRAg.Dx < 1. To cope with climate change in Hungary, an urgent mitigation plan should be implemented.

Biostimulants, when applied to plants in small amounts, increase crop yield and plant tolerance to abiotic and biotic stress. They play an important role in the development of new environmentally sustainable technologies. The aim of the current experiment was to investigate the potential of a cyanobacterium strain (Nostoc piscinale) to improve the growth, grain yield and stress tolerance of maize (Zea mays SY Zephir hybrid). Field trials were established at two sites. Freeze-dried biomass of N. piscinale resuspended in tap water (1g/L DW) was applied as a single foliar treatment (400 L/ha) at the V6-V7 phenological stage. Number of leaves, chlorophyll content, relative water content (RWC%) and free proline content were measured weekly. Grain yield, yield components and grain protein content were measured at harvest. N. piscinale treated maize had significantly earlier development in the vegetative growth stages with a higher number of leaves. Chlorophyll content (SPAD value) was significantly higher in the treated plants during the reproductive stages. There was little difference in the RWC and proline content compared to control plants. Faster vegetative growth and higher chlorophyll content in the cyanobacterium treated plants meant great photosynthetic light absorption over a longer period of time, resulting in significantly higher grain yield (6.5% and 11.5% at the two production sites) and increased grain protein content. Grain yield was significantly influenced by cob length and thousand grain weight. In conclusion, it was proved in field trials conducted in two different regions in Hungary that a single foliar application of a cyanobacterium-based biostimulant can contribute to crop production in a sustainable and environmentally friendly manner.

Introduction: Accurate prediction of soil moisture content (SMC) is crucial for agricultural systems as it affects hydrological cycles, crop growth, and resource management. Considering the challenges with prediction accuracy and determining the effect of soil texture, depth, and meteorological data on SMC variation and prediction capability of the used models, this research has been conducted. Methods: Three machine learning (ML) models—random forest regression (RFR), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)—were developed to predict SMC in three soil types (loam, sandy loam, and silt loam) at five depths of 5, 20, 40, 60, and 80 cm. The dataset was collected during the maize season in 2023, encompassing meteorological parameters collected using Internet of Things (IoT)-based sensors and SMC data calculated using the gravimetric method. Results: The results showed variations in SMC in all studied soil types and depths, with silt loam exhibiting the highest variation in SMC. RFR demonstrated high accuracy at different depths and soil types, particularly in loam soil, at a depth of 80 with a root mean square error (RMSE) value of 0.89 and a mean absolute error (MAE) value of 0.74, and in silt loam at 40 cm depth with an RMSE value of 0.498 and an MAE of 0.416. LSTM performed effectively at shallower and moderate depths (60 and 20 cm) with RMSE values of 0.391 and 0.804 and MAE values of 0.335 and 0.793, respectively. In sandy loam soil at 5 cm depth, XGBoost displayed minimal errors and robust performance at the same depths with higher accuracy, achieving an RMSE of 0.025 and an MAE of 0.159. Analysis of training and validation loss revealed that the LSTM model stabilized and improved with more epochs, showing a more consistent decrease in MSE, while RFR and XGBoost exhibited higher performance with increased model complexity, shown in low MSE and RMSE values. Comparisons between measured and predicted SMC% values demonstrated the models’ effectiveness in capturing soil moisture dynamics. Furthermore, feature importance analysis revealed that solar radiation and precipitation were the most influential predictors across all models, offering critical insights into dominant environmental drivers of soil moisture variability. Discussion: By providing precise SMC predictions across different spatial and temporal scales, this study underscores the value of ML models for SMC prediction, which could have implications for improving irrigation scheduling, reducing water wastages, and enhancing sustainability.