Increasing the productivity of cereals such as maize while protecting the environment remains a fundamental impetus of healthy food production systems. The use of biostimulants is one of the sustainable strategies to achieve this balance, although the ability of biostimulants to enhance maize productivity varies. Moreover, research on the efficacy of biostimulants is ubiquitous with limited comprehensive global analysis. In this context, this systematic review evaluated the sole and interactive effects of biostimulants on the yield and quality of maize grain from a global perspective. Changes in yield (t ha^-1), protein content (%), starch content (%) and oil content (%) of maize grain were assessed. Results revealed that sole and combined application of biostimulants significantly improved grain yield. Irrespective of the region, the highest and the lowest grain yields ranged between 16-20 t ha^-1 and 1-5 t ha^-1, respectively. In sole application, the promising biostimulants were chicken feather (16.5 t ha^-1), and endophyte Colletotrichum tofieldiae (14.5 t ha^-1). Sewage sludge × NPK (15.4 t ha^-1), humic acid × control release urea (12.4 t ha^-1), Azospirillum brasilense or Bradyrhizobium japonicum × maize hybrids (11.6 t ha^-1), and Rhizophagus intraradices × earthworms (10.0 t ha^-1) had higher yield for the interactive effects. The effects of biostimulants on grain quality were minimal, and all attributes improved in the range from 0.1 to 3.7%. Overall, biostimulants had a distinct improvement effect on yield, rather than on the quality of grain. As one way of maximising maize productivity, soil health, and the overall functioning of crop agroecosystems, the integrated application of synergistic microbial and non-microbial biostimulants could provide a viable option. However, the ability to produce consistent yield and quality of grain improvement remains a major concern.

Artificial intelligence, specifically machine learning (ML), serves as a valuable tool for decision support in crop management under ongoing climate change. However, ML implementation to predict maize yield is still limited in Central Europe, especially in Hungary. In this context, we assessed the performance of four ML algorithms (Bagging (BG), Decision Table (DT), Random Forest (RF) and Artificial Neural Network-Multi Layer Perceptron (ANN-MLP)) in predicting maize yield based on four different input scenarios. The collected data included both agricultural data (production (PROD) (ton) and maize cropped area (AREA) (ha)) and climate data (annual mean temperature °C (Tmean), precipitation (PRCP) (mm), rainy days (RD), frosty days (FD) and hot days (HD)). This research adopted four scenarios, as follows: SC1: AREA+ PROD+ Tmean+ PRCP+ RD+ FD+ HD; SC2: AREA+ PROD; SC3: Tmean+ PRCP+ RD+ FD+ HD; and SC4: AREA+ PROD+ Tmean+ PRCP. In the training stage, ANN-MLP-_SC1 and ANN-MLP-_SC4 outperformed other ML algorithms; the correlation coefficient (r) was 0.99 for both, while the root mean squared errors (RMSEs) were 107.9 (ANN-MLP-_SC1) and 110.7 (ANN-MLP-_SC4). In the testing phase, the ANN-MLP-_SC4 had the highest r value (0.96), followed by ANN-MLP-_SC1 (0.94) and RF-_SC2 (0.94). The 10-fold cross validation also revealed that the ANN-MLP-_SC4 and ANN-MLP-_SC1 have the highest performance. We further evaluated the performance of the ANN-MLP-_SC4 in predicting maize yield on a regional scale (Budapest). The ANN-MLP-_SC4 succeeded in reaching a high-performance standard (r = 0.98, relative absolute error = 21.87%, root relative squared error = 20.4399% and RMSE = 423.23). This research promotes the use of ANN as an efficient tool for predicting maize yield, which could be highly beneficial for planners and decision makers in developing sustainable plans for crop management.

Remote sensing is an efficient tool to detect vegetation heterogeneity and dynamics of crop development in real-time. In this study, the performance of three maize hybrids (Fornad FAO-420, Merida FAO-380, and Corasano FAO-490-510) was monitored as a function of nitrogen dose (0, 80 and 160 kg N ha⁻¹), soil tillage technologies (winter ploughing, strip-tillage, and ripping), and irrigation (rainfed and 3x25 mm) in a warm temperature dry region of East-Central Europe. Dynamics of the Normalized Difference Vegetation Index (NDVI) were followed in the vegetation period of 2021, a year of drought, by using sensors mounted on an unmanned aerial vehicle. N-fertilization resulted in significantly higher NDVI throughout the entire vegetation period (p < 0.001) in each experimental combination. A significant positive effect of irrigation was observed on the NDVI during the drought period (77–141 days after sowing). For both the tillage technologies and hybrids, NDVI was found to be significantly different between treatments, but showing different dynamics. Grain yield was in strong positive correlation with the NDVI between the late vegetative and the early generative stages (r = 0.80–0.84). The findings suggest that the NDVI dynamics is an adequate indicator for evaluating the impact of different treatments on plant development and yield prediction.

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 CARBATCLIM 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 Y_lossAD 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 $\mathrm{SRAg}.{\mathrm{D}}_x$ < 1. To cope with climate change in Hungary, an urgent mitigation plan should be implemented.

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 (p_i, P_total) (mm), daily maximum precipitation (P_d-max) (mm), monthly mean temperature (T_avg) (°C), daily maximum mean temperature (T_d-max) (°C), and daily minimum mean temperature (T_d-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 (NSE_{Budapest(SC3)} = 0.71, NSE_Pécs(SC2) = 0.69). Additionally, the performance of RBF was accurate (NSE_{Debrecen(SC4)} = 0.68, NSE_Pécs(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 (P_d-max + p_i + P_total) and SC4 (P_total + T_avg + T_d-max + T_d-min) as the best scenarios for predicting MFI by using the ANN–MLP and ANN–RBF, respectively. However, the sensitivity analysis highlighted that P_total, p_i, and T_d-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.