Determination of genetic diversity and population structure of breeding material is an important prerequisite for discovering novel and valuable alleles aimed at crop improvement. This study’s main objective was to characterize genetic diversity and population structure of a collection representing a 40-year long historical period of barley (Hordeum vulgare L.) breeding, using microsatellites, pedigree, and phenotypic data. The set of 90 barley genotypes was phenotyped during three growing seasons and genotyped with 338 polymorphic alleles. The indicators of genetic diversity showed differentiation changes throughout the breeding periods. The population structure discriminated the breeding material into three distinctive groups. The principal coordinate analysis grouped the genotypes according to their growth habit and row type. An analysis of phenotypic variance (ANOVA) showed that almost all investigated traits varied significantly between row types, seasons, and breeding periods. A positive effect on yield progress during the 40-year long breeding period could be partly attributed to breeding for shorter plants, which reduced lodging and thus provided higher yield stability. The breeding material revealed a considerable diversity level based on microsatellite and phenotypic data without a tendency of genetic erosion throughout the breeding history and implied dynamic changes in genetic backgrounds, providing a great gene pool suitable for further barley improvement.

The study was based on data from selected long-term field trials established at the Experimental Fields of the Institute of Field and Vegetable Crops, Novi Sad (Serbia). The effect of tillage systems on SOC concentration and SOC stock was most pronounced at 0–10 cm depth. In a 0–40 cm soil layer, in a 7-year period, no-till (NT) sequestrated 863 kg SOC ha⁻¹ yr⁻¹ more compared to moldboard plow tillage (PT), while the effects of disc tillage (DT) and chisel tillage (CT) were not significantly different. Unfertilized three-crop rotation (CSW) compared to two-crop rotation (CW) enhanced SOC storage in a 0–30 cm soil layer by 151 kg C ha⁻¹ yr⁻¹ in a 56-year period. Within fertilized treatments, SOC concentration was highest under continuous corn (CC). Mineral fertilization (F) non-significantly increased the SOC stock compared to no fertilization in corn monoculture in a 32-year period. The incorporation of mineral fertilizers and harvest residues (F + HR) and mineral fertilizers and farmyard manure (F + FYM) sequestered 195 and 435 kg C ha⁻¹ yr⁻¹ more than the unfertilized plot, respectively, in a 0–30 cm soil layer, in a 35-year period. Irrigation did not significantly affect SOC sequestration.

The study, conducted to evaluate the effects of long-term straw management combined with the application of increasing nitrogen rates on the yield of twenty winter wheat varieties, as well as on soil properties, was carried out in a long-term field trial established in 1971. The trial was monitored for twenty growing seasons under rainfed conditions in a typical chernozem zone of the southern part of the Pannonian Plain. The cropping system was a winter wheat-maize-soybean rotation. The ten SN-treatments (combinations of straw management (S) and N-fertilization) were as follows: In the plot (treatment) with straw return (S₁), seven variants of nitrogen fertilization (0–180 kg N ha⁻¹) were included, while on the plot without straw return (S₀) the variants of N-fertilization were 0, 90 and 150 kg N ha^−l. Based on the high relative share in the total sum of squares, variance analysis showed that wheat grain yield (GY) was significantly affected by years, SN-treatments, and their interaction, and they can explain the largest part of the total variance of GY. The results showed that straw return integrated with N fertilization could increase wheat yield to varying degrees over 20 years. On average, for all years, the highest GYs were obtained in the treatment S₁ and fertilization with 180 and 150 kg N ha⁻¹. The overall results showed that long-term straw returning significantly increased GY by an average of 8.4 ± 4.5%, with a considerable simultaneous increase in yield stability compared to straw removal. In addition, straw incorporation (SI) significantly increased soil humus, total nitrogen (TN), and soil organic carbon (SOC) contents at a soil depth of 0–30 cm by an average of 4.2, 3.8, and 11.3%, respectively. The results of our study have demonstrated that the long-term practice of straw return, in combination with the application of mineral fertilizers, has the potential to serve as a sustainable soil management strategy that is economically viable and environmentally acceptable. However, additional research is required to investigate its interactive effects on both grain yield and soil productivity.

Accurate and timely wheat yield prediction is valuable globally for enhancing agricultural planning, optimizing resource use, and supporting trade strategies. Study addresses the need for precision in yield estimation by applying machine-learning (ML) regression models to high-resolution Unmanned Aerial Vehicle (UAV) multispectral (MS) and Red-Green-Blue (RGB) imagery. Research analyzes five European wheat cultivars across 400 experimental plots created by combining 20 nitrogen, phosphorus, and potassium (NPK) fertilizer treatments. Yield variations from 1.41 to 6.42 t/ha strengthen model robustness with diverse data. The ML approach is automated using PyCaret, which optimized and evaluated 25 regression models based on 65 vegetation indices and yield data, resulting in 66 feature variables across 400 observations. The dataset, split into training (70%) and testing sets (30%), was used to predict yields at three growth stages: 9 May, 20 May, and 6 June 2022. Key models achieved high accuracy, with the Support Vector Regression (SVR) model reaching R² = 0.95 on 9 May and R² = 0.91 on 6 June, and the Multi-Layer Perceptron (MLP) Regressor attaining R² = 0.94 on 20 May. The findings underscore the effectiveness of precisely measured MS indices and a rigorous experimental approach in achieving high-accuracy yield predictions. This study demonstrates how a precise experimental setup, large-scale field data, and AutoML can harness UAV and machine learning’s potential to enhance wheat yield predictions. The main limitations of this study lie in its focus on experimental fields under specific conditions; future research could explore adaptability to diverse environments and wheat varieties for broader applicability.