Filters
Genotype-Trait (GT) Biplot Analysis for Yield and Quality Stability in Some Sweet Corn (Zea mays L. saccharata Sturt.) Genotypes
A strong statistical method for investigating the correlations between traits, assessing genotypes based on numerous traits, and finding individuals who excel in particular traits is genotype–trait (GT) biplot analysis. The current study was applied to evaluate 11 sweet corn (Zea mays L. saccharata) genotypes and correlate them based on genotype–trait (GT) biplot analysis for two cropping seasons in Erzurum, Türkiye using the RCBD experimental design with three reputations. The results showed that the genotypes were significantly different for the majority of the examined variables according to the combined analysis of variance findings at 0.01 probability level. An ecological analysis was performed to evaluate sweet corn varieties and environmental conditions and interactions between them (genotype × environmental conditions). Our results showed that the summation of the first two and second main components was responsible for 73.51% of the combined cropping years of the sweet corn growth and development variance, demonstrating the biplot graph’s optimum relative validity, which was obtained. In this study, the Khan F1 (G6) genotype was found to be the stablest genotype, and the Kompozit Seker (G7) genotype was the non-stable genotype, moreover based on the first cropping year, second cropping year, and the average mean of the two cropping years. As a conclusion, the Khan F1 (G6) genotype is the highest-yielding genotype, and the Kompozit Seker (G7) is the lowest. Based on the heat map dendrogram, the context of the differential extent of trait association of all genotypes into two clusters is indicated. The highest genetic distance was shown between the BATEM Tatlı (G3) and Febris (G5) genotypes. Our results provide helpful information about the sweet corn genotypes and environments for future breeding programs.
Prediction of Blueberry (Vaccinium corymbosum L.) Yield Based on Artificial Intelligence Methods
In this paper, we present a high-accuracy model for blueberry yield prediction, trained using structurally innovative data sets. Blueberries are blooming plants, valued for their antioxidant and anti-inflammatory properties. Yield on the plantations depends on several factors, both internal and external. Predicting the accurate amount of harvest is an important aspect in work planning and storage space selection. Machine learning algorithms are commonly used in such prediction tasks, since they are capable of finding correlations between various factors at play. Overall data were collected from years 2016–2021, and included agronomic, climatic and soil data as well satellite-imaging vegetation data. Additionally, growing periods according to BBCH scale and aggregates were taken into account. After extensive data preprocessing and obtaining cumulative features, a total of 11 models were trained and evaluated. Chosen classifiers were selected from state-of-the-art methods in similar applications. To evaluate the results, Mean Absolute Percentage Error was chosen. It is superior to alternatives, since it takes into account absolute values, negating the risk that opposite variables will cancel out, while the final result outlines percentage difference between the actual value and prediction. Regarding the research presented, the best performing solution proved to be Extreme Gradient Boosting algorithm, with MAPE value equal to 12.48%. This result meets the requirements of practical applications, with sufficient accuracy to improve the overall yield management process. Due to the nature of machine learning methodology, the presented solution can be further improved with annually collected data.
Estimating Energy Consumption During Soil Cultivation Using Geophysical Scanning and Machine Learning Methods
The agricultural sector is one of the most significant sectors of the global economy, yet it is concurrently a highly energy-intensive industry. The issue of optimizing field operations in terms of energy consumption is therefore a key consideration for sustainable agriculture, and the solution to this issue leads to both environmental and financial benefits. The aim of this study was to estimate energy consumption during soil cultivation using geophysical scanning data and machine learning (ML) algorithms. This included determining the optimal set of independent variables and the most suitable ML method. Soil parameters such as electrical conductivity, magnetic susceptibility, and soil reflectance in infrared spectra were mapped using data from Geonics EM-38 and Veris 3100 scanners. These data, along with soil texture, served as inputs for predicting fuel consumption and field productivity. Three machine learning algorithms were tested: support vector machines (SVMs), multilayer perceptron (MLP), and radial basis function (RBF) neural networks. Among these, SVM achieved the best performance, showing a MAPE of 4% and a strong correlation (R = 0.97) between predicted and actual productivity values. For fuel consumption, the optimal method was MLP (MAPE = 4% and R = 0.63). The findings demonstrate the viability of geophysical scanning and machine learning for accurately predicting energy use in tillage operations. This approach supports more sustainable agriculture by enabling optimized fuel use and reducing environmental impact through data-driven field management. Further research is needed to obtain training data for different soil parameters and agrotechnical treatments in order to develop more universal models.
Somaclonal Variation for Genetic Improvement of Starch Accumulation in Potato (Solanum tuberosum) Tubers
Starch content is one of the major quality criteria targeted by potato breeding programs. Traditional potato breeding is a laborious duty due to the tetraploid nature and immense heterozygosity of potato genomes. In addition, screening for functional genetic variations in wild relatives is slow and strenuous. Moreover, genetic diversity, which is the raw material for breeding programs, is limited due to vegetative propagation used in the potato industry. Somaclonal variation provides a time-efficient tool to breeders for obtaining genetic variability, which is essential for breeding programs, at a reasonable cost and independent of sophisticated technology. The present investigation aimed to create potato somaclones with an improved potential for starch accumulation. Based on the weight and starch content of tubers, the somaclonal variant Ros 119, among 105 callus-sourced clones, recorded a higher tuberization potential than the parent cv Lady Rosetta in a field experiment. Although this somaclone was similar to the parent in the number of tubers produced, it exhibited tubers with 42 and 61% higher fresh and dry weights, respectively. Additionally, this clone recorded 10 and 75% increases in starch content based on the dry weight and average content per plant, respectively. The enhanced starch accumulation was associated with the upregulation of six starch-synthesis-related genes, namely, the AGPase, GBSS I, SBE I, SBE II, SS II and SS III genes. AGPase affords the glycosyl moieties required for the synthesis of amylose and amylopectin. GBSS is required for amylose elongation, while SBE I, SBE II, SS II and SS III are responsible for amylopectin.
Combining Machine Learning Algorithms with Earth Observations for Crop Monitoring and Management
Combining machine learning algorithms with Earth observations has great potential in the context of crop monitoring and management, which is essential in the face of global challenges related to food security and climate change [...]
Connecting the dots to unleash the innovation potential for digital transformation of the European agri-food sector
Genetic Diversity and Population Structure in Bread Wheat Germplasm from Türkiye Using iPBS-Retrotransposons-Based Markers
This study investigated the genetic diversity and population structure of 63 genotypes from Turkish bread wheat germplasm using iPBS-retrotransposons primers. The thirty-four iPBS primers produced a total of 1231 polymorphic bands, ranging from 8 (iPBS-2375) to 60 (iPBS-2381) alleles per marker, with an average number of 36.00 alleles. The polymorphism information content (PIC) per marker varied between 0.048 (iPBS 2087) and 0.303 (iPBS 2382), with an average of 0.175. The numbers of effective alleles (ne), genetic diversity of Nei (h), and Shannon’s information index (I) value were calculated as 1.157, 0.95, and 0.144, respectively. The greatest genetic distance (0.164) was between Eastern Anatolia Agricultural Research Institute genotypes and Çukurova Agricultural Research Institute genotypes. The unweighted pair-group method with arithmetic mean (UPGMA) dendrogram placed the 63 wheat genotypes into three clusters. The percentage of genetic diversity explained by each of the three main coordinates of the basic coordinate analysis was determined to be 44.58, 12.08, and 3.44, respectively. AMOVA (Analysis of Molecular Variance) showed that the variation within populations was 99% and that between populations was 1%. The result of genetic structure analysis suggests that the greatest value of K was calculated as 3. The F-statistic (Fst) value was determined as 0.4005, 0.2374, and 0.3773 in the first to third subpopulations, respectively. Likewise, the expected heterozygosity values (He) were determined as 0.2203, 0.2599, and 0.2155 in the first, second, and third subpopulations, respectively. According to the information obtained in the study, the most genetically distant genotypes were the G1 (Aksel 2000) and G63 (Karasu 90) genotypes. This study provided a deep insight into genetic variations in Turkish bread wheat germplasm using the iPBS-retrotransposons marker system.
Digital Repeat Photography Application for Flowering Stage Classification of Selected Woody Plants
Digital repeat photography is currently applied mainly in geophysical studies of ecosystems. However, its role as a tool that can be utilized in conventional phenology, tracking a plant’s seasonal developmental cycle, is growing. This study’s main goal was to develop an easy-to-reproduce, single-camera-based novel approach to determine the flowering phases of 12 woody plants of various deciduous species. Field observations served as binary class calibration datasets (flowering and non-flowering stages). All the image RGB parameters, designated for each plant separately, were used as plant features for the models’ parametrization. The training data were subjected to various transformations to achieve the best classifications using the weighted k-nearest neighbors algorithm. The developed models enabled the flowering classifications at the 0, 1, 2, 3, and 5 onset day shift (absolute values) for 2, 3, 3, 2, and 2 plants, respectively. For 9 plants, the presented method enabled the flowering duration estimation, which is a valuable yet rarely used parameter in conventional phenological studies. We found the presented method suitable for various plants, despite their petal color and flower size, until there is a considerable change in the crown color during the flowering stage.
Predicting Starch Content in Early Potato Varieties Using Neural Networks and Regression Models: A Comparative Study
Starch content serves as a crucial indicator of the quality and palatability of potato tubers. It has become a common practice to evaluate the polysaccharide content directly in tubers freshly harvested from the field. This study aims to develop models that can predict starch content prior to the harvesting of potato tubers. Very early potato varieties were cultivated in the northern and northwestern regions of Poland. The research involved constructing multiple linear regression (MLR) and artificial neural network (ANN-MLP) models, drawing on data from eight years of field trials. The independent variables included factors such as sunshine duration, average daily air temperatures, precipitation, soil nutrient levels, and phytophenological data. The NSM demonstrated a higher accuracy in predicting the dependent variable compared to the RSM, with MAPE errors of 7.258% and 9.825%, respectively. This study confirms that artificial neural networks are an effective tool for predicting starch content in very early potato varieties, making them valuable for monitoring potato quality.
Insights into Drought Tolerance of Tetraploid Wheat Genotypes in the Germination Stage Using Machine Learning Algorithms
Throughout germination, which represents the initial and crucial phase of the wheat life cycle, the plant is notably susceptible to the adverse effects of drought. The identification and selection of genotypes exhibiting heightened drought tolerance stand as pivotal strategies aimed at mitigating these effects. For the stated objective, this study sought to evaluate the responses of distinct wheat genotypes to diverse levels of drought stress encountered during the germination stage. The induction of drought stress was achieved using polyethylene glycol at varying concentrations, and the assessment was conducted through the application of multivariate analysis and machine learning algorithms. Statistical significance (p < 0.01) was observed in the differences among genotypes, stress levels, and their interaction. The ranking of genotypes based on tolerance indicators was evident through a principal component analysis and biplot graphs utilizing germination traits and stress tolerance indices. The drought responses of wheat genotypes were modeled using germination data. Predictions were then generated using four distinct machine learning techniques. An evaluation based on R-square, mean square error, and mean absolute deviation metrics indicated the superior performance of the elastic-net model in estimating germination speed, germination power, and water absorption capacity. Additionally, in assessing the criterion metrics, it was determined that the Gaussian processes classifier exhibited a better performance in estimating root length, while the extreme gradient boosting model demonstrated superior performance in estimating shoot length, fresh weight, and dry weight. The study’s findings underscore that drought tolerance, susceptibility levels, and parameter estimation for durum wheat and similar plants can be reliably and efficiently determined through the applied methods and analyses, offering a fast and cost-effective approach.
Prediction of Potato (Solanum tuberosum L.) Yield Based on Machine Learning Methods
This research delves into the application of machine learning methods for predicting the yield of potato varieties used for French fries in Poland. By integrating a comprehensive dataset comprising agronomical, climatic, soil, and satellite-based vegetation data from 36 commercial potato fields over five growing seasons (2018–2022), we developed three distinct models: non-satellite, satellite, and hybrid. The non-satellite model, relying on 85 features, excludes vegetation indices, whereas the satellite model includes these indices within its 128 features. The hybrid model, combining all available features, encompasses a total of 165 features, presenting the most-comprehensive approach. Our findings revealed that the hybrid model, particularly when enhanced with SVM outlier detection, exhibited superior performance with the lowest Mean Absolute Percentage Error (MAPE) of 5.85%, underscoring the effectiveness of integrating diverse data sources into agricultural yield prediction. In contrast, the non-satellite and satellite models displayed higher MAPE values, indicating less accuracy compared to the hybrid model. Advanced data-processing techniques such as PCA and outlier detection methods (LOF and One-Class SVM) played a pivotal role in model performance, optimising feature selection and dataset refinement. The study concluded that machine learning methods, particularly when leveraging a multifaceted approach involving a wide array of data sources and advanced processing techniques, can significantly enhance the accuracy of agricultural yield predictions. These insights pave the way for more-efficient and -informed agricultural practices, emphasising the potential of machine learning in revolutionising yield prediction and crop management.
A Framework for Financing Post-Registration Variety Testing System: A Case Study from Poland
Agriculture is essential to ensuring food security and prosperity around the world. The importance of cultivating agricultural plant species cannot be overestimated. One of the key challenges faced by modern food producers is to increase efficiency while ensuring sustainability and improving resilience to unfavorable environmental conditions brought about by ongoing climate change. To meet these challenges, it is vital to continue breeding work and to select plant varieties best adapted to local farming conditions. Undoubtedly, future yield increases will only be achievable by way of genetic improvement. In turn, crop-variety recommendations should rely on the results of properly designed post-registration variety testing (PRVT, in polish PDO), followed up by specific variety recommendations for growers. In this article, we attempt to fill a gap in the international literature regarding post-registration variety testing. We present PRVT as a unique scheme that is key to selecting agricultural plant varieties recommended for cultivation, with due account taken of Poland’s specific farming conditions. Every year, over 1000 field cultivar tests are carried out as part of PRVT. The results of these tests constitute reliable, objective source material for farmers and help them make choices regarding the most valuable varieties for cultivation that are also best adapted to local farming conditions. Among the financial benefits of selecting the right crop varieties for agriculture are lower cultivation costs, including reduced fertilizer and pesticide spending, and higher income generated by larger yields.
Comparative Evaluation of CNN and Transformer Architectures for Flowering Phase Classification of Tilia cordata Mill. with Automated Image Quality Filtering
Understanding and monitoring the phenological phases of trees is essential for ecological research and climate change studies. In this work, we present a comprehensive evaluation of state-of-the-art convolutional neural networks (CNNs) and transformer architectures for the automated classification of the flowering phase of Tilia cordata Mill. (small-leaved lime) based on a large set of real-world images acquired under natural field conditions. The study introduces a novel, automated image quality filtering approach using an XGBoost classifier trained on diverse exposure and sharpness features to ensure robust input data for subsequent deep learning models. Seven modern neural network architectures, including VGG16, ResNet50, EfficientNetB3, MobileNetV3 Large, ConvNeXt Tiny, Vision Transformer (ViT-B/16), and Swin Transformer Tiny, were fine-tuned and evaluated under a rigorous cross-validation protocol. All models achieved excellent performance, with cross-validated F1-scores exceeding 0.97 and balanced accuracy up to 0.993. The best results were obtained for ResNet50 and ConvNeXt Tiny (F1-score: 0.9879 ± 0.0077 and 0.9860 ± 0.0073, balanced accuracy: 0.9922 ± 0.0054 and 0.9927 ± 0.0042, respectively), indicating outstanding sensitivity and specificity for both flowering and non-flowering classes. Classical CNNs (VGG16, ResNet50, and ConvNeXt Tiny) demonstrated slightly superior robustness compared to transformer-based models, though all architectures maintained high generalization and minimal variance across folds. The integrated quality assessment and classification pipeline enables scalable, high-throughput monitoring of flowering phases in natural environments. The proposed methodology is adaptable to other plant species and locations, supporting future ecological monitoring and climate studies. Our key contributions are as follows: (i) introducing an automated exposure-quality filtering stage for field imagery; (ii) publishing a curated, season-long dataset of Tilia cordata images; and (iii) providing the first systematic cross-validated benchmark that contrasts classical CNNs with transformer architectures for phenological phase recognition.
New Developments in Smart Farming Applied in Sustainable Agriculture
Sustainable agriculture aims to increase agricultural productivity while minimising negative environmental impacts [...]
Predictions and Estimations in Agricultural Production under a Changing Climate
In the 21st century, agriculture is facing numerous challenges [...]
Tworzenie połączeń w celu uwolnienia potencjału innowacyjnego w zakresie cyfrowej transformacji europejskiego sektora rolno-spożywczego
Application of Artificial Neural Networks Sensitivity Analysis for the Pre-Identification of Highly Significant Factors Influencing the Yield and Digestibility of Grassland Sward in the Climatic Conditions of Central Poland
Progressive climate changes are the most important challenges for modern agriculture. Permanent grassland represents around 70% of all agricultural land. In comparison with other agroecosystems, grasslands are more sensitive to climate change. The aim of this study was to create deterministic models based on artificial neural networks to identify highly significant factors influencing the yield and digestibility of grassland sward in the climatic conditions of central Poland. The models were based on data from a grassland experiment conducted between 2014 and 2016. Phytophenological data (harvest date and botanical composition of sward) and meteorological data (average temperatures, total rainfall, and total effective temperatures) were used as independent variables, whereas qualitative and quantitative parameters of the feed made from the grassland sward (dry matter digestibility, dry matter yield, and protein yield) were used as dependent variables. Nine deterministic models were proposed Y_G, DIG_G, P_G, Y_GB, DIG_GB, P_GB, Y_GC, DIG_GC, and P_GC, which differed in the input variable and the main factor from the grassland experiment. The analysis of the sensitivity of the neural networks in the models enabled the identification of the independent variables with the greatest influence on the yield of dry matter and protein as well as the digestibility of the dry matter of the first regrowth of grassland sward, taking its diverse botanical composition into account. The results showed that the following factors were the most significant (rank 1): the average daily air temperature, total rainfall, and the percentage of legume plants. This research will be continued on a larger group of factors influencing the output variables and it will involve an attempt to optimise these factors.
Exploring Digital Innovations in Agriculture: A Pathway to Sustainable Food Production and Resource Management
Today’s agriculture faces numerous challenges due to climate change, a growing population and the need to increase food productivity [...]
Application of Artificial Neural Network Sensitivity Analysis to Identify Key Determinants of Harvesting Date and Yield of Soybean (Glycine max [L.] Merrill) Cultivar Augusta
Genotype and weather conditions play crucial roles in determining the volume and stability of a soybean yield. The aim of this study was to identify the key meteorological factors affecting the harvest date (model M_HARV) and yield of the soybean variety Augusta (model M_YIELD) using a neural network sensitivity analysis. The dates of the start of flowering and maturity, the yield data, the average daily temperatures and precipitation were collected, and the Selyaninov hydrothermal coefficients were calculated during a fifteen-year study (2005–2020 growing seasons). During the experiment, highly variable weather conditions occurred, strongly modifying the course of phenological phases in soybean and the achieved seed yield of Augusta cultivar. The harvesting of mature soybean seeds took place between 131 and 156 days after sowing, while the harvested yield ranged from 0.6 t·ha−1 to 2.6 t·ha−1. The sensitivity analysis of the MLP neural network made it possible to identify the factors which had the greatest impact on the tested dependent variables among all the analyzed factors. It was revealed that the variables assigned ranks 1 and 2 in the sensitivity analysis of the neural network forming the M_HARV model were total rainfall in the first decade of June and the first decade of August. The variables with the highest impact on the Augusta soybean seed yield (model M_YIELD) were the mean daily air temperature in the second decade of May and the Seljaninov coefficient values calculated for the sowing–flowering date period.
Correction: Helal et al. Improving Yield Components and Desirable Eating Quality of Two Wheat Genotypes Using Si and NanoSi Particles under Heat Stress. Plants 2022, 11, 1819
In the original publication [...]
