Search Results (95)

Rice, as one of the world’s four major staple crops, is frequently threatened by pests and diseases during its growth. With the rapid expansion of agricultural information data, the effective management and utilization of such data have become crucial for the development of agricultural informatization. Named entity recognition technology offers precise support for the early prevention and control of crop pests and diseases. However, entity recognition for rice pests and diseases faces challenges such as structural complexity and prevalent nesting issues. Inspired by biological visual mechanisms, we propose a deep learning model capable of extracting multi-granularity features. Text representations are encoded using BERT, and the model enhances its ability to capture nested boundary information through multi-granularity convolutional neural networks (CNNs). Finally, sequence modeling and labeling are performed using a bidirectional long short-term memory network (BiLSTM) combined with a conditional random field (CRF). Experimental results demonstrate that the proposed model effectively identifies entities related to rice diseases and pests, achieving an F1 score of 91.74% on a self-constructed dataset. Full article

Winter wheat is a major staple crop worldwide, and real-time monitoring of soil moisture content (SMC) is critical for yield security. Targeting the monitoring needs under arid conditions in southern Xinjiang, this study proposes a UAV multispectral-based SMC estimation method that constructs novel three-dimensional (3-D) texture indices. Field experiments were conducted over two consecutive growing seasons in Kunyu City, southern Xinjiang, China, with four irrigation and four fertilization levels. High-resolution multispectral imagery was acquired at the jointing stage using a UAV-mounted camera. From the imagery, conventional texture features were extracted, and six two-dimensional (2-D) and four 3-D texture indices were constructed. A correlation matrix approach was used to screen feature combinations significantly associated with SMC. Random forest (RF), partial least squares regression (PLSR), and back-propagation neural networks (BPNN) were then used to develop SMC models for three soil depths (0–20, 20–40, and 40–60 cm). Results showed that estimation accuracy for the shallow layer (0–20 cm) was markedly higher than for the middle and deep layers. Under single-source input, using 3-D texture indices (Combination 3) with RF achieved the best shallow-layer performance (validation R² = 0.827, RMSE = 0.534, MRE = 2.686%). With multi-source fusion inputs (Combination 7: texture features + 2-D texture indices + 3-D texture indices) combined with RF, shallow-layer SMC estimation further improved (R² = 0.890, RMSE = 0.395, MRE = 1.91%). Relative to models using only conventional texture features, fusion increased R² by approximately 11.4%, 11.7%, and 18.1% for the shallow, middle, and deep layers, respectively. The findings indicate that 3-D texture indices (e.g., DTTI), which integrate multi-band texture information, more comprehensively capture canopy spatial structure and are more sensitive to shallow-layer moisture dynamics. Multi-source fusion provides complementary information and substantially enhances model accuracy. The proposed approach offers a new pathway for accurate SMC monitoring in arid croplands and is of practical significance for remote sensing-based moisture estimation and precision irrigation. Full article

Global food security is increasingly challenged by climate change and the availability of arable land. This situation calls for improved crop monitoring and management strategies. Rice is a staple food for nearly half of the world’s population and a significant source of calories. Accurately identifying rice varieties is crucial for maintaining varietal purity, planning agricultural activities, and enhancing genetic improvement strategies. This study evaluates the effectiveness of machine learning algorithms to identify the most effective approach to predicting rice varieties, using multitemporal Sentinel-2 images in the Marismas del Guadalquivir of Sevilla, Spain. Spectral reflectance data were collected from ten Sentinel-2 bands, which include visible, red-edge, near-infrared, and shortwave infrared regions, at two key phenological stages: tillering and reproduction. The models were trained on pixel-level data from the growing seasons of 2021 and 2024, and they were evaluated using a test set from 2022. Four classifiers were compared: random forest, XGBoost, K-nearest neighbors, and logistic regression. Performance was assessed based on accuracy, precision, recall, specificity and F1 score. Non-linear models outperformed linear ones. The highest performance was achieved with the Random Forest classifier during the reproduction phase, reaching an exceptional accuracy of 0.94 using all bands or only the most informative subset (red edge, NIR, and SWIR). This classifier also maintained excellent accuracy (0.93 and 0.92) during the initial tillering phase. This fact demonstrates that it is possible to perform reliable varietal mapping in the early stages of the growing season. Full article

Wheat is a staple crop widely sown in Northwest China, and understanding and modelling evapotranspiration (ET) during the wheat-growing stage is important for irrigation scheduling and the efficient use of agricultural water resources. In this study, a four-year observation was conducted on a spring wheat field with border irrigation (BI) treatment and drip irrigation (DI) treatment, based on two Bowen ratio energy balance (BREB) systems. The results showed that the average ET across the whole growing stage scale was 512.0 mm for the BI treatment and 446.9 mm for the DI treatment, and the DI treatment reduced ET by 65.1 mm across the growing stage scale. The driving factors of the changes in ET in the two treatments were investigated using partial correlation analysis after understanding the changing pattern of ET. Net radiation (Rn), soil water content (SWC), and leaf area index (LAI) were the main meteorological, soil, and crop factors leading to the changes in ET in the two treatments. In terms of ET simulation, the SWAP model and different types of machine learning algorithms were used in this study to numerically simulate ET at a daily scale. The total ET values simulated by the SWAP model at the interannual scale were 11.0–14.2% lower than the observed values of ET, and the simulation accuracy varied at different growing stages. In terms of the machine learning simulation of ET, this study is the first to apply five machine learning algorithms to simulate a typical irrigated wheat field in the arid region of Northwest China. It was found that the Stacking algorithm as well as the SWAP model had the optimal simulation among all machine learning algorithms. These findings can provide a scientific basis for irrigation management and the efficient use of agricultural water resources in spring wheat fields in arid regions. Full article

Rice is a staple food for over half of the world’s population, and it is grown in over 100 countries. Rice blast disease can cause 10% to 30% crop loss, enough to feed 60 million people. Breeding for resistance can help farmers avoid costly fungicides. This study assessed the relationship between rice blast disease and zinc or anthocyanin content in biofortified rice. Susceptibility to foliar and panicle blast was assessed in a rice panel which differed on grain zinc content and pigmentation. A rice panel (n = 23) was challenged with inoculum of two isolates of Magnaporthe oryzae in a screenhouse-based assay. The zinc content with foliar blast severity was analyzed in the leaves and grain of a subset of non-inoculated rice plants. The effect of foliar zinc supplementation on seedlings was assessed by varying levels of zinc fertilizer solution on four blast susceptible cultivars at 14 days after planting (DAP), followed by inoculation with the blast pathogen at 21 DAP. Foliar blast severity was scored on a 0–9 scale at 7 days after inoculation. The rice panel was scored for anthocyanin content, and the data were correlated with foliar blast severity. The panel was grown in the field, and panicle blast, grain yield and yield-related agronomic traits were measured. Significant differences were observed in foliar blast severity among the rice genotypes, with IRBLK-KA and IR96248-16-2-3-3-B having mean scores greater than 4, as well as BASMATI 370 (a popular aromatic variety), while the rest of the genotypes were resistant. Supplementation with foliar zinc led to a significant decrease in susceptibility. A positive correlation was observed between foliar and panicle blast. The Zn in the leaves was negatively correlated with foliar blast severity, and had a marginally positive correlation with panicle blast. There was no relationship between foliar blast severity and anthocyanin content. Grain yield had a negative correlation with panicle blast, but no correlation was observed between Zn in the grain and grain yield. This study shows that Zn biofortification in the grain may not enhance resistance to foliar and panicle blast. Furthermore, the zinc-biofortified genotypes were not agronomically superior to the contemporary rice varieties. There is a need to apply genomic selection to combine promising alleles into adapted rice genetic backgrounds. Full article

Potatoes, as the world’s fourth-largest staple crop, are vital for global food security. Efficient methods for assessing yield and quality are essential for policy-making and optimizing production. Traditional yield assessment techniques remain destructive, labor-intensive, and unsuitable for large-scale monitoring. While remote sensing has offered a promising alternative, current approaches largely depend on empirical correlations rather than physiological mechanisms. This limitation arises because potato tubers grow underground, rendering their traits invisible to aboveground sensors. This study investigated the mechanisms underlying hyperspectral remote sensing for assessing belowground yield traits in potatoes. Field experiments with four cultivars and five nitrogen treatments were conducted to collect foliar biochemistries (chlorophyll, nitrogen, and water and dry matter content), yield traits (tuber yield, fresh/dry weight, starch, protein, and water content), and leaf spectra. Two approaches were developed for predicting belowground yield traits: (1) a direct method linking leaf spectra to yield via statistical models and (2) an indirect method using structural equation modeling (SEM) to link foliar biochemistry to yield. The SEM analysis revealed that foliar nitrogen exhibited negative effects on tuber fresh weight (path coefficient b = −0.57), yield (−0.37), and starch content (−0.30). Similarly, leaf water content negatively influenced tuber water content (0.52), protein (−0.27), and dry weight (−0.42). Conversely, chlorophyll content showed positive associations with both tuber protein (0.59) and dry weight (0.56). Direct models (PLSR, SVR, and RFR) achieved higher accuracy for yield (R² = 0.58–0.84) than indirect approaches (R² = 0.16–0.45), though the latter provided physiological insights. The reduced accuracy in indirect methods primarily stemmed from error propagation within the SEM framework. Future research should scale these leaf-level mechanisms to canopy observations and integrate crop growth models to improve robustness across environments. This work advances precision agriculture by clarifying spectral–yield linkages in potato systems, offering a framework for hyperspectral-based yield prediction. Full article

Maize is one of the top five field crops worldwide and is indispensable as animal feed, serves as a raw material in many industries, and is a staple for human food. However, its production is under increasing pressure mainly due to abiotic stress. Drought and excessive precipitation, air temperature fluctuations, and reduced soil fertility due to inadequate soil pH reactions are among the biggest challenges that must be overcome. Therefore, the goal of this study was to determine the effects of these combined stressful abiotic conditions on maize grain yield and quality and to determine the genetic-specific response of maize genotypes in such conditions. The experiment was set up in eastern Croatia according to the randomized complete block design in four replications. A total of 10 maize hybrids of different FAO maturity groups were evaluated across four diverse environments, each subjected to one or two abiotic stresses (extreme precipitation, drought, high air temperatures, and acidic soil). Analysis of variance revealed that all treatment effects were statistically significant, except for the effect of hybrids on grain yield. Depending on the effect of abiotic stress, the variations among environments were up to 51.4% for yield and up to 12.1%, 18.9%, and 0.81% for protein, oil, and starch content, respectively. Differences among hybrids were less pronounced for yield (7.9%), while for protein (13.5%), oil (17.3%), and starch content (1.5%) were similar. However, the largest variation was found for the interaction effect. In the conducted research, ENV2 recorded the highest grain yield, along with the highest oil and starch content, as well as the second-highest protein content, while the hybrid effect remained unclear. Generally, ENV4 had the greatest negative impact due to the combined effects of extreme abiotic stresses, including soil acidity, drought, and high air temperatures. Full article

Yam is a staple crop in Africa that is constrained by its low multiplication rate. This results in a short supply of seed tubers, which is a challenge to increased production. This study assessed the influence of different minisett weights (10, 20, 30, 40, and 50 g) on tuber production and seed categorization in twelve Dioscorea rotundata and four Dioscorea alata varieties over two planting seasons in a Randomized Complete Block Design (r = 3). The yield parameters were collected and analyzed using ANOVA. The effects of varieties, the minisett weight (SW), and the variety × SW interaction were significant for the proportion of setts that produced seed tubers and ranged from 40.2 ± 5.0% (50 g) to 56.4 ± 5.0% (10 g) in 2013, from 46.4 ± 0.8% (40 g) to 60.5 ± 0.8% (30 g) in 2014, from 23% (TDa00/00194, 30 g) to 93.7% (Ojuyawo, 10 g) in 2013, and from 39.7% (TDa00/00194, 30 g) to 100% (TDr89/02665, 20 g) in 2014. The 10 g and 30 g produced more seed yam in 2013 and 2014, respectively, while 50 g produced more ware yam sizes (>300 g) and is thus recommended to farmers for intended yam production category. D. rotundata varieties produced a higher proportion of seed yam, while D. alata varieties produced are a higher proportion of yams above seed class. Full article

Plant modeling uses mathematical and computational methods to simulate plant structures, physiological processes, and interactions with various environments. In precision agriculture, it enables the digital monitoring and prediction of crop growth, supporting better management and efficient resource use. Wheat, as a major global staple, is vital for food security. However, wheat stripe rust, a widespread and destructive disease, threatens yield stability. The paper proposes wheat cultivation suitability evaluation with stripe rust disease using an agriculture group consensus framework (WCSE-AGC) to tackle this issue. Assessing stripe rust severity in regions relies on wheat pathologists’ judgments based on multiple criteria, creating a multi-attribute, multi-decision-maker consensus problem. Limited regional coverage and inconsistent evaluations among wheat pathologists complicate consensus-reaching. To support wheat pathologist participation, this study employs artificial-intelligence-generated content (AIGC) techniques by using Claude 3.7 to simulate wheat pathologists’ scoring through role-playing and chain-of-thought prompting. WCSE-AGC comprises three main stages. First, a graph neural network (GNN) models trust propagation within wheat pathologists’ social networks, completing missing trust links and providing a solid foundation for weighting and clustering. This ensures reliable expert influence estimations. Second, integrating secretary bird optimization (SBO), K-means, and three-way clustering detects overlapping wheat pathologist subgroups, reducing opinion divergence and improving consensus inclusiveness and convergence. Third, a two-stage optimization balances group fairness and adjustment cost, enhancing consensus practicality and acceptance. The paper conducts experiments using publicly available real wheat stripe rust datasets from four different locations, Ethiopia, India, Turkey, and China, and validates the effectiveness and robustness of the framework through comparative and sensitivity analyses. Full article

Wheat is a vital staple crop addressing significant nutritional needs. However, it faces micronutrient deficiencies in Ethiopia, prompting the use of balanced nutrient fertilizers to obtain better yields, nutrient concentration, and nutritional quality. This study investigated the effect of different P and Zn fertilizer combinations on wheat yield and nutrient use efficiency across three locations in Tigray, Ethiopia. A randomized complete block design (RCBD) was used with four P levels (0, 10, 20, and 30 kg P ha⁻¹), and three Zn levels (0, 5, and 10 kg Zn ha⁻¹) in three replications. A balanced application of P and Zn fertilizers significantly increased wheat grain and biomass yields, while applying higher rates of both nutrients (i.e., 30 kg P ha⁻¹ and 10 kg Zn ha⁻¹) reduced yields. The combined application of 20 kg P ha⁻¹ and 5 kg Zn ha⁻¹ achieved the best yield, which also improved Zn use efficiency. Increasing Zn application (from 5 to 10 kg Zn ha⁻¹) while reducing P (from 20 to 10 kg P ha⁻¹) enhanced Zn concentration in wheat grain. These findings highlight the importance of carefully managing P and Zn fertilization to optimize grain yield and Zn bioavailability, contributing to improved food security in diverse agro-climatic conditions. Full article

The transition of global agriculture from yield-driven production to quality-driven systems has gained urgency, where premium pricing strategies offer pathways to enhance farmer incomes and promote sustainable practices. As a critical staple crop, rice exemplifies the challenges of aligning producer standards with consumer preferences to realize market premiums. This study systematically evaluates determinants of consumers’ willingness to pay (WTP) for premium rice, integrating analyses of attribute preferences, cognition perception, and purchasing experience. Utilizing survey data from 1714 consumers across four Chinese cities, we employ principal component analysis to identify key quality dimensions and ordered logit models to quantify their impacts. Hedonic pricing theory informs the estimation of implicit prices for specific attributes. The results reveal that intrinsic characteristics (like nutrition) and extrinsic cues (like the brand), along with consumers’ nutritional awareness, knowledge, and perceptions of quality-price correlation, jointly drive premium WTP. The mean acceptable premium reaches 4.52 yuan/500 g, with nutritional attention enhancements commanding the highest valuation (0.171 yuan/500 g). The findings underscore the necessity of standardized quality grading systems aligned with consumer preferences and targeted interventions to bridge information asymmetries. Policymakers are recommended to improve supply-side quality signaling through enhanced packaging and certification systems while strengthening demand-side nutrition education to facilitate value chain coordination and sustainable, high-quality development in agriculture. Full article

The worldwide rise in soil salinization is among the most critical consequences of climate change, posing a significant threat to food security. Wheat (Triticum aestivum L.), a staple crop of paramount importance worldwide, encounters significant production limitations due to abiotic stressors, particularly salinity. Consequently, the development and cultivation of salt-tolerant wheat genotypes have emerged as an essential strategy to sustain agricultural productivity and safeguard global food security. The aim of the present study was to investigate the effect of salinity (150 mM) on the performance and combining ability of 10 hybrid combinations (F2) and their parents that were obtained through a line × tester mating design at the seedling stage. Morphological, physiological, and biochemical traits were assessed under both control and salt-stress conditions. Among the assessed traits, SFW emerged as the strongest predictor of salt tolerance, demonstrating the highest correlation with MFVS and the greatest contribution in the regression model. The results highlighted distinct responses among the studied genotypes. Hybrid H5 demonstrated particular promise, surpassing the performance of the superior parent for Na⁺, K⁺, K⁺/Na⁺ and proline (Pro). Furthermore, tester T1 emerged as a good combiner for proline (Pro), total soluble sugars content (Sug), chlorophyll content (Chl) and root length (RL) under saline conditions. In contrast, under control conditions, line L1 and testers T2, T3, and T5 exhibited superior performance, demonstrating significant general combining ability (GCA) effects for four traits simultaneously. Hybrid H4 emerged as outstanding under salt stress, exhibiting favorable specific combining ability (SCA) effects for Na⁺, K⁺/Na⁺ ratio, root length (RL), relative water content (RWC), and total soluble sugars content (Sug). Under normal conditions, hybrids H7 and H10 exhibited significantly superior performance across three traits simultaneously. Non-additive genetic effects predominantly influenced the studied traits under both conditions. The parental and hybrid combinations show promise for incorporation into breeding programs designed to improve salt tolerance under the specific conditions studied. Full article

Rice (Oryza sativa L.), a staple crop vital to global food security, faces escalating threats from climate change and inefficient nitrogen management. This study employed least absolute shrinkage and selection operator (LASSO) regression to analyze the stage-specific impacts of nitrogen application, temperature, and rainfall on rice yield and nitrogen use efficiency (NUE) across three growing seasons (2020–2022) in Jiangsu Province, China. The key findings revealed the following: (1) the reproductive stages (flowering and filling stages) exhibited extreme thermal sensitivity, with high temperatures (>35 °C) causing substantial yield losses (33.1% average) and reducing nitrogen recovery efficiency (NRE: 22.4–60.5% loss) and the nitrogen translocation ratio (NTR: 26.3–61.6% loss); (2) the vegetative stages (tillering and jointing and booting stages) were highly rainfall-sensitive, with rainfall during tillering (2.1–9.7 mm/day) influencing 50% of the traits, including four NUE types; (3) appropriate nitrogen management (250–350 kgN·ha⁻¹) mitigated the heat-induced losses, increasing physiological nitrogen use efficiency (PNUE) by 30.0–41.8% under extreme heat and alleviating the losses of yield. This study further verified the generalizability of LASSO. Compared with the traditional models, LASSO overcomes the issue of multicollinearity and can more effectively identify the key factors driving climate change across different spatial gradients. These findings provide actionable insights for optimizing nitrogen application timing, improving climate-resilient breeding, and developing stage-specific adaptation strategies to safeguard rice productivity under global warming. Full article

Cereal crops are important staple foods, and their defense metabolites hold significant research importance. In this study, we employed LC-MS-based untargeted and widely-targeted metabolomics to profile the leaf metabolome of nine cereal species, including rice, wheat, maize, barley, sorghum, common oat, foxtail millet, broomcorn millet, and adlay. A total of 9869 features were detected, among them, 1131 were annotated, encompassing 18 classes such as flavonoids, lipids, and alkaloids. Results revealed that 531 metabolites were detected in all species, while each cereal crop possessed 4 to 12 unique metabolites. Focusing on defense metabolites, we identified eight benzoxazinoids uniquely present in maize, wheat, and adlay. Hierarchical clustering based on metabolite abundance divided all metabolites into nine clusters, and subsequent pathway enrichment analysis revealed that the stress-related flavonoid biosynthesis pathway was enriched in multiple clusters. Further analysis showed that four downstream compounds of HBOA (2-hydroxy-1,4-benzoxazin-3-one) in the benzoxazinoid biosynthesis pathway were enriched in maize. Wheat uniquely accumulated the 4′-methylated product of tricin, trimethoxytricetin, whereas adlay accumulated the tricin precursor tricetin in the flavonoid biosynthesis pathway. In summary, this study elucidates the metabolic diversity in defense metabolites among various cereal crops, providing valuable background information for the improvement of stress resistance in cereal crops. Full article

Wheat is a key staple crop globally, essential for food security and sustainable agricultural development. The results of this study highlight how innovative monitoring techniques, such as UAV-based multispectral imaging, can significantly improve agricultural practices by providing precise, real-time data on crop growth. This study utilized unmanned aerial vehicle (UAV)-based remote sensing technology at the wheat experimental field of the Hebei Academy of Agriculture and Forestry Sciences to capture the dynamic growth characteristics of wheat using multispectral data, aiming to explore efficient and precise monitoring and management strategies for wheat. A UAV equipped with multispectral sensors was employed to collect high-resolution imagery at five critical growth stages of wheat: tillering, jointing, booting, flowering, and ripening. The data covered four key spectral bands: green (560 nm), red (650 nm), red-edge (730 nm), and near-infrared (840 nm). Combined with ground-truth measurements, such as chlorophyll content and plant height, 21 vegetation indices were analyzed for their nonlinear relationships with wheat growth parameters. Statistical analyses, including Pearson’s correlation and stepwise regression, were used to identify the most effective indices for monitoring wheat growth. The Normalized Difference Red-Edge Index (NDRE) and the Triangular Vegetation Index (TVI) were selected based on their superior performance in predicting wheat growth parameters, as demonstrated by their high correlation coefficients and predictive accuracy. A random forest model was developed to comprehensively evaluate the application potential of multispectral data in wheat growth monitoring. The results demonstrated that the NDRE and TVI indices were the most effective indices for monitoring wheat growth. The random forest model exhibited superior predictive accuracy, with a mean squared error (MSE) significantly lower than that of traditional regression models, particularly during the flowering and ripening stages, where the prediction error for plant height was less than 1.01 cm. Furthermore, dynamic analyses of UAV imagery effectively identified abnormal field areas, such as regions experiencing water stress or disease, providing a scientific basis for precision agricultural interventions. This study highlights the potential of UAV-based remote sensing technology in monitoring wheat growth, addressing the research gap in systematic full-cycle analysis of wheat. It also offers a novel technological pathway for optimizing agricultural resource management and improving crop yields. These findings are expected to advance intelligent agricultural production and accelerate the implementation of precision agriculture. Full article