Image-Based, Organ-Level Plant Phenotyping for Wheat Improvement

A deep learning approach for deriving wheat phenology from near-surface RGB image series using spatiotemporal fusion

Accurate monitoring of wheat phenological stages is essential for effective crop management and informed agricultural decision-making. Traditional methods often rely on labour-intensive field surveys, which are prone to subjective bias and limited temporal resolution. To address these challenges, this study explores the potential of near-surface cameras combined with an advanced deep-learning approach to derive wheat phenological stages from high-quality, real-time RGB image series. Three deep learning models based on three different spatiotemporal feature fusion methods, namely sequential fusion, synchronous fusion, and parallel fusion, were constructed and evaluated for deriving wheat phenological stages with these near-surface RGB image series. Moreover, the impact of different image resolutions, capture perspectives, and model training strategies on the performance of deep learning models was also investigated. The results indicate that the model using the sequential fusion method is optimal, with an overall accuracy (OA) of 0.935, a mean absolute error (MAE) of 0.069, F1-score (F1) of 0.936, and kappa coefficients (Kappa) of 0.924 in wheat phenological stages. Besides, the enhanced image resolution of 512 × 512 pixels and a suitable image capture perspective, specifically a sensor viewing angle of 40° to 60° vertically, introduce more effective features for phenological stage detection, thereby enhancing the model's accuracy. Furthermore, concerning the model training, applying a two-step fine-tuning strategy will also enhance the model's robustness to random variations in perspective. This research introduces an innovative approach for real-time phenological stage detection and provides a solid foundation for precision agriculture. By accurately deriving critical phenological stages, the methodology developed in this study supports the optimization of crop management practices, which may result in improved resource efficiency and sustainability across diverse agricultural settings. The implications of this work extend beyond wheat, offering a scalable solution that can be adapted to monitor other crops, thereby contributing to more efficient and sustainable agricultural systems.

Challenges facing sustainable protein production: Opportunities for cereals

Rising demands for protein worldwide are likely to drive increases in livestock production, as meat provides ∼40% of dietary protein. This will come at a significant environmental cost, and a shift toward plant-based protein sources would therefore provide major benefits. While legumes provide substantial amounts of plant-based protein, cereals are the major constituents of global foods, with wheat alone accounting for 15-20% of the required dietary protein intake. Improvement of protein content in wheat is limited by phenotyping challenges, lack of genetic potential of modern germplasms, negative yield trade-offs, and environmental costs of nitrogen fertilizers. Presenting wheat as a case study, we discuss how increasing protein content in cereals through a revised breeding strategy combined with robust phenotyping could ensure a sustainable protein supply while minimizing the environmental impact of nitrogen fertilizer.

Image-based phenotyping of seed architectural traits and prediction of seed weight using machine learning models in soybean

Among seed attributes, weight is one of the main factors determining the soybean harvest index. Recently, the focus of soybean breeding has shifted to improving seed size and weight for crop optimization in terms of seed and oil yield. With recent technological advancements, there is an increasing application of imaging sensors that provide simple, real-time, non-destructive, and inexpensive image data for rapid image-based prediction of seed traits in plant breeding programs. The present work is related to digital image analysis of seed traits for the prediction of hundred-seed weight (HSW) in soybean. The image-based seed architectural traits (i-traits) measured were area size (AS), perimeter length (PL), length (L), width (W), length-to-width ratio (LWR), intersection of length and width (IS), seed circularity (CS), and distance between IS and CG (DS). The phenotypic investigation revealed significant genetic variability among 164 soybean genotypes for both i-traits and manually measured seed weight. Seven popular machine learning (ML) algorithms, namely Simple Linear Regression (SLR), Multiple Linear Regression (MLR), Random Forest (RF), Support Vector Regression (SVR), LASSO Regression (LR), Ridge Regression (RR), and Elastic Net Regression (EN), were used to create models that can predict the weight of soybean seeds based on the image-based novel features derived from the Red-Green-Blue (RGB)/visual image. Among the models, random forest and multiple linear regression models that use multiple explanatory variables related to seed size traits (AS, L, W, and DS) were identified as the best models for predicting seed weight with the highest prediction accuracy (coefficient of determination, R2=0.98 and 0.94, respectively) and the lowest prediction error, i.e., root mean square error (RMSE) and mean absolute error (MAE). Finally, principal components analysis (PCA) and a hierarchical clustering approach were used to identify IC538070 as a superior genotype with a larger seed size and weight. The identified donors/traits can potentially be used in soybean improvement programs.

Molecular Advances to Combat Different Biotic and Abiotic Stresses in Linseed (Linum usitatissimum L.): A Comprehensive Review

Flax, or linseed, is considered a "superfood", which means that it is a food with diverse health benefits and potentially useful bioactive ingredients. It is a multi-purpose crop that is prized for its seed oil, fibre, nutraceutical, and probiotic qualities. It is suited to various habitats and agro-ecological conditions. Numerous abiotic and biotic stressors that can either have a direct or indirect impact on plant health are experienced by flax plants as a result of changing environmental circumstances. Research on the impact of various stresses and their possible ameliorators is prompted by such expectations. By inducing the loss of specific alleles and using a limited number of selected varieties, modern breeding techniques have decreased the overall genetic variability required for climate-smart agriculture. However, gene banks have well-managed collectionns of landraces, wild linseed accessions, and auxiliary Linum species that serve as an important source of novel alleles. In the past, flax-breeding techniques were prioritised, preserving high yield with other essential traits. Applications of molecular markers in modern breeding have made it easy to identify quantitative trait loci (QTLs) for various agronomic characteristics. The genetic diversity of linseed species and the evaluation of their tolerance to abiotic stresses, including drought, salinity, heavy metal tolerance, and temperature, as well as resistance to biotic stress factors, viz., rust, wilt, powdery mildew, and alternaria blight, despite addressing various morphotypes and the value of linseed as a supplement, are the primary topics of this review.

PiTLiD: Identification of Plant Disease From Leaf Images Based on Convolutional Neural Network

With the development of plant phenomics, the identification of plant diseases from leaf images has become an effective and economic approach in plant disease science. Among the methods of plant diseases identification, the convolutional neural network (CNN) is the most popular one for its superior performance. However, CNN's representation power is still a challenge in dealing with small datasets, which greatly affects its popularization. In this work, we propose a new method, namely PiTLiD, based on pretrained Inception-V3 convolutional neural network and transfer learning to identify plant leaf diseases from phenotype data of plant leaf with small sample size. To evaluate the robustness of the proposed method, the experiments on several datasets with small-scale samples were implemented. The results show that PiTLiD performs better than compared methods. This study provides a plant disease identification tool based on a deep learning algorithm for plant phenomics. All the source data and code are accessible at https://github.com/zhanglab-wbgcas/PiTLiD.

Analysis of chlorophyll fluorescence parameters as predictors of biomass accumulation and tolerance to heat and drought stress of wheat (Triticum aestivum) plants

Agricultural technologies aimed at increasing yields require the development of highly productive and stress-tolerant cultivars. Phenotyping can significantly accelerate breeding; however, no reliable markers have been identified to select the most promising cultivars at an early stage. In this work, we determined the light-induced dynamic of chlorophyll fluorescence (ChlF) parameters in young seedlings of 10 wheat (Triticum aestivum L.) cultivars and evaluated potency of these parameters as predictors of biomass accumulation and stress tolerance. Dry matter accumulation positively correlated with the effective quantum efficiency of photosystem II (Φ PSIIef ) and negatively correlated with the half-time of Φ PSIIef reaching (t 1/2 (Φ PSIIef )). There was a highly significant correlation between t 1/2 (Φ PSIIef ) and dry matter accumulation with increasing prediction period. Short-term heating and drought caused an inhibition of biomass accumulation and photosynthetic activity depending on the stressor intensity. The positive correlation between the Φ PSII dark level (Φ PSIId ) in young seedlings and tolerance to a rapidly increasing short-term stressor (heating) was shown. In the case of a long-term stressor (drought), we revealed a strong negative relationship between tolerance and the level of non-photochemical fluorescence quenching (NPQ). In general, the results show the potency of the ChlF parameters of young seedlings as predictors of biomass accumulation and stress tolerance.

Microbe-mediated adaptation in plants

Interactions with microbial symbionts have yielded great macroevolutionary innovations across the tree of life, like the origins of chloroplasts and the mitochondrial powerhouses of eukaryotic cells. There is also increasing evidence that host-associated microbiomes influence patterns of microevolutionary adaptation in plants and animals. Here we describe how microbes can facilitate adaptation in plants and how to test for and differentiate between the two main mechanisms by which microbes can produce adaptive responses in higher organisms: microbe-mediated local adaptation and microbe-mediated adaptive plasticity. Microbe-mediated local adaptation is when local plant genotypes have higher fitness than foreign genotypes because of a genotype-specific affiliation with locally beneficial microbes. Microbe-mediated adaptive plasticity occurs when local plant phenotypes, elicited by either the microbial community or the non-microbial environment, have higher fitness than foreign phenotypes as a result of interactions with locally beneficial microbes. These microbial effects on adaptation can be difficult to differentiate from traditional modes of adaptation but may be prevalent. Ignoring microbial effects may lead to erroneous conclusions about the traits and mechanisms underlying adaptation, hindering management decisions in conservation, restoration, and agriculture.