Machine Learning for High-Throughput Stress Phenotyping in Plants

Enhanced climate change resilience on wheat anther morphology using optimized deep learning techniques

Wheat commands attention due to its significant impact on culture, nutrition, the economy, and the guarantee of food security. The anticipated rise in temperatures resulting from climate change is a key factor contributing to food insecurity, as it markedly reduces wheat harvests. Terminal heat stress mostly affects spike fertility in wheat, specifically influencing pollen fertility and anther morphology. This research especially focuses on the shape of anthers and examines the effects of heat stress. The DinoLite Microscope's high-resolution images are used to measure the length and width of wheat anthers. By using object identification techniques, the research accurately measures the length and width of each anther in images, offering valuable insights into the differences between various wheat varieties. Furthermore, Deep Learning (DL) methodologies are utilized to enhance agriculture, specifically employing record categorization to advance plant breeding management. Given the ongoing challenges in agriculture, there is a belief that incorporating the latest technologies is crucial. The primary objective of this study is to explore how Deep Learning algorithms can be beneficial in categorizing agricultural records, particularly in monitoring and identifying variations in spring wheat germplasm. Various Deep Learning algorithms, including Convolution Neural Network (CNN), LeNet, and Inception-V3 are implemented to classify the records and extract various patterns. LeNet demonstrates optimized accuracy in classifying the records, outperforming CNN by 52% and Inception-V3 by 70%. Moreover, Precision, Recall, and F1 Measure are utilized to ascertain accuracy levels. The investigation also enhances our comprehension of the distinct roles played by various genes in abiotic stress tolerance among diverse wheat varieties. The outcomes of the research hold the potential to transform agricultural practices by introducing a more effective, data-driven approach to plant breeding management.

Clivia biosensor: Soil moisture identification based on electrophysiology signals with deep learning

Research has shown that plants have the ability to detect environmental changes and generate electrical signals in response. These electrical signals can regulate the physiological state of plants and produce corresponding feedback. This suggests that plants have the potential to be used as biosensors for monitoring environmental information. However, there are current challenges in linking environmental information with plant electrical signals, especially in collecting and classifying the corresponding electrical signals under soil moisture gradients. This study documented the electrical signals of clivia under different soil moisture gradients and created a dataset for classifying electrical signals. Subsequently, we proposed a lightweight convolutional neural network (CNN) model (PlantNet) for classifying the electrical signal dataset. Compared to traditional CNN models, our model achieved optimal classification performance with the lowest computational resource consumption. The model achieved an accuracy of 99.26%, precision of 99.31%, recall of 92.26%, F1-score of 99.21%, with 0.17M parameters, a size of 7.17MB, and 14.66M FLOPs. Therefore, this research provides scientific evidence for the future development of plants as biosensors for detecting soil moisture, and offers insight into developing plants as biosensors for detecting signals such as ozone, PM2.5, Volatile Organic Compounds(VOCs), and more. These studies are expected to drive the development of environmental monitoring technology and provide new pathways for better understanding the interaction between plants and the environment.

Weakly supervised localization model for plant disease based on Siamese networks

Problems

Plant diseases significantly impact crop growth and yield. The variability and unpredictability of symptoms postinfection increase the complexity of image-based disease detection methods, leading to a higher false alarm rate.

Aim

To address this challenge, we have developed an efficient, weakly supervised agricultural disease localization model using Siamese neural networks.

Methods

This model innovatively employs a Siamese network structure with a weight-sharing mechanism to effectively capture the visual differences in plants affected by diseases. Combined with our proprietary Agricultural Disease Precise Localization Class Activation Mapping algorithm (ADPL-CAM), the model can accurately identify areas affected by diseases, achieving effective localization of plant diseases.

Results and conclusion

The results showed that ADPL-CAM performed the best on all network architectures. On ResNet50, ADPL-CAM's top-1 accuracy was 3.96% higher than GradCAM and 2.77% higher than SmoothCAM; the average Intersection over Union (IoU) is 27.09% higher than GradCAM and 19.63% higher than SmoothCAM. Under the SPDNet architecture, ADPL-CAM achieves a top-1 accuracy of 54.29% and an average IoU of 67.5%, outperforming other CAM methods in all metrics. It can accurately and promptly identify and locate diseased leaves in crops.

Advancing microbial production through artificial intelligence-aided biology

Microbial cell factories (MCFs) have been leveraged to construct sustainable platforms for value-added compound production. To optimize metabolism and reach optimal productivity, synthetic biology has developed various genetic devices to engineer microbial systems by gene editing, high-throughput protein engineering, and dynamic regulation. However, current synthetic biology methodologies still rely heavily on manual design, laborious testing, and exhaustive analysis. The emerging interdisciplinary field of artificial intelligence (AI) and biology has become pivotal in addressing the remaining challenges. AI-aided microbial production harnesses the power of processing, learning, and predicting vast amounts of biological data within seconds, providing outputs with high probability. With well-trained AI models, the conventional Design-Build-Test (DBT) cycle has been transformed into a multidimensional Design-Build-Test-Learn-Predict (DBTLP) workflow, leading to significantly improved operational efficiency and reduced labor consumption. Here, we comprehensively review the main components and recent advances in AI-aided microbial production, focusing on genome annotation, AI-aided protein engineering, artificial functional protein design, and AI-enabled pathway prediction. Finally, we discuss the challenges of integrating novel AI techniques into biology and propose the potential of large language models (LLMs) in advancing microbial production.

Integrating high-throughput phenotyping and genome-wide association studies for enhanced drought resistance and yield prediction in wheat

Drought, especially terminal drought, severely limits wheat growth and yield. Understanding the complex mechanisms behind the drought response in wheat is essential for developing drought-resistant varieties. This study aimed to dissect the genetic architecture and high-yielding wheat ideotypes under terminal drought. An automated high-throughput phenotyping platform was used to examine 28 392 image-based digital traits (i-traits) under different drought conditions during the flowering stage of a natural wheat population. Of the i-traits examined, 17 073 were identified as drought-related. A genome-wide association study (GWAS) identified 5320 drought-related significant single-nucleotide polymorphisms (SNPs) and 27 SNP clusters. A notable hotspot region controlling wheat drought tolerance was discovered, in which TaPP2C6 was shown to be an important negative regulator of the drought response. The tapp2c6 knockout lines exhibited enhanced drought resistance without a yield penalty. A haplotype analysis revealed a favored allele of TaPP2C6 that was significantly correlated with drought resistance, affirming its potential value in wheat breeding programs. We developed an advanced prediction model for wheat yield and drought resistance using 24 i-traits analyzed by machine learning. In summary, this study provides comprehensive insights into the high-yielding ideotype and an approach for the rapid breeding of drought-resistant wheat.

Prediction accuracy and repeatability of UAV based biomass estimation in wheat variety trials as affected by variable type, modelling strategy and sampling location

BACKGROUND

This study explores the use of Unmanned Aerial Vehicles (UAVs) for estimating wheat biomass, focusing on the impact of phenotyping and analytical protocols in the context of late-stage variety selection programs. It emphasizes the importance of variable selection, model specificity, and sampling location within the experimental plot in predicting biomass, aiming to refine UAV-based estimation techniques for enhanced selection accuracy and throughput in variety testing programs.

RESULTS

The research uncovered that integrating geometric and spectral traits led to an increase in prediction accuracy, whilst a recursive feature elimination (RFE) based variable selection workflowled to slight reductions in accuracy with the benefit of increased interpretability. Models, tailored to specific experiments were more accurate than those modelling all experiments together, while models trained for broad-growth stages did not significantly increase accuracy. The comparison between a permanent and a precise region of interest (ROI) within the plot showed negligible differences in biomass prediction accuracy, indicating the robustness of the approach across different sampling locations within the plot. Significant differences in the within-season repeatability (w2) of biomass predictions across different experiments highlighted the need for further investigation into the optimal timing of measurement for prediction.

CONCLUSIONS

The study highlights the promising potential of UAV technology in biomass prediction for wheat at a small plot scale. It suggests that the accuracy of biomass predictions can be significantly improved through optimizing analytical and modelling protocols (i.e., variable selection, algorithm selection, stage-specific model development). Future work should focus on exploring the applicability of these findings under a wider variety of conditions and from a more diverse set of genotypes.

Deep learning models for the early detection of maize streak virus and maize lethal necrosis diseases in Tanzania

Agriculture is considered the backbone of Tanzania's economy, with more than 60% of the residents depending on it for survival. Maize is the country's dominant and primary food crop, accounting for 45% of all farmland production. However, its productivity is challenged by the limitation to detect maize diseases early enough. Maize streak virus (MSV) and maize lethal necrosis virus (MLN) are common diseases often detected too late by farmers. This has led to the need to develop a method for the early detection of these diseases so that they can be treated on time. This study investigated the potential of developing deep-learning models for the early detection of maize diseases in Tanzania. The regions where data was collected are Arusha, Kilimanjaro, and Manyara. Data was collected through observation by a plant. The study proposed convolutional neural network (CNN) and vision transformer (ViT) models. Four classes of imagery data were used to train both models: MLN, Healthy, MSV, and WRONG. The results revealed that the ViT model surpassed the CNN model, with 93.1 and 90.96% accuracies, respectively. Further studies should focus on mobile app development and deployment of the model with greater precision for early detection of the diseases mentioned above in real life.

Cotton morphological traits tracking through spatiotemporal registration of terrestrial laser scanning time-series data

Understanding the complex interactions between genotype-environment dynamics is fundamental for optimizing crop improvement. However, traditional phenotyping methods limit assessments to the end of the growing season, restricting continuous crop monitoring. To address this limitation, we developed a methodology for spatiotemporal registration of time-series 3D point cloud data, enabling field phenotyping over time for accurate crop growth tracking. Leveraging multi-scan terrestrial laser scanning (TLS), we captured high-resolution 3D LiDAR data in a cotton breeding field across various stages of the growing season to generate four-dimensional (4D) crop models, seamlessly integrating spatial and temporal dimensions. Our registration procedure involved an initial pairwise terrain-based matching for rough alignment, followed by a bird's-eye view adjustment for fine registration. Point clouds collected throughout nine sessions across the growing season were successfully registered both spatially and temporally, with average registration errors of approximately 3 cm. We used the generated 4D models to monitor canopy height (CH) and volume (CV) for eleven cotton genotypes over two months. The consistent height reference established via our spatiotemporal registration process enabled precise estimations of CH (R 2 = 0.95, RMSE = 7.6 cm). Additionally, we analyzed the relationship between CV and the interception of photosynthetically active radiation (IPAR f ), finding that it followed a curve with exponential saturation, consistent with theoretical models, with a standard error of regression (SER) of 11%. In addition, we compared mathematical models from the Richards family of sigmoid curves for crop growth modeling, finding that the logistic model effectively captured CH and CV evolution, aiding in identifying significant genotype differences. Our novel TLS-based digital phenotyping methodology enhances precision and efficiency in field phenotyping over time, advancing plant phenomics and empowering efficient decision-making for crop improvement efforts.

Recent advances in the population biology and management of maize foliar fungal pathogens Exserohilum turcicum, Cercospora zeina and Bipolaris maydis in Africa

Maize is the most widely cultivated and major security crop in sub-Saharan Africa. Three foliar diseases threaten maize production on the continent, namely northern leaf blight, gray leaf spot, and southern corn leaf blight. These are caused by the fungi Exserohilum turcicum, Cercospora zeina, and Bipolaris maydis, respectively. Yield losses of more than 10% can occur if these pathogens are diagnosed inaccurately or managed ineffectively. Here, we review recent advances in understanding the population biology and management of the three pathogens, which are present in Africa and thrive under similar environmental conditions during a single growing season. To effectively manage these pathogens, there is an increasing adoption of breeding for resistance at the small-scale level combined with cultural practices. Fungicide usage in African cropping systems is limited due to high costs and avoidance of chemical control. Currently, there is limited knowledge available on the population biology and genetics of these pathogens in Africa. The evolutionary potential of these pathogens to overcome host resistance has not been fully established. There is a need to conduct large-scale sampling of isolates to study their diversity and trace their migration patterns across the continent.

Classification and prediction of drought and salinity stress tolerance in barley using GenPhenML

Genetic and agronomic advances consistently lead to an annual increase in global barley yield. Since abiotic stresses (physical environmental factors that negatively affect plant growth) reduce barley yield, it is necessary to predict barley resistance. Artificial intelligence and machine learning (ML) models are new and powerful tools for predicting product resilience. Considering the research gap in the use of molecular markers in predicting abiotic stresses, this paper introduces a new approach called GenPhenML that combines molecular markers and phenotypic traits to predict the resistance of barley genotypes to drought and salinity stresses by ML models. GenPhenML uses feature selection algorithms to determine the most important molecular markers. It then identifies the best model that predicts atmospheric resistance with lower MAE, RMSE, and higher R2. The results showed that GenPhenML with a neural network model predicted the salinity stress resistance score with MAE, RMSE and R2 values of 0.1206, 0.0308 and 0.9995, respectively. Also, the NN model predicted drought stress scores with MAE, RMSE and R2 values of 0.0727, 0.0105 and 0.9999, respectively. The GenPhenML approach was also used to classify barley genotypes as resistant and stress-sensitive. The results showed that the accuracy, accuracy and F1 score of the proposed approach for salinity and drought stress classification were higher than 97%.

Precision Detection of Salt Stress in Soybean Seedlings Based on Deep Learning and Chlorophyll Fluorescence Imaging

Soil salinization poses a critical challenge to global food security, impacting plant growth, development, and crop yield. This study investigates the efficacy of deep learning techniques alongside chlorophyll fluorescence (ChlF) imaging technology for discerning varying levels of salt stress in soybean seedlings. Traditional methods for stress identification in plants are often laborious and time-intensive, prompting the exploration of more efficient approaches. A total of six classic convolutional neural network (CNN) models-AlexNet, GoogLeNet, ResNet50, ShuffleNet, SqueezeNet, and MobileNetv2-are evaluated for salt stress recognition based on three types of ChlF images. Results indicate that ResNet50 outperforms other models in classifying salt stress levels across three types of ChlF images. Furthermore, feature fusion after extracting three types of ChlF image features in the average pooling layer of ResNet50 significantly enhanced classification accuracy, achieving the highest accuracy of 98.61% in particular when fusing features from three types of ChlF images. UMAP dimensionality reduction analysis confirms the discriminative power of fused features in distinguishing salt stress levels. These findings underscore the efficacy of deep learning and ChlF imaging technologies in elucidating plant responses to salt stress, offering insights for precision agriculture and crop management. Overall, this study demonstrates the potential of integrating deep learning with ChlF imaging for precise and efficient crop stress detection, offering a robust tool for advancing precision agriculture. The findings contribute to enhancing agricultural sustainability and addressing global food security challenges by enabling more effective crop stress management.

Sunpheno: A Deep Neural Network for Phenological Classification of Sunflower Images

Leaf senescence is a complex trait which becomes crucial for grain filling because photoassimilates are translocated to the seeds. Therefore, a correct sync between leaf senescence and phenological stages is necessary to obtain increasing yields. In this study, we evaluated the performance of five deep machine-learning methods for the evaluation of the phenological stages of sunflowers using images taken with cell phones in the field. From the analysis, we found that the method based on the pre-trained network resnet50 outperformed the other methods, both in terms of accuracy and velocity. Finally, the model generated, Sunpheno, was used to evaluate the phenological stages of two contrasting lines, B481_6 and R453, during senescence. We observed clear differences in phenological stages, confirming the results obtained in previous studies. A database with 5000 images was generated and was classified by an expert. This is important to end the subjectivity involved in decision making regarding the progression of this trait in the field and could be correlated with performance and senescence parameters that are highly associated with yield increase.

Controlled Environment Ecosystem: A Cutting-Edge Technology in Speed Breeding

The controlled environment ecosystem is a meticulously designed plant growing chamber utilized for cultivating biofortified crops and microgreens, addressing hidden hunger and malnutrition prevalent in the growing population. The integration of speed breeding within such controlled environments effectively eradicates morphological disruptions encountered in traditional breeding methods such as inbreeding depression, male sterility, self-incompatibility, embryo abortion, and other unsuccessful attempts. In contrast to the unpredictable climate conditions that often prolong breeding cycles to 10-15 years in traditional breeding and 4-5 years in transgenic breeding within open ecosystems, speed breeding techniques expedite the achievement of breeding objectives and F1-F6 generations within 2-3 years under controlled growing conditions. In comparison, traditional breeding may take 5-10 years for plant population line creation, 3-5 years for field trials, and 1-2 years for variety release. The effectiveness of speed breeding in trait improvement and population line development varies across different crops, requiring approximately 4 generations in rice and groundnut, 5 generations in soybean, pea, and oat, 6 generations in sorghum, Amaranthus sp., and subterranean clover, 6-7 generations in bread wheat, durum wheat, and chickpea, 7 generations in broad bean, 8 generations in lentil, and 10 generations in Arabidopsis thaliana annually within controlled environment ecosystems. Artificial intelligence leverages neural networks and algorithm models to screen phenotypic traits and assess their role in diverse crop species. Moreover, in controlled environment systems, mechanistic models combined with machine learning effectively regulate stable nutrient use efficiency, water use efficiency, photosynthetic assimilation product, metabolic use efficiency, climatic factors, greenhouse gas emissions, carbon sequestration, and carbon footprints. However, any negligence, even minor, in maintaining optimal photoperiodism, temperature, humidity, and controlling pests or diseases can lead to the deterioration of crop trials and speed breeding techniques within the controlled environment system. Further comparative studies are imperative to comprehend and justify the efficacy of climate management techniques in controlled environment ecosystems compared to natural environments, with or without soil.

Field-based high-throughput phenotyping enhances phenomic and genomic predictions for grain yield and plant height across years in maize

Field-based phenomic prediction employs novel features, like vegetation indices (VIs) from drone images, to predict key agronomic traits in maize, despite challenges in matching biomarker measurement time points across years or environments. This study utilized functional principal component analysis (FPCA) to summarize the variation of temporal VIs, uniquely allowing the integration of this data into phenomic prediction models tested across multiple years (2018-2021) and environments. The models, which included 1 genomic, 2 phenomic, 2 multikernel, and 1 multitrait type, were evaluated in 4 prediction scenarios (CV2, CV1, CV0, and CV00), relevant for plant breeding programs, assessing both tested and untested genotypes in observed and unobserved environments. Two hybrid populations (415 and 220 hybrids) demonstrated the visible atmospherically resistant index's strong temporal correlation with grain yield (up to 0.59) and plant height. The first 2 FPCAs explained 59.3 ± 13.9% and 74.2 ± 9.0% of the temporal variation of temporal data of VIs, respectively, facilitating predictions where flight times varied. Phenomic data, particularly when combined with genomic data, often were comparable to or numerically exceeded the base genomic model in prediction accuracy, particularly for grain yield in untested hybrids, although no significant differences in these models' performance were consistently observed. Overall, this approach underscores the effectiveness of FPCA and combined models in enhancing the prediction of grain yield and plant height across environments and diverse agricultural settings.

Vegetation change detection and recovery assessment based on post-fire satellite imagery using deep learning

Wildfires are uncontrolled fires fuelled by dry conditions, high winds, and flammable materials that profoundly impact vegetation, leading to significant consequences including noteworthy changes to ecosystems. In this study, we provide a novel methodology to understand and evaluate post-fire effects on vegetation. In regions affected by wildfires, earth-observation data from various satellite sources can be vital in monitoring vegetation and assessing its impact. These effects can be understood by detecting vegetation change over the years using a novel unsupervised method termed Deep Embedded Clustering (DEC), which enables us to classify regions based on whether there has been a change in vegetation after the fire. Our model achieves an impressive accuracy of 96.17%. Appropriate vegetation indices can be used to evaluate the evolution of vegetation patterns over the years; for this study, we utilized Enhanced Vegetation Index (EVI) based trend analysis showing the greening fraction, which ranges from 0.1 to 22.4 km2 while the browning fraction ranges from 0.1 to 18.1 km2 over the years. Vegetation recovery maps can be created to assess re-vegetation in regions affected by the fire, which is performed via a deep learning-based unsupervised method, Adaptive Generative Adversarial Neural Network Model (AdaptiGAN) on post-fire data collected from various regions affected by wildfire with a training error of 0.075 proving its capability. Based on the results obtained from the study, our approach tends to have notable merits when compared to pre-existing works.

Machine learning ensembles, neural network, hybrid and sparse regression approaches for weather based rainfed cotton yield forecast

Cotton is a major economic crop predominantly cultivated under rainfed situations. The accurate prediction of cotton yield invariably helps farmers, industries, and policy makers. The final cotton yield is mostly determined by the weather patterns that prevail during the crop growing phase. Crop yield prediction with greater accuracy is possible due to the development of innovative technologies which analyses the bigdata with its high-performance computing abilities. Machine learning technologies can make yield prediction reasonable and faster and with greater flexibility than process based complex crop simulation models. The present study demonstrates the usability of ML algorithms for yield forecasting and facilitates the comparison of different models. The cotton yield was simulated by employing the weekly weather indices as inputs and the model performance was assessed by nRMSE, MAPE and EF values. Results show that stacked generalised ensemble model and artificial neural networks predicted the cotton yield with lower nRMSE, MAPE and higher efficiency compared to other models. Variable importance studies in LASSO and ENET model found minimum temperature and relative humidity as the main determinates of cotton yield in all districts. The models were ranked based these performance metrics in the order of Stacked generalised ensemble > ANN > PCA ANN > SMLR ANN > LASSO> ENET > SVM > PCA SMLR > SMLR SVM > SMLR. This study shows that stacked generalised ensembling and ANN method can be used for reliable yield forecasting at district or county level and helps stakeholders in timely decision-making.

Enhancing the potential of phenomic and genomic prediction in winter wheat breeding using high-throughput phenotyping and deep learning

Integrating high-throughput phenotyping (HTP) based traits into phenomic and genomic selection (GS) can accelerate the breeding of high-yielding and climate-resilient wheat cultivars. In this study, we explored the applicability of Unmanned Aerial Vehicles (UAV)-assisted HTP combined with deep learning (DL) for the phenomic or multi-trait (MT) genomic prediction of grain yield (GY), test weight (TW), and grain protein content (GPC) in winter wheat. Significant correlations were observed between agronomic traits and HTP-based traits across different growth stages of winter wheat. Using a deep neural network (DNN) model, HTP-based phenomic predictions showed robust prediction accuracies for GY, TW, and GPC for a single location with R2 of 0.71, 0.62, and 0.49, respectively. Further prediction accuracies increased (R2 of 0.76, 0.64, and 0.75) for GY, TW, and GPC, respectively when advanced breeding lines from multi-locations were used in the DNN model. Prediction accuracies for GY varied across growth stages, with the highest accuracy at the Feekes 11 (Milky ripe) stage. Furthermore, forward prediction of GY in preliminary breeding lines using DNN trained on multi-location data from advanced breeding lines improved the prediction accuracy by 32% compared to single-location data. Next, we evaluated the potential of incorporating HTP-based traits in multi-trait genomic selection (MT-GS) models in the prediction of GY, TW, and GPC. MT-GS, models including UAV data-based anthocyanin reflectance index (ARI), green chlorophyll index (GCI), and ratio vegetation index 2 (RVI_2) as covariates demonstrated higher predictive ability (0.40, 0.40, and 0.37, respectively) as compared to single-trait model (0.23) for GY. Overall, this study demonstrates the potential of integrating HTP traits into DL-based phenomic or MT-GS models for enhancing breeding efficiency.

Simulation of Automatically Annotated Visible and Multi-/Hyperspectral Images Using the Helios 3D Plant and Radiative Transfer Modeling Framework

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

Tackling unbalanced datasets for yellow and brown rust detection in wheat

This study evaluates the efficacy of hyperspectral data for detecting yellow and brown rust in wheat, employing machine learning models and the SMOTE (Synthetic Minority Oversampling Technique) augmentation technique to tackle unbalanced datasets. Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), and Gaussian Naïve Bayes (GNB) models were assessed. Overall, SVM and RF models showed higher accuracies, particularly when utilizing SMOTE-enhanced datasets. The RF model achieved 70% accuracy in detecting yellow rust without data alteration. Conversely, for brown rust, the SVM model outperformed others, reaching 63% accuracy with SMOTE applied to the training set. This study highlights the potential of spectral data and machine learning (ML) techniques in plant disease detection. It emphasizes the need for further research in data processing methodologies, particularly in exploring the impact of techniques like SMOTE on model performance.

Out-of-Distribution Detection Algorithms for Robust Insect Classification

Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.

Machine Learning Application in Horticulture and Prospects for Predicting Fresh Produce Losses and Waste: A Review

The current review examines the state of knowledge and research on machine learning (ML) applications in horticultural production and the potential for predicting fresh produce losses and waste. Recently, ML has been increasingly applied in horticulture for efficient and accurate operations. Given the health benefits of fresh produce and the need for food and nutrition security, efficient horticultural production and postharvest management are important. This review aims to assess the application of ML in preharvest and postharvest horticulture and the potential of ML in reducing postharvest losses and waste by predicting their magnitude, which is crucial for management practices and policymaking in loss and waste reduction. The review starts by assessing the application of ML in preharvest horticulture. It then presents the application of ML in postharvest handling and processing, and lastly, the prospects for its application in postharvest loss and waste quantification. The findings revealed that several ML algorithms perform satisfactorily in classification and prediction tasks. Based on that, there is a need to further investigate the suitability of more models or a combination of models with a higher potential for classification and prediction. Overall, the review suggested possible future directions for research related to the application of ML in postharvest losses and waste quantification.

Stress phenotyping analysis leveraging autofluorescence image sequences with machine learning

Background

Autofluorescence-based imaging has the potential to non-destructively characterize the biochemical and physiological properties of plants regulated by genotypes using optical properties of the tissue. A comparative study of stress tolerant and stress susceptible genotypes of Brassica rapa with respect to newly introduced stress-based phenotypes using machine learning techniques will contribute to the significant advancement of autofluorescence-based plant phenotyping research.

Methods

Autofluorescence spectral images have been used to design a stress detection classifier with two classes, stressed and non-stressed, using machine learning algorithms. The benchmark dataset consisted of time-series image sequences from three Brassica rapa genotypes (CC, R500, and VT), extreme in their morphological and physiological traits captured at the high-throughput plant phenotyping facility at the University of Nebraska-Lincoln, USA. We developed a set of machine learning-based classification models to detect the percentage of stressed tissue derived from plant images and identified the best classifier. From the analysis of the autofluorescence images, two novel stress-based image phenotypes were computed to determine the temporal variation in stressed tissue under progressive drought across different genotypes, i.e., the average percentage stress and the moving average percentage stress.

Results

The study demonstrated that both the computed phenotypes consistently discriminated against stressed versus non-stressed tissue, with oilseed type (R500) being less prone to drought stress relative to the other two Brassica rapa genotypes (CC and VT).

Conclusion

Autofluorescence signals from the 365/400 nm excitation/emission combination were able to segregate genotypic variation during a progressive drought treatment under a controlled greenhouse environment, allowing for the exploration of other meaningful phenotypes using autofluorescence image sequences with significance in the context of plant science.

The State of the Art in Root System Architecture Image Analysis Using Artificial Intelligence: A Review

Roots are essential for acquiring water and nutrients to sustain and support plant growth and anchorage. However, they have been studied less than the aboveground traits in phenotyping and plant breeding until recent decades. In modern times, root properties such as morphology and root system architecture (RSA) have been recognized as increasingly important traits for creating more and higher quality food in the "Second Green Revolution". To address the paucity in RSA and other root research, new technologies are being investigated to fill the increasing demand to improve plants via root traits and overcome currently stagnated genetic progress in stable yields. Artificial intelligence (AI) is now a cutting-edge technology proving to be highly successful in many applications, such as crop science and genetic research to improve crop traits. A burgeoning field in crop science is the application of AI to high-resolution imagery in analyses that aim to answer questions related to crops and to better and more speedily breed desired plant traits such as RSA into new cultivars. This review is a synopsis concerning the origins, applications, challenges, and future directions of RSA research regarding image analyses using AI.

Deciphering temporal growth patterns in maize: integrative modeling of phenotype dynamics and underlying genomic variations

Quantifying the temporal or longitudinal growth dynamics of crops in diverse environmental conditions is crucial for understanding plant development, requiring further modeling techniques. In this study, we analyzed the growth patterns of two different maize (Zea mays L.) populations using high-throughput phenotyping with a maize population consisting of 515 recombinant inbred lines (RILs) grown in Texas and a hybrid population containing 1090 hybrids grown in Missouri. Two models, Gaussian peak and functional principal component analysis (FPCA), were employed to study the Normalized Green-Red Difference Index (NGRDI) scores. The Gaussian peak model showed strong correlations (c. 0.94 for RILs and c. 0.97 for hybrids) between modeled and non-modeled temporal trajectories. Functional principal component analysis differentiated NGRDI trajectories in RILs under different conditions, capturing substantial variability (75%, 20%, and 5% for RILs; 88% and 12% for hybrids). By comparing these models with conventional BLUP values, common quantitative trait loci (QTLs) were identified, containing candidate genes of brd1, pin11, zcn8 and rap2. The harmony between these loci's additive effects and growing degree days, as well as the differentiation of RIL haplotypes across growth stages, underscores the significant interplay of these loci in driving plant development. These findings contribute to advancing understanding of plant-environment interactions and have implications for crop improvement strategies.

Artificial intelligence models for validating and predicting the impact of chemical priming of hydrogen peroxide (H2O2) and light emitting diodes on in vitro grown industrial hemp (Cannabis sativa L.)

Industrial hemp (Cannabis sativa L.) is a highly recalcitrant plant under in vitro conditions that can be overcome by employing external stimuli. Hemp seeds were primed with 2.0-3.0% hydrogen peroxide (H2O2) followed by culture under different Light Emitting Diodes (LEDs) sources. Priming seeds with 2.0% yielded relatively high germination rate, growth, and other biochemical and enzymatic activities. The LED lights exerted a variable impact on Cannabis germination and enzymatic activities. Similarly, variable responses were observed for H2O2 × Blue-LEDs combination. The results were also analyzed by multiple regression analysis, followed by an investigation of the impact of both factors by Pareto chart and normal plots. The results were optimized by contour and surface plots for all parameters. Response surface optimizer optimized 2.0% H2O2 × 918 LUX LEDs for maximum scores of all output parameters. The results were predicted by employing Multilayer Perceptron (MLP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms. Moreover, the validity of these models was assessed by using six different performance metrics. MLP performed better than RF and XGBoost models, considering all six-performance metrics. Despite the differences in scores, the performance indicators for all examined models were quite close to each other. It can easily be concluded that all three models are capable of predicting and validating data for cannabis seeds primed with H2O2 and grown under different LED lights.

A review of artificial intelligence-assisted omics techniques in plant defense: current trends and future directions

Plants intricately deploy defense systems to counter diverse biotic and abiotic stresses. Omics technologies, spanning genomics, transcriptomics, proteomics, and metabolomics, have revolutionized the exploration of plant defense mechanisms, unraveling molecular intricacies in response to various stressors. However, the complexity and scale of omics data necessitate sophisticated analytical tools for meaningful insights. This review delves into the application of artificial intelligence algorithms, particularly machine learning and deep learning, as promising approaches for deciphering complex omics data in plant defense research. The overview encompasses key omics techniques and addresses the challenges and limitations inherent in current AI-assisted omics approaches. Moreover, it contemplates potential future directions in this dynamic field. In summary, AI-assisted omics techniques present a robust toolkit, enabling a profound understanding of the molecular foundations of plant defense and paving the way for more effective crop protection strategies amidst climate change and emerging diseases.

Practical Identifiability of Plant Growth Models: A Unifying Framework and Its Specification for Three Local Indices

Amid the rise of machine learning models, a substantial portion of plant growth models remains mechanistic, seeking to capture an in-depth understanding of the underlying phenomena governing the system's dynamics. The development of these models typically involves parameter estimation from experimental data. Ensuring that the estimated parameters align closely with their respective "true" values is crucial since they hold biological interpretation, leading to the challenge of uniqueness in the solutions. Structural identifiability analysis addresses this issue under the assumption of perfect observations of system dynamics, whereas practical identifiability considers limited measurements and the accompanying noise. In the literature, definitions for structural identifiability vary only slightly among authors, whereas the concept and quantification of practical identifiability lack consensus, with several indices coexisting. In this work, we provide a unified framework for studying identifiability, accommodating different definitions that need to be instantiated depending on each application case. In a more applicative second step, we focus on three widely used methods for quantifying practical identifiability: collinearity indices, profile likelihood, and average relative error. We show the limitations of their local versions, and we propose a new risk index built on the profile likelihood-based confidence intervals. We illustrate the usefulness of these concepts for plant growth modeling using a discrete-time individual plant growth model, LNAS, and a continuous-time plant population epidemics model. Through this work, we aim to underline the significance of identifiability analysis as a complement to any parameter estimation study and offer guidance to the modeler.

Are unmanned aerial vehicle-based hyperspectral imaging and machine learning advancing crop science?

The past few years have seen increased interest in unmanned aerial vehicle (UAV)-based hyperspectral imaging (HSI) and machine learning (ML) in agricultural research, concomitant with an increase in published research on these topics. We provide an updated review, written for agriculturalists, highlighting the benefits in the retrieval of biophysical parameters of crops via UAVs relative to less sophisticated options. We reviewed >70 recent papers and found few consistent results between similar studies. Owing to their high complexity and cost, especially when applied to crops of low value, the benefits of most of the research reviewed are difficult to explain. Future effort will be necessary to distill research findings into lower-cost options for end-users.

Non-destructive real-time analysis of plant metabolite accumulation in radish microgreens under different LED light recipes

Introduction

The future of human space missions relies on the ability to provide adequate food resources for astronauts and also to reduce stress due to the environment (microgravity and cosmic radiation). In this context, microgreens have been proposed for the astronaut diet because of their fast-growing time and their high levels of bioactive compounds and nutrients (vitamins, antioxidants, minerals, etc.), which are even higher than mature plants, and are usually consumed as ready-to-eat vegetables.

Methods

Our study aimed to identify the best light recipe for the soilless cultivation of two cultivars of radish microgreens (Raphanus sativus, green daikon, and rioja improved) harvested eight days after sowing that could be used for space farming. The effects on plant metabolism of three different light emitting diodes (LED) light recipes (L1-20% red, 20% green, 60% blue; L2-40% red, 20% green, 40% blue; L3-60% red, 20% green, 20% blue) were tested on radish microgreens hydroponically grown. A fluorimetric-based technique was used for a real-time non-destructive screening to characterize plant methabolism. The adopted sensors allowed us to quantitatively estimate the fluorescence of flavonols, anthocyanins, and chlorophyll via specific indices verified by standardized spectrophotometric methods. To assess plant growth, morphometric parameters (fresh and dry weight, cotyledon area and weight, hypocotyl length) were analyzed.

Results

We observed a statistically significant positive effect on biomass accumulation and productivity for both cultivars grown under the same light recipe (40% blue, 20% green, 40% red). We further investigated how the addition of UV and/or far-red LED lights could have a positive effect on plant metabolite accumulation (anthocyanins and flavonols).

Discussion

These results can help design plant-based bioregenerative life-support systems for long-duration human space exploration, by integrating fluorescence-based non-destructive techniques to monitor the accumulation of metabolites with nutraceutical properties in soilless cultivated microgreens.

PlantPAD: a platform for large-scale image phenomics analysis of disease in plant science

Plant disease, a huge burden, can cause yield loss of up to 100% and thus reduce food security. Actually, smart diagnosing diseases with plant phenomics is crucial for recovering the most yield loss, which usually requires sufficient image information. Hence, phenomics is being pursued as an independent discipline to enable the development of high-throughput phenotyping for plant disease. However, we often face challenges in sharing large-scale image data due to incompatibilities in formats and descriptions provided by different communities, limiting multidisciplinary research exploration. To this end, we build a Plant Phenomics Analysis of Disease (PlantPAD) platform with large-scale information on disease. Our platform contains 421 314 images, 63 crops and 310 diseases. Compared to other databases, PlantPAD has extensive, well-annotated image data and in-depth disease information, and offers pre-trained deep-learning models for accurate plant disease diagnosis. PlantPAD supports various valuable applications across multiple disciplines, including intelligent disease diagnosis, disease education and efficient disease detection and control. Through three applications of PlantPAD, we show the easy-to-use and convenient functions. PlantPAD is mainly oriented towards biologists, computer scientists, plant pathologists, farm managers and pesticide scientists, which may easily explore multidisciplinary research to fight against plant diseases. PlantPAD is freely available at http://plantpad.samlab.cn.

Novel statistical time series data augmentation and machine learning based classification of unobtrusive respiration data for respiration Digital Twin model

Digital Twin (DT), a concept of Healthcare (4.0), represents the subject's biological properties and characteristics in a digital model. DT can help in monitoring respiratory failures, enabling timely interventions, personalized treatment plans to improve healthcare, and decision-support for healthcare professionals. Large-scale implementation of DT technology requires extensive patient data for accurate monitoring and decision-making with Machine Learning (ML) and Deep Learning (DL). Initial respiration data was collected unobtrusively with the ESP32 Wi-Fi Channel State Information (CSI) sensor. Due to limited respiration data availability, the paper proposes a novel statistical time series data augmentation method for generating larger synthetic respiration data. To ensure accuracy and validity in the augmentation method, correlation methods (Pearson, Spearman, and Kendall) are implemented to provide a comparative analysis of experimental and synthetic datasets. Data processing methodologies of denoising (smoothing and filtering) and dimensionality reduction with Principal Component Analysis (PCA) are implemented to estimate a patient's Breaths Per Minute (BPM) from raw respiration sensor data and the synthetic version. The methodology provided the BPM estimation accuracy of 92.3% from raw respiration data. It was observed that out of 27 supervised classifications with k-fold cross-validation, the Bagged Tree ensemble algorithm provided the best ML-supervised classification. In the case of binary-class and multi-class, the Bagged Tree ensemble showed accuracies of 89.2% and 83.7% respectively with combined real and synthetic respiration dataset with the larger synthetic dataset. Overall, this provides a blueprint of methodologies for the development of the respiration DT model.

Ameliorating the effects of multiple stresses on agronomic traits in crops: modern biotechnological and omics approaches

While global climate change poses a significant environmental threat to agriculture, the increasing population is another big challenge to food security. To address this, developing crop varieties with increased productivity and tolerance to biotic and abiotic stresses is crucial. Breeders must identify traits to ensure higher and consistent yields under inconsistent environmental challenges, possess resilience against emerging biotic and abiotic stresses and satisfy customer demands for safer and more nutritious meals. With the advent of omics-based technologies, molecular tools are now integrated with breeding to understand the molecular genetics of genotype-based traits and develop better climate-smart crops. The rapid development of omics technologies offers an opportunity to generate novel datasets for crop species. Identifying genes and pathways responsible for significant agronomic traits has been made possible by integrating omics data with genetic and phenotypic information. This paper discusses the importance and use of omics-based strategies, including genomics, transcriptomics, proteomics and phenomics, for agricultural and horticultural crop improvement, which aligns with developing better adaptability in these crop species to the changing climate conditions.

Genome-wide association study on resistance of cultivated soybean to Fusarium oxysporum root rot in Northeast China

BACKGROUND

Fusarium oxysporum is a prevalent fungal pathogen that diminishes soybean yield through seedling disease and root rot. Preventing Fusarium oxysporum root rot (FORR) damage entails on the identification of resistance genes and developing resistant cultivars. Therefore, conducting fine mapping and marker development for FORR resistance genes is of great significance for fostering the cultivation of resistant varieties. In this study, 350 soybean germplasm accessions, mainly from Northeast China, underwent genotyping using the SoySNP50K Illumina BeadChip, which includes 52,041 single nucleotide polymorphisms (SNPs). Their resistance to FORR was assessed in a greenhouse. Genome-wide association studies utilizing the general linear model, mixed linear model, compressed mixed linear model, and settlement of MLM under progressively exclusive relationship models were conducted to identify marker-trait associations while effectively controlling for population structure.

RESULTS

The results demonstrated that these models effectively managed population structure. Eight SNP loci significantly associated with FORR resistance in soybean were detected, primarily located on Chromosome 6. Notably, there was a strong linkage disequilibrium between the large-effect SNPs ss715595462 and ss715595463, contributing substantially to phenotypic variation. Within the genetic interval encompassing these loci, 28 genes were present, with one gene Glyma.06G088400 encoding a protein kinase family protein containing a leucine-rich repeat domain identified as a potential candidate gene in the reference genome of Williams82. Additionally, quantitative real-time reverse transcription polymerase chain reaction analysis evaluated the gene expression levels between highly resistant and susceptible accessions, focusing on primary root tissues collected at different time points after F. oxysporum inoculation. Among the examined genes, only this gene emerged as the strongest candidate associated with FORR resistance.

CONCLUSIONS

The identification of this candidate gene Glyma.06G088400 improves our understanding of soybean resistance to FORR and the markers strongly linked to resistance can be beneficial for molecular marker-assisted selection in breeding resistant soybean accessions against F. oxysporum.

Predicting rice diseases using advanced technologies at different scales: present status and future perspectives

The past few years have witnessed significant progress in emerging disease detection techniques for accurately and rapidly tracking rice diseases and predicting potential solutions. In this review we focus on image processing techniques using machine learning (ML) and deep learning (DL) models related to multi-scale rice diseases. Furthermore, we summarize applications of different detection techniques, including genomic, physiological, and biochemical approaches. In addition, we also present the state-of-the-art in contemporary optical sensing applications of pathogen-plant interaction phenotypes. This review serves as a valuable resource for researchers seeking effective solutions to address the challenges of high-throughput data and model recognition for early detection of issues affecting rice crops through ML and DL models.

Thermal imaging: The digital eye facilitates high-throughput phenotyping traits of plant growth and stress responses

Plant phenotyping is important for plants to cope with environmental changes and ensure plant health. Imaging techniques are perceived as the most critical and reliable tools for studying plant phenotypes. Thermal imaging has opened up new opportunities for nondestructive imaging of plant phenotyping. However, a comprehensive summary of thermal imaging in plant phenotyping is still lacking. Here we discuss the progress and future prospects of thermal imaging for assessing plant growth and stress responses. First, we classify thermal imaging into ground-based and aerial platforms based on their adaptability to different experimental environments (including laboratory, greenhouse, and field). It is convenient to collect phenotypic information of different dimensions. Second, in order to enhance the efficiency of thermal image processing, automatic algorithms based on deep learning are employed instead of traditional manual methods, greatly reducing the time cost of experiments. Considering its ease of implementation, handling and instant response, thermal imaging has been widely used in research on environmental stress, crop yield, and seed vigor. We have found that thermal imaging can detect thermal energy dissipation caused by living organisms (e.g., pests, viruses, bacteria, fungi, and oomycetes), enabling early disease diagnosis. It also recognizes changes leaf surface temperatures resulting from reduced transpiration rates caused by nutrient deficiency, drought, salinity, or freezing. Furthermore, thermal imaging predicts crop yield under different water states and forecasts the viability of dormant seeds after water absorption by monitoring temperature changes in the seeds. This work will assist biologists and agronomists in studying plant phenotypes and serve a guide for breeders to develop high-yielding, stress-tolerant, and superior crops.

Artificial intelligence-driven systems engineering for next-generation plant-derived biopharmaceuticals

Recombinant biopharmaceuticals including antigens, antibodies, hormones, cytokines, single-chain variable fragments, and peptides have been used as vaccines, diagnostics and therapeutics. Plant molecular pharming is a robust platform that uses plants as an expression system to produce simple and complex recombinant biopharmaceuticals on a large scale. Plant system has several advantages over other host systems such as humanized expression, glycosylation, scalability, reduced risk of human or animal pathogenic contaminants, rapid and cost-effective production. Despite many advantages, the expression of recombinant proteins in plant system is hindered by some factors such as non-human post-translational modifications, protein misfolding, conformation changes and instability. Artificial intelligence (AI) plays a vital role in various fields of biotechnology and in the aspect of plant molecular pharming, a significant increase in yield and stability can be achieved with the intervention of AI-based multi-approach to overcome the hindrance factors. Current limitations of plant-based recombinant biopharmaceutical production can be circumvented with the aid of synthetic biology tools and AI algorithms in plant-based glycan engineering for protein folding, stability, viability, catalytic activity and organelle targeting. The AI models, including but not limited to, neural network, support vector machines, linear regression, Gaussian process and regressor ensemble, work by predicting the training and experimental data sets to design and validate the protein structures thereby optimizing properties such as thermostability, catalytic activity, antibody affinity, and protein folding. This review focuses on, integrating systems engineering approaches and AI-based machine learning and deep learning algorithms in protein engineering and host engineering to augment protein production in plant systems to meet the ever-expanding therapeutics market.

Maize Feature Store: A centralized resource to manage and analyze curated maize multi-omics features for machine learning applications

The big-data analysis of complex data associated with maize genomes accelerates genetic research and improves agronomic traits. As a result, efforts have increased to integrate diverse datasets and extract meaning from these measurements. Machine learning models are a powerful tool for gaining knowledge from large and complex datasets. However, these models must be trained on high-quality features to succeed. Currently, there are no solutions to host maize multi-omics datasets with end-to-end solutions for evaluating and linking features to target gene annotations. Our work presents the Maize Feature Store (MFS), a versatile application that combines features built on complex data to facilitate exploration, modeling and analysis. Feature stores allow researchers to rapidly deploy machine learning applications by managing and providing access to frequently used features. We populated the MFS for the maize reference genome with over 14 000 gene-based features based on published genomic, transcriptomic, epigenomic, variomic and proteomics datasets. Using the MFS, we created an accurate pan-genome classification model with an AUC-ROC score of 0.87. The MFS is publicly available through the maize genetics and genomics database. Database URL  https://mfs.maizegdb.org/.

Identification of apple leaf disease via novel attention mechanism based convolutional neural network

Introduction

The identification of apple leaf diseases is crucial for apple production.

Methods

To assist farmers in promptly recognizing leaf diseases in apple trees, we propose a novel attention mechanism. Building upon this mechanism and MobileNet v3, we introduce a new deep learning network.

Results and discussion

Applying this network to our carefully curated dataset, we achieved an impressive accuracy of 98.7% in identifying apple leaf diseases, surpassing similar models such as EfficientNet-B0, ResNet-34, and DenseNet-121. Furthermore, the precision, recall, and f1-score of our model also outperform these models, while maintaining the advantages of fewer parameters and less computational consumption of the MobileNet network. Therefore, our model has the potential in other similar application scenarios and has broad prospects.

Modeling the spatial-spectral characteristics of plants for nutrient status identification using hyperspectral data and deep learning methods

Sustainable fertilizer management in precision agriculture is essential for both economic and environmental reasons. To effectively manage fertilizer input, various methods are employed to monitor and track plant nutrient status. One such method is hyperspectral imaging, which has been on the rise in recent times. It is a remote sensing tool used to monitor plant physiological changes in response to environmental conditions and nutrient availability. However, conventional hyperspectral processing mainly focuses on either the spectral or spatial information of plants. This study aims to develop a hybrid convolution neural network (CNN) capable of simultaneously extracting spatial and spectral information from quinoa and cowpea plants to identify their nutrient status at different growth stages. To achieve this, a nutrient experiment with four treatments (high and low levels of nitrogen and phosphorus) was conducted in a glasshouse. A hybrid CNN model comprising a 3D CNN (extracts joint spectral-spatial information) and a 2D CNN (for abstract spatial information extraction) was proposed. Three pre-processing techniques, including second-order derivative, standard normal variate, and linear discriminant analysis, were applied to selected regions of interest within the plant spectral hypercube. Together with the raw data, these datasets were used as inputs to train the proposed model. This was done to assess the impact of different pre-processing techniques on hyperspectral-based nutrient phenotyping. The performance of the proposed model was compared with a 3D CNN, a 2D CNN, and a Hybrid Spectral Network (HybridSN) model. Effective wavebands were selected from the best-performing dataset using a greedy stepwise-based correlation feature selection (CFS) technique. The selected wavebands were then used to retrain the models to identify the nutrient status at five selected plant growth stages. From the results, the proposed hybrid model achieved a classification accuracy of over 94% on the test dataset, demonstrating its potential for identifying nitrogen and phosphorus status in cowpea and quinoa at different growth stages.

Deep learning for plant bioinformatics: an explainable gradient-based approach for disease detection

Emerging in the realm of bioinformatics, plant bioinformatics integrates computational and statistical methods to study plant genomes, transcriptomes, and proteomes. With the introduction of high-throughput sequencing technologies and other omics data, the demand for automated methods to analyze and interpret these data has increased. We propose a novel explainable gradient-based approach EG-CNN model for both omics data and hyperspectral images to predict the type of attack on plants in this study. We gathered gene expression, metabolite, and hyperspectral image data from plants afflicted with four prevalent diseases: powdery mildew, rust, leaf spot, and blight. Our proposed EG-CNN model employs a combination of these omics data to learn crucial plant disease detection characteristics. We trained our model with multiple hyperparameters, such as the learning rate, number of hidden layers, and dropout rate, and attained a test set accuracy of 95.5%. We also conducted a sensitivity analysis to determine the model's resistance to hyperparameter variations. Our analysis revealed that our model exhibited a notable degree of resilience in the face of these variations, resulting in only marginal changes in performance. Furthermore, we conducted a comparative examination of the time efficiency of our EG-CNN model in relation to baseline models, including SVM, Random Forest, and Logistic Regression. Although our model necessitates additional time for training and validation due to its intricate architecture, it demonstrates a faster testing time per sample, offering potential advantages in real-world scenarios where speed is paramount. To gain insights into the internal representations of our EG-CNN model, we employed saliency maps for a qualitative analysis. This visualization approach allowed us to ascertain that our model effectively captures crucial aspects of plant disease, encompassing alterations in gene expression, metabolite levels, and spectral discrepancies within plant tissues. Leveraging omics data and hyperspectral images, this study underscores the potential of deep learning methods in the realm of plant disease detection. The proposed EG-CNN model exhibited impressive accuracy and displayed a remarkable degree of insensitivity to hyperparameter variations, which holds promise for future plant bioinformatics applications.

Towards the synthesis of spectral imaging and machine learning-based approaches for non-invasive phenotyping of plants

High-throughput phenotyping is now central to the progress of plant sciences, accelerated breeding, and precision farming. The power of phenotyping comes from the automated, rapid, non-invasive collection of large datasets describing plant objects. In this context, the goal of extracting relevant information from different kinds of images is of paramount importance. We review both the spectral and machine learning-based approaches to imaging of plants for the purpose of their phenotyping. The advantages and drawbacks of both approaches will be discussed with a focus on the monitoring of plants. We argue that an emerging approach combining the strengths of the spectral and the machine learning-based approaches will remain a promising direction in plant phenotyping in the nearest future.

Quantifying physiological trait variation with automated hyperspectral imaging in rice

Advancements in hyperspectral imaging (HSI) together with the establishment of dedicated plant phenotyping facilities worldwide have enabled high-throughput collection of plant spectral images with the aim of inferring target phenotypes. Here, we test the utility of HSI-derived canopy data, which were collected as part of an automated plant phenotyping system, to predict physiological traits in cultivated Asian rice (Oryza sativa). We evaluated 23 genetically diverse rice accessions from two subpopulations under two contrasting nitrogen conditions and measured 14 leaf- and canopy-level parameters to serve as ground-reference observations. HSI-derived data were used to (1) classify treatment groups across multiple vegetative stages using support vector machines (≥ 83% accuracy) and (2) predict leaf-level nitrogen content (N, %, n=88) and carbon to nitrogen ratio (C:N, n=88) with Partial Least Squares Regression (PLSR) following RReliefF wavelength selection (validation: R 2 = 0.797 and RMSEP = 0.264 for N; R 2 = 0.592 and RMSEP = 1.688 for C:N). Results demonstrated that models developed using training data from one rice subpopulation were able to predict N and C:N in the other subpopulation, while models trained on a single treatment group were not able to predict samples from the other treatment. Finally, optimization of PLSR-RReliefF hyperparameters showed that 300-400 wavelengths generally yielded the best model performance with a minimum calibration sample size of 62. Results support the use of canopy-level hyperspectral imaging data to estimate leaf-level N and C:N across diverse rice, and this work highlights the importance of considering calibration set design prior to data collection as well as hyperparameter optimization for model development in future studies.

Plant and Disease Recognition Based on PMF Pipeline Domain Adaptation Method: Using Bark Images as Meta-Dataset

Efficient image recognition is important in crop and forest management. However, it faces many challenges, such as the large number of plant species and diseases, the variability of plant appearance, and the scarcity of labeled data for training. To address this issue, we modified a SOTA Cross-Domain Few-shot Learning (CDFSL) method based on prototypical networks and attention mechanisms. We employed attention mechanisms to perform feature extraction and prototype generation by focusing on the most relevant parts of the images, then used prototypical networks to learn the prototype of each category and classify new instances. Finally, we demonstrated the effectiveness of the modified CDFSL method on several plant and disease recognition datasets. The results showed that the modified pipeline was able to recognize several cross-domain datasets using generic representations, and achieved up to 96.95% and 94.07% classification accuracy on datasets with the same and different domains, respectively. In addition, we visualized the experimental results, demonstrating the model's stable transfer capability between datasets and the model's high visual correlation with plant and disease biological characteristics. Moreover, by extending the classes of different semantics within the training dataset, our model can be generalized to other domains, which implies broad applicability.

Regulation of plant epigenetic memory in response to cold and heat stress: towards climate resilient agriculture

Plants have evolved to adapt and grow in hot and cold climatic conditions. Some also adapt to daily and seasonal temperature changes. Epigenetic modifications play an important role in regulating plant tolerance under such conditions. DNA methylation and post-translational modifications of histone proteins influence gene expression during plant developmental stages and under stress conditions, including cold and heat stress. While short-term modifications are common, some modifications may persist and result in stress memory that can be inherited by subsequent generations. Understanding the mechanisms of epigenomes responding to stress and the factors that trigger stress memory is crucial for developing climate-resilient agriculture, but such an integrated view is currently limited. This review focuses on the plant epigenetic stress memory during cold and heat stress. It also discusses the potential of machine learning to modify stress memory through epigenetics to develop climate-resilient crops.

Sugarcane nitrogen nutrition estimation with digital images and machine learning methods

The color and texture characteristics of crops can reflect their nitrogen (N) nutrient status and help optimize N fertilizer management. This study conducted a one-year field experiment to collect sugarcane leaf images at tillering and elongation stages using a commercial digital camera and extract leaf image color feature (CF) and texture feature (TF) parameters using digital image processing techniques. By analyzing the correlation between leaf N content and feature parameters, feature dimensionality reduction was performed using principal component analysis (PCA), and three regression methods (multiple linear regression; MLR, random forest regression; RF, stacking fusion model; SFM) were used to construct N content estimation models based on different image feature parameters. All models were built using five-fold cross-validation and grid search to verify the model performance and stability. The results showed that the models based on color-texture integrated principal component features (C-T-PCA) outperformed the single-feature models based on CF or TF. Among them, SFM had the highest accuracy for the validation dataset with the model coefficient of determination (R2) of 0.9264 for the tillering stage and 0.9111 for the elongation stage, with the maximum improvement of 9.85% and 8.91%, respectively, compared with the other tested models. In conclusion, the SFM framework based on C-T-PCA combines the advantages of multiple models to enhance the model performance while enhancing the anti-interference and generalization capabilities. Combining digital image processing techniques and machine learning facilitates fast and nondestructive estimation of crop N-substance nutrition.

To What Extent Does Yellow Rust Infestation Affect Remotely Sensed Nitrogen Status?

The utilization of high-throughput in-field phenotyping systems presents new opportunities for evaluating crop stress. However, existing studies have primarily focused on individual stresses, overlooking the fact that crops in field conditions frequently encounter multiple stresses, which can display similar symptoms or interfere with the detection of other stress factors. Therefore, this study aimed to investigate the impact of wheat yellow rust on reflectance measurements and nitrogen status assessment. A multi-sensor mobile platform was utilized to capture RGB and multispectral images throughout a 2-year fertilization-fungicide trial. To identify disease-induced damage, the SegVeg approach, which combines a U-NET architecture and a pixel-wise classifier, was applied to RGB images, generating a mask capable of distinguishing between healthy and damaged areas of the leaves. The observed proportion of damage in the images demonstrated similar effectiveness to visual scoring methods in explaining grain yield. Furthermore, the study discovered that the disease not only affected reflectance through leaf damage but also influenced the reflectance of healthy areas by disrupting the overall nitrogen status of the plants. This emphasizes the importance of incorporating disease impact into reflectance-based decision support tools to account for its effects on spectral data. This effect was successfully mitigated by employing the NDRE vegetation index calculated exclusively from the healthy portions of the leaves or by incorporating the proportion of damage into the model. However, these findings also highlight the necessity for further research specifically addressing the challenges presented by multiple stresses in crop phenotyping.

Integrated Genomic Selection for Accelerating Breeding Programs of Climate-Smart Cereals

Rapidly rising population and climate changes are two critical issues that require immediate action to achieve sustainable development goals. The rising population is posing increased demand for food, thereby pushing for an acceleration in agricultural production. Furthermore, increased anthropogenic activities have resulted in environmental pollution such as water pollution and soil degradation as well as alterations in the composition and concentration of environmental gases. These changes are affecting not only biodiversity loss but also affecting the physio-biochemical processes of crop plants, resulting in a stress-induced decline in crop yield. To overcome such problems and ensure the supply of food material, consistent efforts are being made to develop strategies and techniques to increase crop yield and to enhance tolerance toward climate-induced stress. Plant breeding evolved after domestication and initially remained dependent on phenotype-based selection for crop improvement. But it has grown through cytological and biochemical methods, and the newer contemporary methods are based on DNA-marker-based strategies that help in the selection of agronomically useful traits. These are now supported by high-end molecular biology tools like PCR, high-throughput genotyping and phenotyping, data from crop morpho-physiology, statistical tools, bioinformatics, and machine learning. After establishing its worth in animal breeding, genomic selection (GS), an improved variant of marker-assisted selection (MAS), has made its way into crop-breeding programs as a powerful selection tool. To develop novel breeding programs as well as innovative marker-based models for genetic evaluation, GS makes use of molecular genetic markers. GS can amend complex traits like yield as well as shorten the breeding period, making it advantageous over pedigree breeding and marker-assisted selection (MAS). It reduces the time and resources that are required for plant breeding while allowing for an increased genetic gain of complex attributes. It has been taken to new heights by integrating innovative and advanced technologies such as speed breeding, machine learning, and environmental/weather data to further harness the GS potential, an approach known as integrated genomic selection (IGS). This review highlights the IGS strategies, procedures, integrated approaches, and associated emerging issues, with a special emphasis on cereal crops. In this domain, efforts have been taken to highlight the potential of this cutting-edge innovation to develop climate-smart crops that can endure abiotic stresses with the motive of keeping production and quality at par with the global food demand.

Inside out: transforming images of lab-grown plants for machine learning applications in agriculture

Introduction

Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of different growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available.

Methods

In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images.

Results

Furthermore, we use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images.

Discussion

The inclusion of training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data.

Recent advances in artificial intelligence, mechanistic models, and speed breeding offer exciting opportunities for precise and accelerated genomics-assisted breeding

Given the challenges of population growth and climate change, there is an urgent need to expedite the development of high-yielding stress-tolerant crop cultivars. While traditional breeding methods have been instrumental in ensuring global food security, their efficiency, precision, and labour intensiveness have become increasingly inadequate to address present and future challenges. Fortunately, recent advances in high-throughput phenomics and genomics-assisted breeding (GAB) provide a promising platform for enhancing crop cultivars with greater efficiency. However, several obstacles must be overcome to optimize the use of these techniques in crop improvement, such as the complexity of phenotypic analysis of big image data. In addition, the prevalent use of linear models in genome-wide association studies (GWAS) and genomic selection (GS) fails to capture the nonlinear interactions of complex traits, limiting their applicability for GAB and impeding crop improvement. Recent advances in artificial intelligence (AI) techniques have opened doors to nonlinear modelling approaches in crop breeding, enabling the capture of nonlinear and epistatic interactions in GWAS and GS and thus making this variation available for GAB. While statistical and software challenges persist in AI-based models, they are expected to be resolved soon. Furthermore, recent advances in speed breeding have significantly reduced the time (3-5-fold) required for conventional breeding. Thus, integrating speed breeding with AI and GAB could improve crop cultivar development within a considerably shorter timeframe while ensuring greater accuracy and efficiency. In conclusion, this integrated approach could revolutionize crop breeding paradigms and safeguard food production in the face of population growth and climate change.

Glyphosate Separating and Sensing for Precision Agriculture and Environmental Protection in the Era of Smart Materials

The present article critically and comprehensively reviews the most recent reports on smart sensors for determining glyphosate (GLP), an active agent of GLP-based herbicides (GBHs) traditionally used in agriculture over the past decades. Commercialized in 1974, GBHs have now reached 350 million hectares of crops in over 140 countries with an annual turnover of 11 billion USD worldwide. However, rolling exploitation of GLP and GBHs in the last decades has led to environmental pollution, animal intoxication, bacterial resistance, and sustained occupational exposure of the herbicide of farm and companies' workers. Intoxication with these herbicides dysregulates the microbiome-gut-brain axis, cholinergic neurotransmission, and endocrine system, causing paralytic ileus, hyperkalemia, oliguria, pulmonary edema, and cardiogenic shock. Precision agriculture, i.e., an (information technology)-enhanced approach to crop management, including a site-specific determination of agrochemicals, derives from the benefits of smart materials (SMs), data science, and nanosensors. Those typically feature fluorescent molecularly imprinted polymers or immunochemical aptamer artificial receptors integrated with electrochemical transducers. Fabricated as portable or wearable lab-on-chips, smartphones, and soft robotics and connected with SM-based devices that provide machine learning algorithms and online databases, they integrate, process, analyze, and interpret massive amounts of spatiotemporal data in a user-friendly and decision-making manner. Exploited for the ultrasensitive determination of toxins, including GLP, they will become practical tools in farmlands and point-of-care testing. Expectedly, smart sensors can be used for personalized diagnostics, real-time water, food, soil, and air quality monitoring, site-specific herbicide management, and crop control.