Proximal Methods for Plant Stress Detection Using Optical Sensors and Machine Learning

Non-invasive laser bio-speckle technique for the study of optical irradiation on plant leaf lamina: Application to monitor salicylic acid modulated response in Zamioculcas zamiifolia

The intensity of light is one of the major factors influencing the rate of plant physiological activity. For optimization of the agricultural lighting necessary for plant growth, it is vital to understand the plant behavioral response under different light intensities. In the present study, the dynamic activity due to the physiological phenomena in the leaf of a plant when exposed to optical radiation from artificial LED sources is quantified non-destructively. The laser bio-speckle algorithm of obtaining Inertia Moment (IM) values from the Time History of Speckle Patterns (THSP) is utilized as a quantitative measure of the plant leaf dynamic activity. The plant leaf laminas were probed using the laser and the IM values were generated. The dynamic activity variations with the increase in optical intensity were studied on the leaves of Philodendron erubescens, Syngonium podophyllum, Piper nigrum, Plectranthus amboinicus and Epipremnum aureum. The obtained results reveal a unique pattern for each plant leaf and displayed consistent repeatability under fixed experimental conditions. The method was extended to monitor dynamic activity variation with optical irradiation intensity in Zamioculas zamiifolia leaves before and after treatment with salicylic acid, a measure to induce hormonal cross-talks. The obtained results were validated using biochemical estimation techniques and can be useful insights for the development of a non-invasive sensor for analyzing the plant's physiological activity under various light intensity conditions. The present study is the first of its kind to elucidate the viability of conducting a non-invasive analysis of abiotic stress effects on a sample and control plant using laser speckle technique.

Affordable Phenotyping at the Edge for High-Throughput Detection of Hypersensitive Reaction Involving Cotyledon Loss

The use of low-cost depth imaging sensors is investigated to automate plant pathology tests. Spatial evolution is explored to discriminate plant resistance through the hypersensitive reaction involving cotyledon loss. A high temporal frame rate and a protocol operating with batches of plants enable to compensate for the low spatial resolution of depth cameras. Despite the high density of plants, a spatial drop of the depth is observed when the cotyledon loss occurs. We introduce a small and simple spatiotemporal feature space which is shown to carry enough information to automate the discrimination between batches of resistant (loss of cotyledons) and susceptible plants (no loss of cotyledons) with 97% accuracy and with a timing 30 times faster than for human annotation. The robustness of the method-in terms of density of plants in the batch and possible internal batch desynchronization-is assessed successfully with hundreds of varieties of Pepper in various environments. A study on the generalizability of the method suggests that it can be extended to other pathosystems and also to segregating plants, i.e., intermediate state with batches composed of resistant and susceptible plants. The imaging system developed, combined with the feature extraction method and classification model, provides a full pipeline with unequaled throughput and cost efficiency by comparison with the state-of-the-art one. This system can be deployed as a decision-support tool but is also compatible with a standalone technology where computation is done at the edge in real time.

A Prototype Method for the Detection and Recognition of Pigments in the Environment Based on Optical Property Simulation

The possibility of pigment detection and recognition in different environments such as solvents or proteins is a challenging, and at the same time demanding, task. It may be needed in very different situations: from the nondestructive in situ identification of pigments in paintings to the early detection of fungal infection in major agro-industrial crops and products. So, we propose a prototype method, the key feature of which is a procedure analyzing the lineshape of a spectrum. The shape of the absorption spectrum corresponding to this transition strongly depends on the immediate environment of a pigment and can serve as a marker to detect the presence of a particular pigment molecule in a sample. Considering carotenoids as an object of study, we demonstrate that the combined operation of the differential evolution algorithm and semiclassical quantum modeling of the optical response based on a generalized spectral density (the number of vibronic modes is arbitrary) allows us to distinguish quantum models of the pigment for different solvents. Moreover, it is determined that to predict the optical properties of monomeric pigments in protein, it is necessary to create a database containing, for each pigment, in addition to the absorption spectra measured in a predefined set of solvents, the parameters of the quantum model found using differential evolution.

Comparison of the Efficiency of Hyperspectral and Pulse Amplitude Modulation Imaging Methods in Pre-Symptomatic Virus Detection in Tobacco Plants

Early detection of pathogens can significantly reduce yield losses and improve the quality of agricultural products. This study compares the efficiency of hyperspectral (HS) imaging and pulse amplitude modulation (PAM) fluorometry to detect pathogens in plants. Reflectance spectra, normalized indices, and fluorescence parameters were studied in healthy and infected areas of leaves. Potato virus X with GFP fluorescent protein was used to assess the spread of infection throughout the plant. The study found that infection increased the reflectance of leaves in certain wavelength ranges. Analysis of the normalized reflectance indices (NRIs) revealed indices that were sensitive and insensitive to infection. NRI700/850 was optimal for virus detection; significant differences were detected on the 4th day after the virus arrived in the leaf. Maximum (Fv/Fm) and effective quantum yields of photosystem II (ΦPSII) and non-photochemical fluorescence quenching (NPQ) were almost unchanged at the early stage of infection. ΦPSII and NPQ in the transition state (a short time after actinic light was switched on) showed high sensitivity to infection. The higher sensitivity of PAM compared to HS imaging may be due to the possibility of assessing the physiological changes earlier than changes in leaf structure.

An overview of image-based phenotyping as an adaptive 4.0 technology for studying plant abiotic stress: A bibliometric and literature review

Improving the tolerance of crop species to abiotic stresses that limit plant growth and productivity is essential for mitigating the emerging problems of global warming. In this context, imaged data analysis represents an effective method in the 4.0 technology era, where this method has the non-destructive and recursive characterization of plant phenotypic traits as selection criteria. So, the plant breeders are helped in the development of adapted and climate-resilient crop varieties. Although image-based phenotyping has recently resulted in remarkable improvements for identifying the crop status under a range of growing conditions, the topic of its application for assessing the plant behavioral responses to abiotic stressors has not yet been extensively reviewed. For such a purpose, bibliometric analysis is an ideal analytical concept to analyze the evolution and interplay of image-based phenotyping to abiotic stresses by objectively reviewing the literature in light of existing database. Bibliometricy, a bibliometric analysis was applied using a systematic methodology which involved data mining, mining data improvement and analysis, and manuscript construction. The obtained results indicate that there are 554 documents related to image-based phenotyping to abiotic stress until 5 January 2023. All document showed the future development trends of image-based phenotyping will be mainly centered in the United States, European continent and China. The keywords analysis major focus to the application of 4.0 technology and machine learning in plant breeding, especially to create the tolerant variety under abiotic stresses. Drought and saline become an abiotic stress often using image-based phenotyping. Besides that, the rice, wheat and maize as the main commodities in this topic. In conclusion, the present work provides information on resolutive interactions in developing image-based phenotyping to abiotic stress, especially optimizing high-throughput sensors in image-based phenotyping for the future development.

Nitrogen deficiency in maize: Annotated image classification dataset

Nitrogen (N) is one of the key inputs in maize production applied in the form of fertilizers. Nitrogen deficiency during the vegetation period leads to lower yields since N is utilized in proteins and enzymes that enable important biochemical processes such as photosynthesis. Nitrogen deficiency leads to specific symptoms that eventually become visible to the naked eye during vegetation. Our hypothesis was that N deficiency can be detected from maize RGB images in parametric process such as a deep neural network. The aim of the reported dataset is to optimize the usage of N in the farmer's fields and accordingly, reduce its environmental footprint. This dataset contains 1200 images of maize canopy from field trials, annotated by an expert from an agricultural institution. The field trials included three levels of N fertilization: N0 without N fertilization, N75 with 75 kg of added N fertilizer, and NFull with 136 kg of added N fertilizer. For each fertilizer level, 400 plots were created with 238 different maize genotypes, resulting in a total of 1200 plots. Images were taken with a tripod mounted DSLR camera, aperture priority set to f/8 and sensor sensitivity set to ISO400. Images were taken at a 45° angle to each plot. This dataset can be useful to both researchers, data scientists and agronomists, especially in the context of emerging technologies in precision agriculture, such as robotics, 5G networks and unmanned aerial vehicle (UAV). The dataset is one of the first publicly accessible datasets of maize canopy images under different N fertilization levels and represents a valuable public resource for development of machine learning models for in-season detection of N deficiency in maize.

Machine learning in photosynthesis: Prospects on sustainable crop development

Improving photosynthesis is a promising avenue to increase food security. Studying photosynthetic traits with the aim to improve efficiency has been one of many strategies to increase crop yield but analyzing large data sets presents an ongoing challenge. Machine learning (ML) represents a ubiquitous tool that can provide a more elaborate data analysis. Here we review the application of ML in various domains of photosynthetic research, as well as in photosynthetic pigment studies. We highlight how correlating hyperspectral data with photosynthetic parameters to improve crop yield could be achieved through various ML algorithms. We also propose strategies to employ ML in promoting photosynthetic pigment research for furthering crop yield.

Impacts of heat, drought, and combined heat-drought stress on yield, phenotypic traits, and gluten protein traits: capturing stability of spring wheat in excessive environments

Wheat production and end-use quality are severely threatened by drought and heat stresses. This study evaluated stress impacts on phenotypic and gluten protein characteristics of eight spring wheat genotypes (Diskett, Happy, Bumble, SW1, SW2, SW3, SW4, and SW5) grown to maturity under controlled conditions (Biotron) using RGB imaging and size-exclusion high-performance liquid chromatography (SE-HPLC). Among the stress treatments compared, combined heat-drought stress had the most severe negative impacts on biomass (real and digital), grain yield, and thousand kernel weight. Conversely, it had a positive effect on most gluten parameters evaluated by SE-HPLC and resulted in a positive correlation between spike traits and gluten strength, expressed as unextractable gluten polymer (%UPP) and large monomeric protein (%LUMP). The best performing genotypes in terms of stability were Happy, Diskett, SW1, and SW2, which should be further explored as attractive breeding material for developing climate-resistant genotypes with improved bread-making quality. RGB imaging in combination with gluten protein screening by SE-HPLC could thus be a valuable approach for identifying climate stress-tolerant wheat genotypes.

Current and emerging trends in techniques for plant pathogen detection

Plant pathogenic microorganisms cause substantial yield losses in several economically important crops, resulting in economic and social adversity. The spread of such plant pathogens and the emergence of new diseases is facilitated by human practices such as monoculture farming and global trade. Therefore, the early detection and identification of pathogens is of utmost importance to reduce the associated agricultural losses. In this review, techniques that are currently available to detect plant pathogens are discussed, including culture-based, PCR-based, sequencing-based, and immunology-based techniques. Their working principles are explained, followed by an overview of the main advantages and disadvantages, and examples of their use in plant pathogen detection. In addition to the more conventional and commonly used techniques, we also point to some recent evolutions in the field of plant pathogen detection. The potential use of point-of-care devices, including biosensors, have gained in popularity. These devices can provide fast analysis, are easy to use, and most importantly can be used for on-site diagnosis, allowing the farmers to take rapid disease management decisions.

A Synthetic Review of Various Dimensions of Non-Destructive Plant Stress Phenotyping

Non-destructive plant stress phenotyping begins with traditional one-dimensional (1D) spectroscopy, followed by two-dimensional (2D) imaging, three-dimensional (3D) or even temporal-three-dimensional (T-3D), spectral-three-dimensional (S-3D), and temporal-spectral-three-dimensional (TS-3D) phenotyping, all of which are aimed at observing subtle changes in plants under stress. However, a comprehensive review that covers all these dimensional types of phenotyping, ordered in a spatial arrangement from 1D to 3D, as well as temporal and spectral dimensions, is lacking. In this review, we look back to the development of data-acquiring techniques for various dimensions of plant stress phenotyping (1D spectroscopy, 2D imaging, 3D phenotyping), as well as their corresponding data-analyzing pipelines (mathematical analysis, machine learning, or deep learning), and look forward to the trends and challenges of high-performance multi-dimension (integrated spatial, temporal, and spectral) phenotyping demands. We hope this article can serve as a reference for implementing various dimensions of non-destructive plant stress phenotyping.

Proximal hyperspectral sensing of abiotic stresses in plants

Recent attempts, advances and challenges, as well as future perspectives regarding the application of proximal hyperspectral sensing (where sensors are placed within 10 m above plants, either on land-based platforms or in controlled environments) to assess plant abiotic stresses have been critically reviewed. Abiotic stresses, caused by either physical or chemical reasons such as nutrient deficiency, drought, salinity, heavy metals, herbicides, extreme temperatures, and so on, may be more damaging than biotic stresses (affected by infectious agents such as bacteria, fungi, insects, etc.) on crop yields. The proximal hyperspectral sensing provides images at a sub-millimeter spatial resolution for doing an in-depth study of plant physiology and thus offers a global view of the plant's status and allows for monitoring spatio-temporal variations from large geographical areas reliably and economically. The literature update has been based on 362 research papers in this field, published from 2010, most of which are from four years ago and, in our knowledge, it is the first paper that provides a comprehensive review of the applications of the technique for the detection of various types of abiotic stresses in plants.

Paper-based optical sensors paired with smartphones for biomedical analysis

The traditional analytical methods used for biomedical analysis are expensive and not easy to handle and require sophisticated instruments, thus their application is limited in resource-limited settings. Due to their portability, low cost, and ability to be applied to different analytical techniques, paper-based analytical devices are becoming valuable tools for biomedical analysis. The integration of smartphones into analytical devices has provided the ability to build portable, cost-effective, straightforward analytical devices for biomedical analysis and mobile health. The key aim of this review is to emphasize the recent applications of PADs combined with a smartphone for the optical analysis of biomedical species. We started this review by highlighting the type of papers and their modifications with different materials to prepare the PADs. After that, this review presents various detection methods including colorimetry, fluorescence, and luminescence where the smartphone is used for read-out. In the end, we provided the recent applications of the analysis of different biomedical compounds such as cancer and cardiovascular biomarkers, metal ions, glucose, viruses, etc. We believe that the present review will attract a wide scientific community in the areas of analytical chemistry, sensors, and clinical testing.

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

The ornamental crop industry is an important contributor to the economy in the United States. The industry has been facing challenges due to continuously increasing labor and agricultural input costs. Sensing and automation technologies have been introduced to reduce labor requirements and to ensure efficient management operations. This article reviews current sensing and automation technologies used for ornamental nursery crop production and highlights prospective technologies that can be applied for future applications. Applications of sensors, computer vision, artificial intelligence (AI), machine learning (ML), Internet-of-Things (IoT), and robotic technologies are reviewed. Some advanced technologies, including 3D cameras, enhanced deep learning models, edge computing, radio-frequency identification (RFID), and integrated robotics used for other cropping systems, are also discussed as potential prospects. This review concludes that advanced sensing, AI and robotic technologies are critically needed for the nursery crop industry. Adapting these current and future innovative technologies will benefit growers working towards sustainable ornamental nursery crop production.

Continuous monitoring of chemical signals in plants under stress

Time is an often-neglected variable in biological research. Plants respond to biotic and abiotic stressors with a range of chemical signals, but as plants are non-equilibrium systems, single-point measurements often cannot provide sufficient temporal resolution to capture these time-dependent signals. In this article, we critically review the advances in continuous monitoring of chemical signals in living plants under stress. We discuss methods for sustained measurement of the most important chemical species, including ions, organic molecules, inorganic molecules and radicals. We examine analytical and modelling approaches currently used to identify and predict stress in plants. We also explore how the methods discussed can be used for applications beyond a research laboratory, in agricultural settings. Finally, we present the current challenges and future perspectives for the continuous monitoring of chemical signals in plants.

The impact of tritium phytoremediation on plant health as measured by fluorescence

Phytoremediation, using plants for soil, sediment, or water contaminant clean-up, is an established technology dependent on plant health. Tritium (3H), a radioactive isotope of hydrogen that is generally found in the environment as tritiated water (HTO), is a low-level beta emitter with a half-life of 12.32 years. Chlorophyll fluorescence (CF) for monitoring risk assessment of tritium to plant health was conducted at the Tritium Irrigation Facility (TIF) located on the US Department of Energy's Savannah River Site (SRS) near Aiken, SC. Two fluorometers were evaluated in conjunction with phytoremediation at the 25 -acre TIF where tritiated groundwater is being spray-irrigated on a mixed coniferous/deciduous forested watershed as a means of reducing tritium release to a nearby stream that serves as a tributary to the Savannah River. Tritium activity in irrigated water averaged 104 + 42 pCi mL-1 during the 2003 project. Fluorescence parameters measured by the two fluorometers were well correlated with each other (p < 0.0001). Tritium in water respired from oak leaves ranged up to 1845.13 pCi ml-1 and 2138.22 pCi ml-1 in pine needles. Trees in both the test and control sites were approximately 15 years old. Here we demonstrated that fluorescence parameters provide an effective way to estimate the impact of HTO on plant health in a noninvasive, extremely rapid, and cost-effective manner. In the current study applying fluorometry, plants within the TIF phytoremediation site exposed to the site tritiated water were not significantly impacted by the tritium phytoremediation based on CF parameters as compared to the control, a nascent non-irrigated site.

Integrating spaceborne LiDAR and Sentinel-2 images to estimate forest aboveground biomass in Northern China

BACKGROUND

Fast and accurate forest aboveground biomass (AGB) estimation and mapping is the basic work of forest management and ecosystem dynamic investigation, which is of great significance to evaluate forest quality, resource assessment, and carbon cycle and management. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), as one of the latest launched spaceborne light detection and ranging (LiDAR) sensors, can penetrate the forest canopy and has the potential to obtain accurate forest vertical structure parameters on a large scale. However, the along-track segments of canopy height provided by ICESat-2 cannot be used to obtain comprehensive AGB spatial distribution. To make up for the deficiency of spaceborne LiDAR, the Sentinel-2 images provided by google earth engine (GEE) were used as the medium to integrate with ICESat-2 for continuous AGB mapping in our study. Ensemble learning can summarize the advantages of estimation models and achieve better estimation results. A stacking algorithm consisting of four non-parametric base models which are the backpropagation (BP) neural network, k-nearest neighbor (kNN), support vector machine (SVM), and random forest (RF) was proposed for AGB modeling and estimating in Saihanba forest farm, northern China.

RESULTS

The results show that stacking achieved the best AGB estimation accuracy among the models, with an R² of 0.71 and a root mean square error (RMSE) of 45.67 Mg/ha. The stacking resulted in the lowest estimation error with the decreases of RMSE by 22.6%, 27.7%, 23.4%, and 19.0% compared with those from the BP, kNN, SVM, and RF, respectively.

CONCLUSION

Compared with using Sentinel-2 alone, the estimation errors of all models have been significantly reduced after adding the LiDAR variables of ICESat-2 in AGB estimation. The research demonstrated that ICESat-2 has the potential to improve the accuracy of AGB estimation and provides a reference for dynamic forest resources management and monitoring.

Machine Learning in the Analysis of Multispectral Reads in Maize Canopies Responding to Increased Temperatures and Water Deficit

Real-time monitoring of crop responses to environmental deviations represents a new avenue for applications of remote and proximal sensing. Combining the high-throughput devices with novel machine learning (ML) approaches shows promise in the monitoring of agricultural production. The 3 × 2 multispectral arrays with responses at 610 and 680 nm (red), 730 and 760 nm (red-edge) and 810 and 860 nm (infrared) spectra were used to assess the occurrence of leaf rolling (LR) in 545 experimental maize plots measured four times for calibration dataset (n = 2180) and 145 plots measured once for external validation. Multispectral reads were used to calculate 15 simple normalized vegetation indices. Four ML algorithms were assessed: single and multilayer perceptron (SLP and MLP), convolutional neural network (CNN) and support vector machines (SVM) in three validation procedures, which were stratified cross-validation, random subset validation and validation with external dataset. Leaf rolling occurrence caused visible changes in spectral responses and calculated vegetation indexes. All algorithms showed good performance metrics in stratified cross-validation (accuracy >80%). SLP was the least efficient in predictions with external datasets, while MLP, CNN and SVM showed comparable performance. Combining ML with multispectral sensing shows promise in transition towards agriculture based on data-driven decisions especially considering the novel Internet of Things (IoT) avenues.

Assessing expected utility and profitability to support decision-making for disease control strategies in ornamental heather production

Many farmers hesitate to adopt new management strategies with actual or perceived risks and uncertainties. Especially in ornamental plant production, farmers often stick to current production strategies to avoid the risk of economically harmful plant losses, even though they may recognize the need to optimize farm management. This work focused on the economically important and little-researched production system of ornamental heather (Calluna vulgaris) to help farmers find appropriate measures to sustainably improve resource use, plant quality, and profitability despite existing risks. Probabilistic cost-benefit analysis was applied to simulate alternative disease monitoring strategies. The outcomes for more intensive visual monitoring, as well as sensor-based monitoring using hyperspectral imaging were simulated. Based on the results of the probabilistic cost-benefit analysis, the expected utility of the alternative strategies was assessed as a function of the farmer's level of risk aversion. The analysis of expected utility indicated that heather production is generally risky. Concerning the alternative strategies, more intensive visual monitoring provides the highest utility for farmers for almost all levels of risk aversion compared to all other strategies. Results of the probabilistic cost-benefit analysis indicated that more intensive visual monitoring increases net benefits in 68% of the simulated cases. The application of sensor-based monitoring leads to negative economic outcomes in 85% of the simulated cases. This research approach is widely applicable to predict the impacts of new management strategies in precision agriculture. The methodology can be used to provide farmers in other data-scarce production systems with concrete recommendations that account for uncertainties and risks.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11119-022-09909-z.

Entropy Weight Ensemble Framework for Yield Prediction of Winter Wheat Under Different Water Stress Treatments Using Unmanned Aerial Vehicle-Based Multispectral and Thermal Data

Crop breeding programs generally perform early field assessments of candidate selection based on primary traits such as grain yield (GY). The traditional methods of yield assessment are costly, inefficient, and considered a bottleneck in modern precision agriculture. Recent advances in an unmanned aerial vehicle (UAV) and development of sensors have opened a new avenue for data acquisition cost-effectively and rapidly. We evaluated UAV-based multispectral and thermal images for in-season GY prediction using 30 winter wheat genotypes under 3 water treatments. For this, multispectral vegetation indices (VIs) and normalized relative canopy temperature (NRCT) were calculated and selected by the gray relational analysis (GRA) at each growth stage, i.e., jointing, booting, heading, flowering, grain filling, and maturity to reduce the data dimension. The elastic net regression (ENR) was developed by using selected features as input variables for yield prediction, whereas the entropy weight fusion (EWF) method was used to combine the predicted GY values from multiple growth stages. In our results, the fusion of dual-sensor data showed high yield prediction accuracy [coefficient of determination (R ²) = 0.527-0.667] compared to using a single multispectral sensor (R ² = 0.130-0.461). Results showed that the grain filling stage was the optimal stage to predict GY with R ² = 0.667, root mean square error (RMSE) = 0.881 t ha^-1, relative root-mean-square error (RRMSE) = 15.2%, and mean absolute error (MAE) = 0.721 t ha^-1. The EWF model outperformed at all the individual growth stages with R ² varying from 0.677 to 0.729. The best prediction result (R ² = 0.729, RMSE = 0.831 t ha^-1, RRMSE = 14.3%, and MAE = 0.684 t ha^-1) was achieved through combining the predicted values of all growth stages. This study suggests that the fusion of UAV-based multispectral and thermal IR data within an ENR-EWF framework can provide a precise and robust prediction of wheat yield.

Field Phenomics: Will It Enable Crop Improvement?

Field phenomics has been identified as a promising enabling technology to assist plant breeders with the development of improved cultivars for farmers. Yet, despite much investment, there are few examples demonstrating the application of phenomics within a plant breeding program. We review recent progress in field phenomics and highlight the importance of targeting breeders' needs, rather than perceived technology needs, through developing and enhancing partnerships between phenomics researchers and plant breeders.