Identifying Optimal Wavelengths as Disease Signatures Using Hyperspectral Sensor and Machine Learning

High-Throughput Analysis of Leaf Chlorophyll Content in Aquaponically Grown Lettuce Using Hyperspectral Reflectance and RGB Images

Chlorophyll content reflects plants' photosynthetic capacity, growth stage, and nitrogen status and is, therefore, of significant importance in precision agriculture. This study aims to develop a spectral and color vegetation indices-based model to estimate the chlorophyll content in aquaponically grown lettuce. A completely open-source automated machine learning (AutoML) framework (EvalML) was employed to develop the prediction models. The performance of AutoML along with four other standard machine learning models (back-propagation neural network (BPNN), partial least squares regression (PLSR), random forest (RF), and support vector machine (SVM) was compared. The most sensitive spectral (SVIs) and color vegetation indices (CVIs) for chlorophyll content were extracted and evaluated as reliable estimators of chlorophyll content. Using an ASD FieldSpec 4 Hi-Res spectroradiometer and a portable red, green, and blue (RGB) camera, 3600 hyperspectral reflectance measurements and 800 RGB images were acquired from lettuce grown across a gradient of nutrient levels. Ground measurements of leaf chlorophyll were acquired using an SPAD-502 m calibrated via laboratory chemical analyses. The results revealed a strong relationship between chlorophyll content and SPAD-502 readings, with an R2 of 0.95 and a correlation coefficient (r) of 0.975. The developed AutoML models outperformed all traditional models, yielding the highest values of the coefficient of determination in prediction (Rp2) for all vegetation indices (VIs). The combination of SVIs and CVIs achieved the best prediction accuracy with the highest Rp2 values ranging from 0.89 to 0.98, respectively. This study demonstrated the feasibility of spectral and color vegetation indices as estimators of chlorophyll content. Furthermore, the developed AutoML models can be integrated into embedded devices to control nutrient cycles in aquaponics systems.

Reference-Free Plant Disease Detection Using Machine Learning and Long-Read Metagenomic Sequencing

Surveillance for early disease detection is crucial to reduce the threat of plant diseases to food security. Metagenomic sequencing and taxonomic classification have recently been used to detect and identify plant pathogens. However, for an emerging pathogen, its genome may not be similar enough to any public genome to permit reference-based tools to identify infected samples. Also, in the case of point-of care diagnosis in the field, database access may be limited. Therefore, here we explore reference-free detection of plant pathogens using metagenomic sequencing and machine learning (ML). We used long-read metagenomes from healthy and infected plants as our model system and constructed k-mer frequency tables to test eight different ML models. The accuracy in classifying individual reads as coming from a healthy or infected metagenome were compared. Of all models, random forest (RF) had the best combination of short run-time and high accuracy (over 0.90) using tomato metagenomes. We further evaluated the RF model with a different tomato sample infected with the same pathogen or a different pathogen and a grapevine sample infected with a grapevine pathogen and achieved similar performances. ML models can thus learn features to successfully perform reference-free detection of plant diseases whereby a model trained with one pathogen-host system can also be used to detect different pathogens on different hosts. Potential and challenges of applying ML to metagenomics in plant disease detection are discussed. IMPORTANCE Climate change may lead to the emergence of novel plant diseases caused by yet unknown pathogens. Surveillance for emerging plant diseases is crucial to reduce their threat to food security. However, conventional genomic based methods require knowledge of existing plant pathogens and cannot be applied to detecting newly emerged pathogens. In this work, we explored reference-free, meta-genomic sequencing-based disease detection using machine learning. By sequencing the genomes of all microbial species extracted from an infected plant sample, we were able to train machine learning models to accurately classify individual sequencing reads as coming from a healthy or an infected plant sample. This method has the potential to be integrated into a generic pipeline for a meta-genomic based plant disease surveillance approach but also has limitations that still need to be overcome.

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography-Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R² of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.

Intelligent Identification and Features Attribution of Saline–Alkali-Tolerant Rice Varieties Based on Raman Spectroscopy

Planting rice in saline–alkali land can effectively improve saline–alkali soil and increase grain yield, but traditional identification methods for saline–alkali-tolerant rice varieties require tedious and time-consuming field investigations based on growth indicators by rice breeders. In this study, the Python machine deep learning method was used to analyze the Raman molecular spectroscopy of rice and assist in feature attribution, in order to study a fast and efficient identification method of saline–alkali-tolerant rice varieties. A total of 156 Raman spectra of four rice varieties (two saline–alkali-tolerant rice varieties and two saline–alkali-sensitive rice varieties) were analyzed, and the wave crests were extracted by an improved signal filtering difference method and the feature information of the wave crest was automatically extracted by scipy.signal.find_peaks. Select K Best (SKB), Recursive Feature Elimination (RFE) and Select F Model (SFM) were used to select useful molecular features. Based on these feature selection methods, a Logistic Regression Model (LRM) and Random Forests Model (RFM) were established for discriminant analysis. The experimental results showed that the RFM identification model based on the RFE method reached a higher recognition rate of 89.36%. According to the identification results of RFM and the identification of feature attribution materials, amylum was the most significant substance in the identification of saline–alkali-tolerant rice varieties. Therefore, an intelligent method for the identification of saline–alkali-tolerant rice varieties based on Raman molecular spectroscopy is proposed.

Hyperspectral Imaging Combined with Machine Learning for the Detection of Fusiform Rust Disease Incidence in Loblolly Pine Seedlings

Loblolly pine is an economically important timber species in the United States, with almost 1 billion seedlings produced annually. The most significant disease affecting this species is fusiform rust, caused by Cronartium quercuum f. sp. fusiforme. Testing for disease resistance in the greenhouse involves artificial inoculation of seedlings followed by visual inspection for disease incidence. An automated, high-throughput phenotyping method could improve both the efficiency and accuracy of the disease screening process. This study investigates the use of hyperspectral imaging for the detection of diseased seedlings. A nursery trial comprising families with known in-field rust resistance data was conducted, and the seedlings were artificially inoculated with fungal spores. Hyperspectral images in the visible and near-infrared region (400–1000 nm) were collected six months after inoculation. The disease incidence was scored with traditional methods based on the presence or absence of visible stem galls. The seedlings were segmented from the background by thresholding normalized difference vegetation index (NDVI) images, and the delineation of individual seedlings was achieved through object detection using the Faster RCNN model. Plant parts were subsequently segmented using the DeepLabv3+ model. The trained DeepLabv3+ model for semantic segmentation achieved a pixel accuracy of 0.76 and a mean Intersection over Union (mIoU) of 0.62. Crown pixels were segmented using geometric features. Support vector machine discrimination models were built for classifying the plants into diseased and non-diseased classes based on spectral data, and balanced accuracy values were calculated for the comparison of model performance. Averaged spectra from the whole plant (balanced accuracy = 61%), the crown (61%), the top half of the stem (77%), and the bottom half of the stem (62%) were used. A classification model built using the spectral data from the top half of the stem was found to be the most accurate, and resulted in an area under the receiver operating characteristic curve (AUC) of 0.83.