Summary: Agriculture is expanding into regions that are affected by salinity. This review considers the energetic costs of salinity tolerance in crop plants and provides a framework for a quantitative assessment of costs. Different sources of energy, and modifications of root system architecture that would maximize water vs ion uptake are addressed. Energy requirements for transport of salt (NaCl) to leaf vacuoles for osmotic adjustment could be small if there are no substantial leaks back across plasma membrane and tonoplast in root and leaf. The coupling ratio of the H⁺‐ATPase also is a critical component. One proposed leak, that of Na⁺ influx across the plasma membrane through certain aquaporin channels, might be coupled to water flow, thus conserving energy. For the tonoplast, control of two types of cation channels is required for energy efficiency. Transporters controlling the Na⁺ and Cl⁻ concentrations in mitochondria and chloroplasts are largely unknown and could be a major energy cost. The complexity of the system will require a sophisticated modelling approach to identify critical transporters, apoplastic barriers and root structures. This modelling approach will inform experimentation and allow a quantitative assessment of the energy costs of NaCl tolerance to guide breeding and engineering of molecular components.

Field phenotyping by remote sensing has received increased interest in recent years with the possibility of achieving high-throughput analysis of crop fields. Along with the various technological developments, the application of machine learning methods for image analysis has enhanced the potential for quantitative assessment of a multitude of crop traits. For wheat breeding purposes, assessing the production of wheat spikes, as the grain-bearing organ, is a useful proxy measure of grain production. Thus, being able to detect and characterize spikes from images of wheat fields is an essential component in a wheat breeding pipeline for the selection of high yielding varieties. We have applied a deep learning approach to accurately detect, count and analyze wheat spikes for yield estimation. We have tested the approach on a set of images of wheat field trial comprising 10 varieties subjected to three fertilizer treatments. The images have been captured over one season, using high definition RGB cameras mounted on a land-based imaging platform, and viewing the wheat plots from an oblique angle. A subset of in-field images has been accurately labeled by manually annotating all the spike regions. This annotated dataset, called SPIKE, is then used to train four region-based Convolutional Neural Networks (R-CNN) which take, as input, images of wheat plots, and accurately detect and count spike regions in each plot. The CNNs also output the spike density and a classification probability for each plot. Using the same R-CNN architecture, four different models were generated based on four different datasets of training and testing images captured at various growth stages. Despite the challenging field imaging conditions, e.g., variable illumination conditions, high spike occlusion, and complex background, the four R-CNN models achieve an average detection accuracy ranging from 88 to \(94\%\) across different sets of test images. The most robust R-CNN model, which achieved the highest accuracy, is then selected to study the variation in spike production over 10 wheat varieties and three treatments. The SPIKE dataset and the trained CNN are the main contributions of this paper. With the availability of good training datasets such us the SPIKE dataset proposed in this article, deep learning techniques can achieve high accuracy in detecting and counting spikes from complex wheat field images. The proposed robust R-CNN model, which has been trained on spike images captured during different growth stages, is optimized for application to a wider variety of field scenarios. It accurately quantifies the differences in yield produced by the 10 varieties we have studied, and their respective responses to fertilizer treatment. We have also observed that the other R-CNN models exhibit more specialized performances. The data set and the R-CNN model, which we make publicly available, have the potential to greatly benefit plant breeders by facilitating the high throughput selection of high yielding varieties.

Unmanned aerial vehicles offer the opportunity for precision agriculture to efficiently monitor agricultural land. A vegetation index (VI) derived from an aerially observed multispectral image (MSI) can quantify crop health, moisture and nutrient content. However, due to the high cost of multispectral sensors, alternate, low-cost solutions have lately received great interest. We present a novel method for model-based estimation of a VI using RGB color images. The non-linear spatio-spectral relationship between the RGB image of vegetation and the index computed by its corresponding MSI is learned through deep neural networks. The learned models can be used to estimate VI of a crop segment. Analysis of images obtained in wheat breeding trials show that the aerially observed VI was highly correlated with ground-measured VI. In addition, VI estimates based on RGB images were highly correlated with VI deduced from MSIs. Spatial, spectral and temporal information of images contributed to estimation of VI. Both intra-variety and inter-variety differences were preserved by estimated VI. However, VI estimates were reliable until just before significant appearance of senescence. The proposed approach validates that it is reasonable to accurately estimate VI using deep neural networks. The results prove that RGB images contain sufficient information for VI estimation. It demonstrates that low-cost VI measurement is possible with standard RGB cameras.

This paper outlines a numerical scheme for accurate, detailed, and high-throughput image analysis of plant roots. In contrast to existing root image analysis tools that focus on root system-average traits, a novel, fully automated and robust approach for the detailed characterization of root traits, based on a graph optimization process is presented. The scheme, firstly, distinguishes primary roots from lateral roots and, secondly, quantifies a broad spectrum of root traits for each identified primary and lateral root. Thirdly, it associates lateral roots and their properties with the specific primary root from which the laterals emerge. The performance of this approach was evaluated through comparisons with other automated and semi-automated software solutions as well as against results based on manual measurements. The comparisons and subsequent application of the algorithm to an array of experimental data demonstrate that this method outperforms existing methods in terms of accuracy, robustness, and the ability to process root images under high-throughput conditions.