Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature.

BACKGROUND: Rice is a major staple food crop for more than half the world's population. As the global population is expected to reach 9.7 billion by 2050, increasing the production of high-quality rice is needed to meet the anticipated increased demand. However, global environmental changes, especially increasing temperatures, can affect grain yield and quality. Heat stress is one of the major causes of an increased proportion of chalkiness in rice, which compromises quality and reduces the market value. Researchers have identified 140 quantitative trait loci linked to chalkiness mapped across 12 chromosomes of the rice genome. However, the available genetic information acquired by employing advances in genetics has not been adequately exploited due to a lack of a reliable, rapid and high-throughput phenotyping tool to capture chalkiness. To derive extensive benefit from the genetic progress achieved, tools that facilitate high-throughput phenotyping of rice chalkiness are needed. RESULTS: We use a fully automated approach based on convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) to detect chalkiness in rice grain images. Specifically, we train a CNN model to distinguish between chalky and non-chalky grains and subsequently use Grad-CAM to identify the area of a grain that is indicative of the chalky class. The area identified by the Grad-CAM approach takes the form of a smooth heatmap that can be used to quantify the degree of chalkiness. Experimental results on both polished and unpolished rice grains using standard instance classification and segmentation metrics have shown that Grad-CAM can accurately identify chalky grains and detect the chalkiness area. CONCLUSIONS: We have successfully demonstrated the application of a Grad-CAM based tool to accurately capture high night temperature induced chalkiness in rice. The models trained will be made publicly available. They are easy-to-use, scalable and can be readily incorporated into ongoing rice breeding programs, without rice researchers requiring computer science or machine learning expertise.

High night temperature effects on wheat and rice: Current status and way forward.

Rapid increases in minimum night temperature than in maximum day temperature is predicted to continue, posing significant challenges to crop productivity. Rice and wheat are two major staples that are sensitive to high night-temperature (HNT) stress. This review aims to (i) systematically compare the grain yield responses of rice and wheat exposed to HNT stress across scales, and (ii) understand the physiological and biochemical responses that affect grain yield and quality. To achieve this, we combined a synthesis of current literature on HNT effects on rice and wheat with information from a series of independent experiments we conducted across scales, using a common set of genetic materials to avoid confounding our findings with differences in genetic background. In addition, we explored HNT-induced alterations in physiological mechanisms including carbon balance, source-sink metabolite changes and reactive oxygen species. Impacts of HNT on grain developmental dynamics focused on grain-filling duration, post-flowering senescence, changes in grain starch and protein composition, starch metabolism enzymes and chalk formation in rice grains are summarized. Finally, we highlight the need for high-throughput field-based phenotyping facilities for improved assessment of large-diversity panels and mapping populations to aid breeding for increased resilience to HNT in crops.

Bottlenecks and opportunities in field-based high-throughput phenotyping for heat and drought stress.

Flowering and grain-filling stages are highly sensitive to heat and drought stress exposure, leading to significant loss in crop yields. Therefore, phenotyping to enhance resilience to these abiotic stresses is critical for sustaining genetic gains in crop improvement programs. However, traditional methods for screening traits related to these stresses are slow, laborious, and often expensive. Remote sensing provides opportunities to introduce low-cost, less biased, high-throughput phenotyping methods to capture large genetic diversity to facilitate enhancement of stress resilience in crops. This review focuses on four key physiological traits and processes that are critical in understanding crop responses to drought and heat stress during reproductive and grain-filling periods. Specifically, these traits include: (i) time of day of flowering, to escape these stresses during flowering; (ii) optimizing photosynthetic efficiency; (iii) storage and translocation of water-soluble carbohydrates; and (iv) yield and yield components to provide in-season yield estimates. Moreover, we provide an overview of current advances in remote sensing in capturing these traits, and discuss the limitations with existing technology as well as future direction of research to develop high-throughput phenotyping approaches. In the future, phenotyping these complex traits will require sensor advancement, high-quality imagery combined with machine learning methods, and efforts in transdisciplinary science to foster integration across disciplines.

Improved cyber-physical system captured post-flowering high night temperature impact on yield and quality of field grown wheat.

Winter wheat (Triticum aestivum L.) is essential to maintain food security for a large proportion of the world's population. With increased risk from abiotic stresses due to climate variability, it is imperative to understand and minimize the negative impact of these stressors, including high night temperature (HNT). Both globally and at regional scales, a differential rate of increase in day and night temperature is observed, wherein night temperatures are increasing at a higher pace and the trend is projected to continue into the future. Previous studies using controlled environment facilities and small field-based removable chambers have shown that post-anthesis HNT stress can induce a significant reduction in wheat grain yield. A prototype was previously developed by utilizing field-based tents allowing for simultaneous phenotyping of popular winter wheat varieties from US Midwest and advanced breeding lines. Hence, the objectives of the study were to (i) design and build a new field-based infrastructure and test and validate the uniformity of HNT stress application on a scaled-up version of the prototype (ii) improve and develop a more sophisticated cyber-physical system to sense and impose post-anthesis HNT stress uniformly through physiological maturity within the scaled-up tents; and (iii) determine the impact of HNT stress during grain filling on the agronomic and grain quality parameters including starch and protein concentration. The system imposed a consistent post-anthesis HNT stress of + 3.8 °C until maturity and maintained uniform distribution of stress which was confirmed by (i) 0.23 °C temperature differential between an array of sensors within the tents and (ii) statistically similar performance of a common check replicated multiple times in each tent. On average, a reduction in grain-filling duration by 3.33 days, kernel weight by 1.25% per °C, grain number by 2.36% per °C and yield by 3.58% per °C increase in night temperature was documented. HNT stress induced a significant reduction in starch concentration indicating disturbed carbon balance. The pilot field-based facility integrated with a robust cyber-physical system provides a timely breakthrough for evaluating HNT stress impact on large diversity panels to enhance HNT stress tolerance across field crops. The flexibility of the cyber-physical system and movement capabilities of the field-based infrastructure allows this methodology to be adaptable to different crops.

Integrating field-based heat tents and cyber-physical system technology to phenotype high night-time temperature impact on winter wheat.

BACKGROUND: Many agronomic traits have been bred into modern wheat varieties, but wheat (Triticum aestivum L.) continues to be vulnerable to heat stress, with high night-time temperature (HNT) stress shown to have large negative impact on yield and quality. Global mean temperature during the day is consistently warming with the minimum night temperature increasing at a much quicker pace. Currently, there is no system or method that allows crop scientists to impose HNT stress at key developmental stages on wheat or crops in general under field conditions, involving diverse genotypes and maintaining a dynamic temperature differential within the tents compared to the outside. RESULTS: Through implementation of a side roll up and a top ventilation system, heaters, and a custom cyber-physical system using a Raspberry Pi, the heat tents were able to consistently maintain an elevated temperature through the night to differentiate heat stress impact on different genotypes. When the tents were placed in their day-time setting they were able to maintain ambient day-time temperature without having to be removed and replaced on the plots. Data averaged from multiple sensors over three consecutive weeks resulted in a consistent but small temperature difference of 0.25 °C within the tents, indicating even distribution of heat. While targeting a temperature differential of 4 °C, the tents were able to maintain an average differential of 3.2 °C consistently throughout the night-time heat stress period, compared to the outside ambient conditions. The impact of HNT stress was confirmed through a statistically significant yield reduction in eleven of the twelve genotypes tested. The average yield under HNT stress was reduced by 20.3% compared to the controls, with the highest reduction being 41.4% and a lowest reduction of 6.9%. Recommendations for fine-tuning the system are provided. CONCLUSION: This methodology is easily accessible and can be widely utilized due to its flexibility and ease of construction. This system can be modified and improved based on some of the recommendations and has the potential to be used across other crops or plants as it is not reliant on access to any hardwired utilities. The method tested will help the crop community to quantify the impact of HNT stress, identify novel donors that induce tolerance to HNT and help the breeders develop crop varieties that are resilient to changing climate.