scholarly journals Stomata Detector: High-throughput automation of stomata counting in a population of African rice (Oryza glaberrima) using transfer learning

2021 ◽  
Author(s):  
Sophie B. Cowling ◽  
Hamidreza Soltani ◽  
Sean Mayes ◽  
Erik H. Murchie
Keyword(s):  
Open Source ◽  
Transfer Learning ◽  
Stomatal Density ◽  
Crop Improvement ◽  
Batch Process ◽  
Crop Productivity ◽  
Oryza Glaberrima ◽  
Detection Model ◽  
Science Community ◽  
Dynamic Structures

AbstractStomata are dynamic structures that control the gaseous exchange of CO2 from the external to internal environment and water loss through transpiration. The density and morphology of stomata have important consequences in crop productivity and water use efficiency, both are integral considerations when breeding climate change resilient crops. The phenotyping of stomata is a slow manual process and provides a substantial bottleneck when characterising phenotypic and genetic variation for crop improvement. There are currently no open-source methods to automate stomatal counting. We used 380 human annotated micrographs of O. glaberrima and O. sativa at x20 and x40 objectives for testing and training. Training was completed using the transfer learning for deep neural networks method and R-CNN object detection model. At a x40 objective our method was able to accurately detect stomata (n = 540, r = 0.94, p<0.0001), with an overall similarity of 99% between human and automated counting methods. Our method can batch process large files of images. As proof of concept, characterised the stomatal density in a population of 155 O. glaberrima accessions, using 13,100 micrographs. Here, we present developed Stomata Detector; an open source, sophisticated piece of software for the plant science community that can accurately identify stomata in Oryza spp., and potentially other monocot species.

scholarly journals Tackling G × E × M interactions to close on-farm yield-gaps: creating novel pathways for crop improvement by predicting contributions of genetics and management to crop productivity

2021 ◽  
Author(s):  
Mark Cooper ◽  
Kai P. Voss-Fels ◽  
Carlos D. Messina ◽  
Tom Tang ◽  
Graeme L. Hammer
Keyword(s):  
Climate Change ◽  
Crop Improvement ◽  
Target Population ◽  
Crop Productivity ◽  
Climate Change Scenarios ◽  
Global Food Security ◽  
Genotype By Environment ◽  
Improvement Strategies ◽  
Yield Gaps ◽  
On Farm

Abstract Key message Climate change and Genotype-by-Environment-by-Management interactions together challenge our strategies for crop improvement. Research to advance prediction methods for breeding and agronomy is opening new opportunities to tackle these challenges and overcome on-farm crop productivity yield-gaps through design of responsive crop improvement strategies. Abstract Genotype-by-Environment-by-Management (G × E × M) interactions underpin many aspects of crop productivity. An important question for crop improvement is “How can breeders and agronomists effectively explore the diverse opportunities within the high dimensionality of the complex G × E × M factorial to achieve sustainable improvements in crop productivity?” Whenever G × E × M interactions make important contributions to attainment of crop productivity, we should consider how to design crop improvement strategies that can explore the potential space of G × E × M possibilities, reveal the interesting Genotype–Management (G–M) technology opportunities for the Target Population of Environments (TPE), and enable the practical exploitation of the associated improved levels of crop productivity under on-farm conditions. Climate change adds additional layers of complexity and uncertainty to this challenge, by introducing directional changes in the environmental dimension of the G × E × M factorial. These directional changes have the potential to create further conditional changes in the contributions of the genetic and management dimensions to future crop productivity. Therefore, in the presence of G × E × M interactions and climate change, the challenge for both breeders and agronomists is to co-design new G–M technologies for a non-stationary TPE. Understanding these conditional changes in crop productivity through the relevant sciences for each dimension, Genotype, Environment, and Management, creates opportunities to predict novel G–M technology combinations suitable to achieve sustainable crop productivity and global food security targets for the likely climate change scenarios. Here we consider critical foundations required for any prediction framework that aims to move us from the current unprepared state of describing G × E × M outcomes to a future responsive state equipped to predict the crop productivity consequences of G–M technology combinations for the range of environmental conditions expected for a complex, non-stationary TPE under the influences of climate change.

scholarly journals Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

2020 ◽  
Vol 13 (1) ◽  
pp. 23
Author(s):  
Wei Zhao ◽  
William Yamada ◽  
Tianxin Li ◽  
Matthew Digman ◽  
Troy Runge
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Precision Agriculture ◽  
Crop Production ◽  
Domain Adaptation ◽  
Training Data ◽  
Detection Accuracy ◽  
Detection Model ◽  
Agriculture Products

In recent years, precision agriculture has been researched to increase crop production with less inputs, as a promising means to meet the growing demand of agriculture products. Computer vision-based crop detection with unmanned aerial vehicle (UAV)-acquired images is a critical tool for precision agriculture. However, object detection using deep learning algorithms rely on a significant amount of manually prelabeled training datasets as ground truths. Field object detection, such as bales, is especially difficult because of (1) long-period image acquisitions under different illumination conditions and seasons; (2) limited existing prelabeled data; and (3) few pretrained models and research as references. This work increases the bale detection accuracy based on limited data collection and labeling, by building an innovative algorithms pipeline. First, an object detection model is trained using 243 images captured with good illimitation conditions in fall from the crop lands. In addition, domain adaptation (DA), a kind of transfer learning, is applied for synthesizing the training data under diverse environmental conditions with automatic labels. Finally, the object detection model is optimized with the synthesized datasets. The case study shows the proposed method improves the bale detecting performance, including the recall, mean average precision (mAP), and F measure (F1 score), from averages of 0.59, 0.7, and 0.7 (the object detection) to averages of 0.93, 0.94, and 0.89 (the object detection + DA), respectively. This approach could be easily scaled to many other crop field objects and will significantly contribute to precision agriculture.

scholarly journals Computer-Aided Colon Polyp Detection on High Resolution Colonoscopy Using Transfer Learning Techniques

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5315
Author(s):  
Chia-Pei Tang ◽  
Kai-Hong Chen ◽  
Tu-Liang Lin
Keyword(s):  
Real Time ◽  
Transfer Learning ◽  
Early Recognition ◽  
Detection System ◽  
Colon Polyp ◽  
Colon Polyps ◽  
Polyp Detection ◽  
Detection Model ◽  
Real Time Detection ◽  
Polyp Type

Colonoscopies reduce the incidence of colorectal cancer through early recognition and resecting of the colon polyps. However, the colon polyp miss detection rate is as high as 26% in conventional colonoscopy. The search for methods to decrease the polyp miss rate is nowadays a paramount task. A number of algorithms or systems have been developed to enhance polyp detection, but few are suitable for real-time detection or classification due to their limited computational ability. Recent studies indicate that the automated colon polyp detection system is developing at an astonishing speed. Real-time detection with classification is still a yet to be explored field. Newer image pattern recognition algorithms with convolutional neuro-network (CNN) transfer learning has shed light on this topic. We proposed a study using real-time colonoscopies with the CNN transfer learning approach. Several multi-class classifiers were trained and mAP ranged from 38% to 49%. Based on an Inception v2 model, a detector adopting a Faster R-CNN was trained. The mAP of the detector was 77%, which was an improvement of 35% compared to the same type of multi-class classifier. Therefore, our results indicated that the polyp detection model could attain a high accuracy, but the polyp type classification still leaves room for improvement.

scholarly journals High-throughput phenotyping reveals a link between transpiration efficiency and transpiration restriction under high evaporative demand and new loci controlling water use-related traits in African rice, Oryza glaberrima Steud.

2021 ◽  
Author(s):  
Pablo Affortit ◽  
Branly Effa Effa ◽  
Mame Sokhatil Ndoye ◽  
Daniel Moukouanga ◽  
Nathalie Luchaire ◽  
...  
Keyword(s):  
Water Use Efficiency ◽  
Water Use ◽  
Association Studies ◽  
Crop Improvement ◽  
Oryza Glaberrima ◽  
Genome Wide Association Studies ◽  
Transpiration Efficiency ◽  
Evaporative Demand ◽  
African Rice ◽  
Use Efficiency

Because water availability is the most important environmental factor limiting crop production, improving water use efficiency, the amount of carbon fixed per water used, is a major target for crop improvement. In rice, the genetic bases of transpiration efficiency, the derivation of water use efficiency at the whole-plant scale, and its putative component trait transpiration restriction under high evaporative demand, remain unknown. These traits were measured in a panel of 147 African rice Oryza glaberrima genotypes, known as potential sources of tolerance genes to biotic and abiotic stresses. Our results reveal that higher transpiration efficiency is associated with transpiration restriction in African rice. Detailed measurements in a subset of highly differentiated genotypes confirmed these associations and suggested that the root to shoot ratio played an important role in transpiration restriction. Genome wide association studies identified marker-trait associations for transpiration response to evaporative demand, transpiration efficiency and its residuals, that links to genes involved in water transport and cell wall patterning. Our data suggest that root shoot partitioning is an important component of transpiration restriction that has a positive effect on transpiration efficiency in African rice. Both traits are heritable and define targets for breeding rice with improved water use strategies.

scholarly journals Concrete Cracks Detection Using Convolutional NeuralNetwork Based on Transfer Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Chao Su ◽  
Wenjun Wang
Keyword(s):  
Transfer Learning ◽  
Crack Detection ◽  
Critical Role ◽  
Concrete Surface ◽  
Surface Cracks ◽  
Generalization Capability ◽  
Detection Model ◽  
Neural Architecture ◽  
Efficient Detection

Crack plays a critical role in the field of evaluating the quality of concrete structures, which affects the safety, applicability, and durability of the structure. Due to its excellent performance in image processing, the convolutional neural network is becoming the mainstream choice to replace manual crack detection. In this paper, we improve the EfficientNetB0 to realize the detection of concrete surface cracks using the transfer learning method. The model is designed by neural architecture search technology. The weights are pretrained on the ImageNet. Supervised learning uses Adam optimizer to update network parameters. In the testing process, crack images from different locations were used to further test the generalization capability of the model. By comparing the detection results with the MobileNetV2, DenseNet201, and InceptionV3 models, the results show that our model greatly reduces the number of parameters while achieving high accuracy (0.9911) and has good generalization capability. Our model is an efficient detection model, which provides a new option for crack detection in areas with limited computing resources.

scholarly journals Legume biology: the basis for crop improvement

2013 ◽  
Vol 40 (12) ◽  
pp. v ◽  
Author(s):  
Rajeev K. Varshney ◽  
Himabindu Kudapa
Keyword(s):  
Target Genes ◽  
Crop Improvement ◽  
Crop Productivity ◽  
Food Sources ◽  
Yield Potential ◽  
Systematic Research ◽  
Breeding Programs ◽  
Biotic Stresses ◽  
Legume Crop ◽  
Precise Understanding

Legumes represent the most valued food sources in agriculture after cereals. Despite the advances made in breeding food legumes, there is a need to develop and further improve legume productivity to meet increasing food demand worldwide. Several biotic and abiotic stresses affect legume crop productivity throughout the world. The study of legume genetics, genomics and biology are all important in order to understand the limitations of yield of legume crops and to support our legume breeding programs. With the advent of huge genomic resources and modern technologies, legume research can be directed towards precise understanding of the target genes responsible for controlling important traits for yield potential, and for resistance to abiotic and biotic stresses. Programmed and systematic research will lead to developing high yielding, stress tolerant and early maturing varieties. This issue of Functional Plant Biology is dedicated to ‘Legume Biology’ research covering part of the work presented at VI International Conference on Legume Genetics and Genomics held at Hyderabad, India, in 2012. The 13 contributions cover recent advances in legume research in the context of plant architecture and trait mapping, functional genomics, biotic stress and abiotic stress.

scholarly journals Genetic determination of stomatal patterning in winter wheat (Triticum aestivum L.)

2018 ◽  
Author(s):  
Steven Andrew Yates ◽  
Andreas Bruun ◽  
Marius Hodel ◽  
Christoph Grieder ◽  
Andreas Hund ◽  
...  
Keyword(s):  
Triticum Aestivum ◽  
Winter Wheat ◽  
Stomatal Density ◽  
Crop Improvement ◽  
Genotypic Variation ◽  
Triticum Aestivum L ◽  
Auxin Signaling ◽  
Genetic Determination ◽  
Wheat Germplasm ◽  
Stomatal Patterning

Leaf stomata are microscopic pores mediating plant-environment interactions. Their role in carbon uptake and transpiration make them prime candidates for improving water use efficiency (WUE). Stomatal density (SD), the number of stomata per unit area, has been shown to be negatively correlated with WUE. However, little is known about the genetic basis of SD in wheat (Triticum aestivum L.), and to what extant genetic variation exists in contemporary wheat germplasm. Here, we evaluated stomatal patterning over two growing seasons in a set of 333 wheat lines, representing the European winter wheat germplasm. Stomatal patterning was mainly determined by two underlying traits, the distance between files of stomata and the distance between stomata within a file. By haplotype association mapping, quantitative trait loci for SD were consistently detected in both seasons on wheat chromosomes (CHR) 2A, 3A and 7B. The single nucleotide polymorphism markers most significantly associated with SD coincided with the genes INDUCER OF CBF EXPRESSION 1 (ICE1) and STOMATAL CYTOKINESIS-DEFECTIVE 1 (SCD1) on CHR 3A, and genes involved in ethylene and auxin signaling on CHR 2A and 7B, respectively. Our study unlocks the phenotypic and genotypic variation for stomatal patterning traits in contemporary wheat germplasm. It provides gene targets for functional validation and practical tools to manipulate SD using marker-assisted selection for crop improvement.

scholarly journals Biodiversity Assessment of Foxtail Millet (Setaria italica L.) Genotypes Based on RAPD Marker

2017 ◽  
Vol 4 (1) ◽  
pp. 21-25 ◽  
Author(s):  
Sintho Wahyuning ARDIE ◽  
Nurul Khumaida ◽  
Nurul Fauziah ◽  
Yudiansyah Yudiansyah
Keyword(s):  
Rapd Markers ◽  
High Salinity ◽  
Rapd Marker ◽  
Crop Improvement ◽  
Foxtail Millet ◽  
Crop Productivity ◽  
Setaria Italica ◽  
Base Pairs ◽  
Improvement Program ◽  
Product Size

Foxtail millet (Setaria italica L.) is an important crop in areas where harsh environmental conditions limit crop productivity, including in high salinity and drought prone areas. In Indonesia millet is cultivated in certain areas; however, superior varieties are less developed in the country. The objective of this study was to analyze the genetic diversity among foxtail genotypes using RAPD markers. Genomic DNA of ten foxtail millet genotypes was amplified using 26 random primers through RAPD analysis. Of these primers, 22 produced reproducible amplicons and were polymorphic among the 10 foxtail millet genotypes. The number of polymorphic markers for each primer varied from 1 (primer E15) to 14 (primer M17). The amplified product size ranged from 120 to 2500 base pairs (bp). A dendrogram constructed based on the UPGMA clustering method put all genotypes in 5 distinct groups at 0.64 coefficient level. Diverse genotypes identified in this study can be used as potential parents in an efficient crop improvement program.

Sign in / Sign up

Export Citation Format

Share Document