Deep Learning for Image-Based Cassava Disease Detection

Ramcharan, Amanda; Baranowski, Kelsee; McCloskey, Peter; Ahmed, Babuali; Legg, J.P.; Hughes, David

doi:10.3389/fpls.2017.01852

Cited by 490 publications

(251 citation statements)

References 17 publications

Supporting

Mentioning

248

Contrasting

Unclassified

Order By: Relevance

“…Detecting symptoms of diseases is a large potential provided by deep learning. For example, CNNs already help detect plant diseases in olive trees 41 , cassavas (Manihot esculenta) 42 or various crops 43 .…”

Section: Population Monitoringmentioning

confidence: 99%

Applications for deep learning in ecology

Christin

Hervet

Lecomte

2018

Preprint

View full text Add to dashboard Cite

A lot of hype has recently been generated around deep learning, a novel group of artificial intelligence approaches able to break accuracy records in pattern recognition. Over the course of just a few years, deep learning has revolutionized several research fields such as bioinformatics and medicine with its flexibility and ability to process large and complex datasets. As ecological datasets are becoming larger and more complex, we believe these methods can be useful to ecologists as well. In this paper, we review existing implementations and show that deep learning has been used successfully to identify species, classify animal behaviour and estimate biodiversity in large datasets like camera‐trap images, audio recordings and videos. We demonstrate that deep learning can be beneficial to most ecological disciplines, including applied contexts, such as management and conservation. We also identify common questions about how and when to use deep learning, such as what are the steps required to create a deep learning network, which tools are available to help, and what are the requirements in terms of data and computer power. We provide guidelines, recommendations and useful resources, including a reference flowchart to help ecologists get started with deep learning. We argue that at a time when automatic monitoring of populations and ecosystems generates a vast amount of data that cannot be effectively processed by humans anymore, deep learning could become a powerful reference tool for ecologists.

show abstract

Section: Population Monitoringmentioning

confidence: 99%

Applications for deep learning in ecology

Christin

Hervet

Lecomte

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Nevertheless, currently, researchers are still using symptomatology and even "train" bioinformatic tools using images of symptoms of infected plants, creating appropriate phone applications, immensely helpful to farmers in remote areas. [5]…”

Section: Symptomatologymentioning

confidence: 99%

Viral Detection: Past, Present, and Future

et al. 2019

View full text Add to dashboard Cite

Viruses are essentially composed of a nucleic acid (segmented or not, DNA, or RNA) and a protein coat. Despite their simplicity, these small pathogens are responsible for significant economic and humanitarian losses that have had dramatic consequences in the course of human history. Since their discovery, scientists have developed different strategies to efficiently detect viruses, using all possible viral features. Viruses shape, proteins, and nucleic acid are used in viral detection. In this review, the development of these techniques, especially for plant and mammalian viruses, their strengths and weaknesses as well as the latest cutting‐edge technologies that may be playing important roles in the years to come are described.

show abstract

“…Technological innovations (Halewood et al, 2018) might magnify the impact of such networks. Userfriendly online applications implemented on cell phones, such as those enabling farmers in Africa to diagnose and report the occurrences of cassava (Manihot esculenta Crantz) diseases and pests (Ramcharan et al, 2017), might be integrated with extensive ecogeographical, climatic, distribution, genotypic, and phenotypic datasets (e.g., Ramírez-Villegas et al, 2010;Sánchez González et al, 2018). That software integration could enable professionals, local communities, and interested individuals to monitor and report essentially in "real time" the conservation status and vulnerabilities for key PGR.…”

Section: Plant Genetic Resource Stewardship and The Futurementioning

confidence: 99%

2017 Frank Meyer Medal for Plant Genetic Resources Lecture: Stewards of Our Agricultural Future

Bretting¹

2018

Crop Science

View full text Add to dashboard Cite

Humanity's survival depends on crops—the green line standing between us and calamity. To meet ever expanding human needs, crops must become increasingly more productive, mainly through genetic gains that exploit diverse plant genetic resources (PGR), the raw materials for crop breeding. For millennia, PGR have been conserved by individuals, communities, and organizations. These stewards of our agricultural future have been nearly as diverse as the PGR that they have conserved. Their invaluable roles in underpinning the security of global agriculture have largely been underappreciated. Furthermore, the challenges and complexity of successful PGR stewardship have been inadequately recognized. This paper pays tribute to these stewards’ characteristic attributes and their contributions to PGR conservation and sustainable use. It describes the pervasive impacts of PGR on crop agriculture and explains how numerous factors have affected PGR stewardship capacities. Plant genetic resource stewardship involves many different components, which are typically conducted over extended timeframes. Sustained, adequate support for PGR maintenance, a key component, has been the exception rather than the rule. Past and present PGR stewardship successes and challenges furnish numerous lessons for meeting future demands. Such lessons include recognizing the importance to PGR stewardship of: dedicated and diverse PGR stewards, continual and persistent financial support for PGR genebanks and their staffs, protecting crop wild relatives, and safeguarding genebank collections from extreme weather and introduced pests and pathogens. In the future, PGR stewardship might be conducted more frequently and more adequately by multi‐institutional networks enabled by advances in information technology and artificial intelligence.

show abstract

Deep Learning for Image-Based Cassava Disease Detection

Cited by 490 publications

References 17 publications

Applications for deep learning in ecology

Applications for deep learning in ecology

Viral Detection: Past, Present, and Future

2017 Frank Meyer Medal for Plant Genetic Resources Lecture: Stewards of Our Agricultural Future

Contact Info

Product

Resources

About