Ultra-high-resolution UAV-imaging and supervised deep learning for accurate detection of Alternaria solani in potato fields

Jana Wieme; Sam Leroux; Simon R. Cool; Jonathan Van Beek; Jan G. Pieters; Wouter H. Maes

doi:10.3389/fpls.2024.1206998

journal article Open Access Mar 05, 2024

Ultra-high-resolution UAV-imaging and supervised deep learning for accurate detection of Alternaria solani in potato fields

Jana Wieme Sam Leroux Simon R. Cool Jonathan Van Beek Jan G. Pieters

Wouter H. Maes

Frontiers in Plant Science Vol. 15 · Frontiers Media SA

View at Publisher Save 10.3389/fpls.2024.1206998

Abstract

Alternaria solani is the second most devastating foliar pathogen of potato crops worldwide, causing premature defoliation of the plants. This disease is currently prevented through the regular application of detrimental crop protection products and is guided by early warnings based on weather predictions and visual observations by farmers. To reduce the use of crop protection products, without additional production losses, it would be beneficial to be able to automatically detect Alternaria solani in potato fields. In recent years, the potential of deep learning in precision agriculture is receiving increasing research attention. Convolutional Neural Networks (CNNs) are currently the state of the art, but also come with challenges, especially regarding in-field robustness. This stems from the fact that they are often trained on datasets that are limited in size or have been recorded in controlled environments, not necessarily representative of real-world settings. We collected a dataset consisting of ultra-high-resolution modified RGB UAV-imagery of both symptomatic and non-symptomatic potato crops in the field during various years and disease stages to cover the great variability in agricultural data. We developed a convolutional neural network to perform in-field detection of Alternaria, defined as a binary classification problem. Our model achieves a similar accuracy as several state-of-the-art models for disease detection, but has a much lower inference time, which enhances its practical applicability. By using training data of three consecutive growing seasons (2019, 2020 and 2021) and test data of an independent fourth year (2022), an F1 score of 0.93 is achieved. Furthermore, we evaluate how different properties of the dataset such as its size and class imbalance impact the obtained accuracy.

Topics

No keywords indexed for this article. Browse by subject →

References

47

[1]

Abade "Plant diseases recognition on images using convolutional neural networks: A systematic review" Comput. Electron. Agric. (2021) 10.1016/j.compag.2021.106125

[2]

Afonso "Blackleg detection in potato plants using convolutional neural networks" IFAC papers Online (2019) 10.1016/j.ifacol.2019.12.481

[3]

Afzaal "Detection of a potato disease (early blight) using artificial intelligence" Remote Sens. (2021) 10.3390/rs13030411

[4]

Automatic blight disease detection in potato (Solanum tuberosum L.) and tomato (Solanum lycopersicum, L. 1753) plants using deep learning

Alberta Odamea Anim-Ayeko, Calogero Schillaci, Aldo Lipani

Smart Agricultural Technology 2023 10.1016/j.atech.2023.100178

[5]

Barbedo "A review on the main challenges in automatic plant disease identification based on visible range images" Biosyst. Eng. (2016) 10.1016/j.biosystemseng.2016.01.017

[6]

Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification

Jayme Garcia Arnal Barbedo

Computers and Electronics in Agriculture 2018 10.1016/j.compag.2018.08.013

[7]

Bhor "A no reference image blur detection using cumulative probability blur detection (cpbd) metric" Int. J. Sci. Modern Eng. (2013)

[8]

Chakraborty "Automated recognition of optical image based potato leaf blight diseases using deep learning" Physiol. Mol. Plant Pathol. (2022) 10.1016/j.pmpp.2021.101781

[9]

Chen "Weakly-supervised learning method for the recognition of potato leaf diseases" Artif. Intell. Rev. (2018) 10.1007/s10462-022-10374-3

[10]

Fei-Fei "ImageNet: Constructing a large-scale image database [Abstract]" (2009)

[11]

Field resistance of potato cultivars to foliar early blight and its relationship with foliage maturity and tuber skin types

Henrique S. S. Duarte, Laércio Zambolim, Fabrício Á. Rodrigues et al.

Tropical Plant Pathology 2014 10.1590/s1982-56762014000400004

[12]

(2022)

[13]

(2023)

[14]

He "Deep residual learning for image recognition" (2016)

[15]

Hou "Recognition of early blight and late blight diseases on potato leaves based on graph cut segmentation" J. Agric. Food Res. (2021) 10.1016/j.jafr.2021.100154

[16]

Huang "Densely connected convolutional networks" (2016)

[17]

Hughes "An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing" arXiv preprint (2015)

[18]

Iqbal "Detection of potato disease using image segmentation and machine learning" (2020)

[19]

Johnson "Enhanced field-based detection of potato blight in complex backgrounds using deep learning" Plant Phenomics (2021) 10.34133/2021/9835724

[20]

Deep learning in agriculture: A survey

Andreas Kamilaris, Francesc X. Prenafeta-Boldú

Computers and Electronics in Agriculture 2018 10.1016/j.compag.2018.02.016

[21]

Khalifa (2021)

[22]

Kingma "Adam: A method for stochastic optimization" (2015)

[23]

Plant diseases and pests detection based on deep learning: a review

Jun Liu

Plant Methods 2021 10.1186/s13007-021-00722-9

[24]

Spatially Located Platform and Aerial Photography for Documentation of Grazing Impacts on Wheat

Mounir Louhaichi, Michael M. Borman, Douglas E. Johnson

Geocarto International 2001 10.1080/10106040108542184

[25]

Lu "Review on convolutional neural network (cnn) applied to plant leaf disease classification" Agriculture (2021) 10.3390/agriculture11080707

[26]

Maes "Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture" Trends Plant Sci. (2019) 10.1016/j.tplants.2018.11.007

[27]

Meno "Looking for a sustainable potato crop. field assessment of early blight management" Agric. For. Meteorology (2021) 10.1016/j.agrformet.2021.108617

[28]

Using Deep Learning for Image-Based Plant Disease Detection

Sharada P. Mohanty, David P. Hughes, Marcel Salathé

Frontiers in Plant Science 2016 10.3389/fpls.2016.01419

[29]

Mzoughi "Deep learning-based segmentation for disease identification" Ecol. Inf. (2023) 10.1016/j.ecoinf.2023.102000

[30]

Nassar "2,4-dichlorophenoxy acetic acid, abscisic acid, and hydrogen peroxide induced resistance-related components against potato early blight (alternaria solani, sorauer)" Ann. Agric. Sci. (2016) 10.1016/j.aoas.2016.04.005

[31]

Nickolls "Scalable parallel programming with cuda: Is cuda the parallel programming model that application developers have been waiting for" (2008)

[32]

Oishi "Automated abnormal potato plant detection system using deep learning models and portable video cameras" Int. J. Appl. Earth Observation Geoinformation (2021) 10.1016/j.jag.2021.102509

[33]

Paszke "Pytorch: An imperative style, high-performance deep learning library" (2019)

[34]

(2020)

[35]

Rashid "Multi-level deep learning model for potato leaf disease recognition" Electronics (2021) 10.3390/electronics10172064

[36]

Sholihati "Potato leaf disease classification using deep learning approach" (2020)

[37]

A survey on Image Data Augmentation for Deep Learning

Connor Shorten, Taghi M. Khoshgoftaar

Journal of Big Data 2019 10.1186/s40537-019-0197-0

[38]

Simonyan "Very deep convolutional networks for large-scale image recognition" (2015)

[39]

Szegedy "Rethinking the inception architecture for computer vision" (2016)

[40]

Tan "Efficientnetv2: Smaller models and faster training" (2021)

[41]

Thakur "Trends in vision-based machine learning techniques for plant disease identification: A systematic review" Expert Syst. Appl. (2022) 10.1016/j.eswa.2022.118117

[42]

Tiwari (2020)

[43]

Van De Vijver "Ultra-high-resolution uav-based detection of alternaria solani infections in potato fields" Remote Sens. (2022) 10.3390/rs14246232

[44]

Van De Vijver "In-field detection of alternaria solani in potato crops using hyperspectral imaging" Comput. Electron. Agric. (2020) 10.1016/j.compag.2019.105106

[45]

Wieme "Supervised detection of Alternaria solani on ultra-high-resolution modified RGB UAV images" (2022) 10.1117/12.2638911

[46]

Xia "Fine-grained potato disease identification based on contrastive convolutional neural networks" Appl. Artif. Intell. (2023) 10.1080/08839514.2023.2166233

[47]

Xu (2015)

Metrics

7

Citations

47

References

Details

Published: Mar 05, 2024
Vol/Issue: 15
License: View

Authors

Cite This Article

Jana Wieme, Sam Leroux, Simon R. Cool, et al. (2024). Ultra-high-resolution UAV-imaging and supervised deep learning for accurate detection of Alternaria solani in potato fields. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1206998

Ultra-high-resolution UAV-imaging and supervised deep learning for accurate detection of Alternaria solani in potato fields

You May Also Like