Next Article in Journal
Airborne Laser Scanning Point Cloud Classification Using the DGCNN Deep Learning Method
Previous Article in Journal
Validation of Visually Interpreted Corine Land Cover Classes with Spectral Values of Satellite Images and Machine Learning
Article

Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

1
Agriculture Victoria, Grains Innovation Park, 110 Natimuk Rd, Horsham, VIC 3400, Australia
2
Agriculture Victoria, AgriBio, Centre for AgriBioscience, 5 Ring Road, Bundoora, VIC 3083, Australia
3
School of Applied Systems Biology, La Trobe University, Bundoora, VIC 3083, Australia
4
Centre for Agricultural Innovation, School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, The University of Melbourne, Melbourne, VIC 3010, Australia
*
Author to whom correspondence should be addressed.
Remote Sens. 2021, 13(5), 858; https://doi.org/10.3390/rs13050858
Received: 29 January 2021 / Revised: 19 February 2021 / Accepted: 22 February 2021 / Published: 25 February 2021
Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high-performance end-to-end machine learning pipelines with minimal effort from the user. However, despite AutoML showing great promise for computer vision tasks, to the best of our knowledge, no study has used AutoML for image-based plant phenotyping. To address this gap in knowledge, we examined the application of AutoML for image-based plant phenotyping using wheat lodging assessment with unmanned aerial vehicle (UAV) imagery as an example. The performance of an open-source AutoML framework, AutoKeras, in image classification and regression tasks was compared to transfer learning using modern convolutional neural network (CNN) architectures. For image classification, which classified plot images as lodged or non-lodged, transfer learning with Xception and DenseNet-201 achieved the best classification accuracy of 93.2%, whereas AutoKeras had a 92.4% accuracy. For image regression, which predicted lodging scores from plot images, transfer learning with DenseNet-201 had the best performance (R2 = 0.8303, root mean-squared error (RMSE) = 9.55, mean absolute error (MAE) = 7.03, mean absolute percentage error (MAPE) = 12.54%), followed closely by AutoKeras (R2 = 0.8273, RMSE = 10.65, MAE = 8.24, MAPE = 13.87%). In both tasks, AutoKeras models had up to 40-fold faster inference times compared to the pretrained CNNs. AutoML has significant potential to enhance plant phenotyping capabilities applicable in crop breeding and precision agriculture. View Full-Text
Keywords: automated machine learning; neural architecture search; high-throughput plant phenotyping; wheat lodging assessment; unmanned aerial vehicle automated machine learning; neural architecture search; high-throughput plant phenotyping; wheat lodging assessment; unmanned aerial vehicle
Show Figures

Graphical abstract

MDPI and ACS Style

Koh, J.C.O.; Spangenberg, G.; Kant, S. Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping. Remote Sens. 2021, 13, 858. https://doi.org/10.3390/rs13050858

AMA Style

Koh JCO, Spangenberg G, Kant S. Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping. Remote Sensing. 2021; 13(5):858. https://doi.org/10.3390/rs13050858

Chicago/Turabian Style

Koh, Joshua C.O., German Spangenberg, and Surya Kant. 2021. "Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping" Remote Sensing 13, no. 5: 858. https://doi.org/10.3390/rs13050858

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop