High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images
To ensure global food security, crop breeders conduct extensive trials across various locations to discover new crop varieties that grow more robustly, have higher yields, and are resilient to local stress factors. These trials consist of thousands of plots, each containing a unique crop variety monitored at intervals during the growing season, requiring considerable manual effort. In this study, we combined satellite imagery and deep learning techniques to automatically collect plot-level phenotypes from plant breeding trials in South Australia and Sonora, Mexico. We implemented two novel methods, utilising state-of-the-art computer vision architectures, to predict plot-level phenotypes: flowering, canopy cover, greenness, height, biomass, and normalised difference vegetation index (NDVI). The first approach uses a classification model to predict for just the centred plot. The second approach predicts per-pixel and then aggregates predictions to determine a value per-plot. Using a modified ResNet18 model to predict the centred plot was found to be the most effective method. These results highlight the exciting potential for improving crop trials with remote sensing and machine learning.
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article/Letter to editor biblioteca |
| Language: | English |
| Subjects: | agriculture, deep learning, object-based image analysis, optical imagery, plant breeding, |
| Online Access: | https://research.wur.nl/en/publications/high-throughput-plot-level-quantitative-phenotyping-using-convolu |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-wur-nl-wurpubs-626700 |
|---|---|
| record_format |
koha |
| spelling |
dig-wur-nl-wurpubs-6267002024-12-04 Victor, Brandon Nibali, Aiden Newman, Saul Justin Coram, Tristan Pinto, Francisco Reynolds, Matthew Furbank, Robert T. He, Zhen Article/Letter to editor Remote Sensing 16 (2024) 2 ISSN: 2072-4292 High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images 2024 To ensure global food security, crop breeders conduct extensive trials across various locations to discover new crop varieties that grow more robustly, have higher yields, and are resilient to local stress factors. These trials consist of thousands of plots, each containing a unique crop variety monitored at intervals during the growing season, requiring considerable manual effort. In this study, we combined satellite imagery and deep learning techniques to automatically collect plot-level phenotypes from plant breeding trials in South Australia and Sonora, Mexico. We implemented two novel methods, utilising state-of-the-art computer vision architectures, to predict plot-level phenotypes: flowering, canopy cover, greenness, height, biomass, and normalised difference vegetation index (NDVI). The first approach uses a classification model to predict for just the centred plot. The second approach predicts per-pixel and then aggregates predictions to determine a value per-plot. Using a modified ResNet18 model to predict the centred plot was found to be the most effective method. These results highlight the exciting potential for improving crop trials with remote sensing and machine learning. en application/pdf https://research.wur.nl/en/publications/high-throughput-plot-level-quantitative-phenotyping-using-convolu 10.3390/rs16020282 https://edepot.wur.nl/649031 agriculture deep learning object-based image analysis optical imagery plant breeding https://creativecommons.org/licenses/by/4.0/ https://creativecommons.org/licenses/by/4.0/ Wageningen University & Research |
| institution |
WUR NL |
| collection |
DSpace |
| country |
Países bajos |
| countrycode |
NL |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-wur-nl |
| tag |
biblioteca |
| region |
Europa del Oeste |
| libraryname |
WUR Library Netherlands |
| language |
English |
| topic |
agriculture deep learning object-based image analysis optical imagery plant breeding agriculture deep learning object-based image analysis optical imagery plant breeding |
| spellingShingle |
agriculture deep learning object-based image analysis optical imagery plant breeding agriculture deep learning object-based image analysis optical imagery plant breeding Victor, Brandon Nibali, Aiden Newman, Saul Justin Coram, Tristan Pinto, Francisco Reynolds, Matthew Furbank, Robert T. He, Zhen High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| description |
To ensure global food security, crop breeders conduct extensive trials across various locations to discover new crop varieties that grow more robustly, have higher yields, and are resilient to local stress factors. These trials consist of thousands of plots, each containing a unique crop variety monitored at intervals during the growing season, requiring considerable manual effort. In this study, we combined satellite imagery and deep learning techniques to automatically collect plot-level phenotypes from plant breeding trials in South Australia and Sonora, Mexico. We implemented two novel methods, utilising state-of-the-art computer vision architectures, to predict plot-level phenotypes: flowering, canopy cover, greenness, height, biomass, and normalised difference vegetation index (NDVI). The first approach uses a classification model to predict for just the centred plot. The second approach predicts per-pixel and then aggregates predictions to determine a value per-plot. Using a modified ResNet18 model to predict the centred plot was found to be the most effective method. These results highlight the exciting potential for improving crop trials with remote sensing and machine learning. |
| format |
Article/Letter to editor |
| topic_facet |
agriculture deep learning object-based image analysis optical imagery plant breeding |
| author |
Victor, Brandon Nibali, Aiden Newman, Saul Justin Coram, Tristan Pinto, Francisco Reynolds, Matthew Furbank, Robert T. He, Zhen |
| author_facet |
Victor, Brandon Nibali, Aiden Newman, Saul Justin Coram, Tristan Pinto, Francisco Reynolds, Matthew Furbank, Robert T. He, Zhen |
| author_sort |
Victor, Brandon |
| title |
High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| title_short |
High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| title_full |
High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| title_fullStr |
High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| title_full_unstemmed |
High-Throughput Plot-Level Quantitative Phenotyping Using Convolutional Neural Networks on Very High-Resolution Satellite Images |
| title_sort |
high-throughput plot-level quantitative phenotyping using convolutional neural networks on very high-resolution satellite images |
| url |
https://research.wur.nl/en/publications/high-throughput-plot-level-quantitative-phenotyping-using-convolu |
| work_keys_str_mv |
AT victorbrandon highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT nibaliaiden highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT newmansauljustin highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT coramtristan highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT pintofrancisco highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT reynoldsmatthew highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT furbankrobertt highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages AT hezhen highthroughputplotlevelquantitativephenotypingusingconvolutionalneuralnetworksonveryhighresolutionsatelliteimages |
| _version_ |
1819140838672826368 |