Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum
Abstract
Unmanned aerial vehicle (UAV)-based remote sensing is gaining momentum in a variety of agricultural and environmental applications. Very-high-resolution remote sensing image sets collected repeatedly throughout a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow for an improved estimation of crop traits, as well as the effects of genetics and the environment on these traits. Multispectral and geometric time series imagery was collected by UAV on 11 dates, along with ground-truth data, in a field trial of 866 genetically diverse biomass sorghum accessions. We compared the performance of Convolution Neural Network (CNN) architectures that used image data from single dates (two spatial dimensions, 2D) versus multiple dates (two spatial dimensions + temporal dimension, 3D) to estimate lodging detection and severity. Lodging was detected with 3D-CNN analysis of time series imagery with 0.88 accuracy, 0.92 Precision, and 0.83 Recall. This outperformed the best 2D-CNN on a single date with 0.85 accuracy, 0.84 Precision, and 0.76 Recall. The variation in lodging severity was estimated by the best 3D-CNN analysis with 9.4% mean absolute error (MAE), 11.9% root mean square error (RMSE), and goodness-of-fit (R2) of 0.76. This wasmore »
- Authors:
- Publication Date:
- Research Org.:
- Center for Advanced Bioenergy and Bioproducts Innovation (CABBI), Urbana, IL (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- OSTI Identifier:
- 1843857
- Alternate Identifier(s):
- OSTI ID: 1996350
- Grant/Contract Number:
- SC0018420
- Resource Type:
- Published Article
- Journal Name:
- Remote Sensing
- Additional Journal Information:
- Journal Name: Remote Sensing Journal Volume: 14 Journal Issue: 3; Journal ID: ISSN 2072-4292
- Publisher:
- MDPI AG
- Country of Publication:
- Switzerland
- Language:
- English
- Subject:
- 47 OTHER INSTRUMENTATION; 3D-convolution neural networks; time series; lodging; sorghum
Citation Formats
Varela, Sebastian, Pederson, Taylor L., and Leakey, Andrew D. B. Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum. Switzerland: N. p., 2022.
Web. doi:10.3390/rs14030733.
Varela, Sebastian, Pederson, Taylor L., & Leakey, Andrew D. B. Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum. Switzerland. https://doi.org/10.3390/rs14030733
Varela, Sebastian, Pederson, Taylor L., and Leakey, Andrew D. B. Fri .
"Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum". Switzerland. https://doi.org/10.3390/rs14030733.
@article{osti_1843857,
title = {Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum},
author = {Varela, Sebastian and Pederson, Taylor L. and Leakey, Andrew D. B.},
abstractNote = {Unmanned aerial vehicle (UAV)-based remote sensing is gaining momentum in a variety of agricultural and environmental applications. Very-high-resolution remote sensing image sets collected repeatedly throughout a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow for an improved estimation of crop traits, as well as the effects of genetics and the environment on these traits. Multispectral and geometric time series imagery was collected by UAV on 11 dates, along with ground-truth data, in a field trial of 866 genetically diverse biomass sorghum accessions. We compared the performance of Convolution Neural Network (CNN) architectures that used image data from single dates (two spatial dimensions, 2D) versus multiple dates (two spatial dimensions + temporal dimension, 3D) to estimate lodging detection and severity. Lodging was detected with 3D-CNN analysis of time series imagery with 0.88 accuracy, 0.92 Precision, and 0.83 Recall. This outperformed the best 2D-CNN on a single date with 0.85 accuracy, 0.84 Precision, and 0.76 Recall. The variation in lodging severity was estimated by the best 3D-CNN analysis with 9.4% mean absolute error (MAE), 11.9% root mean square error (RMSE), and goodness-of-fit (R2) of 0.76. This was a significant improvement over the best 2D-CNN analysis with 11.84% MAE, 14.91% RMSE, and 0.63 R2. The success of the improved 3D-CNN analysis approach depended on the inclusion of “before and after” data, i.e., images collected on dates before and after the lodging event. The integration of geometric and spectral features with 3D-CNN architecture was also key to the improved assessment of lodging severity, which is an important and difficult-to-assess phenomenon in bioenergy feedstocks such as biomass sorghum. This demonstrates that spatio-temporal CNN architectures based on UAV time series imagery have significant potential to enhance plant phenotyping capabilities in crop breeding and Precision agriculture applications.},
doi = {10.3390/rs14030733},
journal = {Remote Sensing},
number = 3,
volume = 14,
place = {Switzerland},
year = {Fri Feb 04 00:00:00 EST 2022},
month = {Fri Feb 04 00:00:00 EST 2022}
}
https://doi.org/10.3390/rs14030733
Works referenced in this record:
Lodging effects on high-yielding crops of irrigated semidwarf wheat
journal, December 1987
- Fischer, R. A.; Stapper, M.
- Field Crops Research, Vol. 17, Issue 3-4
O-CNN: octree-based convolutional neural networks for 3D shape analysis
journal, July 2017
- Wang, Peng-Shuai; Liu, Yang; Guo, Yu-Xiao
- ACM Transactions on Graphics, Vol. 36, Issue 4
3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images
journal, January 2018
- Ji, Shunping; Zhang, Chi; Xu, Anjian
- Remote Sensing, Vol. 10, Issue 2
Monitoring of Wheat Growth Status and Mapping of Wheat Yield’s within-Field Spatial Variations Using Color Images Acquired from UAV-camera System
journal, March 2017
- Du, Mengmeng; Noguchi, Noboru
- Remote Sensing, Vol. 9, Issue 3
Crop Yield Prediction Using Multitemporal UAV Data and Spatio-Temporal Deep Learning Models
journal, December 2020
- Nevavuori, Petteri; Narra, Nathaniel; Linna, Petri
- Remote Sensing, Vol. 12, Issue 23
Biomass sorghum production and components under different irrigation/tillage systems for the southeastern U.S.
journal, March 2012
- Rocateli, A. C.; Raper, R. L.; Balkcom, K. S.
- Industrial Crops and Products, Vol. 36, Issue 1
Mapping Barley Lodging with uas Multispectral Imagery and Machine Learning
journal, January 2021
- Vlachopoulos, O.; Leblon, B.; Wang, J.
- The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XLIII-B1-2021
Wheat Lodging Detection from UAS Imagery Using Machine Learning Algorithms
journal, June 2020
- Zhang, Zhao; Flores, Paulo; Igathinathane, C.
- Remote Sensing, Vol. 12, Issue 11
Phenotyping: New Windows into the Plant for Breeders
journal, April 2020
- Watt, Michelle; Fiorani, Fabio; Usadel, Björn
- Annual Review of Plant Biology, Vol. 71, Issue 1
Vegetative nitrogen stress decreases lodging risk and increases yield of irrigated spring wheat in the subtropics
journal, January 2016
- Peake, A. S.; Bell, K. L.; Carberry, P. S.
- Crop and Pasture Science, Vol. 67, Issue 9
Identification of Maize Lodging: a case Study Using a Remotely Piloted Aircraft System
journal, September 2019
- Acorsi, Matheus G.; Martello, Maurício; Angnes, Graciele
- Engenharia Agrícola, Vol. 39, Issue spe
Identifying Morphological and Mechanical Traits Associated with Stem Lodging in Bioenergy Sorghum (Sorghum bicolor)
journal, March 2017
- Gomez, Francisco E.; Muliana, Anastasia H.; Niklas, Karl J.
- BioEnergy Research, Vol. 10, Issue 3
Root lodging is a physical stress that changes gene expression from sucrose accumulation to degradation in sorghum
journal, January 2018
- Mizuno, Hiroshi; Kasuga, Shigemitsu; Kawahigashi, Hiroyuki
- BMC Plant Biology, Vol. 18, Issue 1
Quantifying Lodging Percentage and Lodging Severity Using a UAV-Based Canopy Height Model Combined with an Objective Threshold Approach
journal, March 2019
- Wilke, Norman; Siegmann, Bastian; Klingbeil, Lasse
- Remote Sensing, Vol. 11, Issue 5
Canopy height measurement by photogrammetric analysis of aerial images: Application to buckwheat (Fagopyrum esculentum Moench) lodging evaluation
journal, November 2012
- Murakami, Toshifumi; Yui, Mamiko; Amaha, Koichi
- Computers and Electronics in Agriculture, Vol. 89
Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review
journal, April 2020
- Jiang, Yu; Li, Changying
- Plant Phenomics, Vol. 2020
A Review of Change Detection in Multitemporal Hyperspectral Images: Current Techniques, Applications, and Challenges
journal, June 2019
- Liu, Sicong; Marinelli, Daniele; Bruzzone, Lorenzo
- IEEE Geoscience and Remote Sensing Magazine, Vol. 7, Issue 2
Lodging markedly reduced the biomass of sweet sorghum via decreasing photosynthesis in saline-alkali field
journal, January 2018
- Guo, Jian Rong; Fan, Hai; Wang, Bao Shan
- E3S Web of Conferences, Vol. 38
Automatic Wheat Lodging Detection and Mapping in Aerial Imagery to Support High-Throughput Phenotyping and In-Season Crop Management
journal, November 2020
- Zhao, Biquan; Li, Jiating; Baenziger, P. Stephen
- Agronomy, Vol. 10, Issue 11
A UAV-based framework for crop lodging assessment
journal, February 2021
- Li, Xiaohan; Li, Xuezhang; Liu, Wen
- European Journal of Agronomy, Vol. 123
Lodging reduces yield of rice by self-shading and reductions in canopy photosynthesis
journal, February 1997
- Setter, T. L.; Laureles, E. V.; Mazaredo, A. M.
- Field Crops Research, Vol. 49, Issue 2-3
Towards Predictive Modeling of Sorghum Biomass Yields Using Fraction of Absorbed Photosynthetically Active Radiation Derived from Sentinel-2 Satellite Imagery and Supervised Machine Learning Techniques
journal, April 2019
- Habyarimana, Ephrem; Piccard, Isabelle; Catellani, Marcello
- Agronomy, Vol. 9, Issue 4
Applications of UAV Thermal Imagery in Precision Agriculture: State of the Art and Future Research Outlook
journal, May 2020
- Messina, Gaetano; Modica, Giuseppe
- Remote Sensing, Vol. 12, Issue 9
The Potential and Uptake of Remote Sensing in Insurance: A Review
journal, November 2014
- de Leeuw, Jan; Vrieling, Anton; Shee, Apurba
- Remote Sensing, Vol. 6, Issue 11
Monitoring Maize Lodging Grades via Unmanned Aerial Vehicle Multispectral Image
journal, December 2019
- Sun, Qian; Sun, Lin; Shu, Meiyan
- Plant Phenomics, Vol. 2019
Efficiency of multi-trait, indirect, and trait-assisted genomic selection for improvement of biomass sorghum
journal, December 2017
- Fernandes, Samuel B.; Dias, Kaio O. G.; Ferreira, Daniel F.
- Theoretical and Applied Genetics, Vol. 131, Issue 3
Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley
journal, July 2015
- Bendig, Juliane; Yu, Kang; Aasen, Helge
- International Journal of Applied Earth Observation and Geoinformation, Vol. 39
Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping
journal, February 2021
- Koh, Joshua C. O.; Spangenberg, German; Kant, Surya
- Remote Sensing, Vol. 13, Issue 5
Understanding Growth Dynamics and Yield Prediction of Sorghum Using High Temporal Resolution UAV Imagery Time Series and Machine Learning
journal, May 2021
- Varela, Sebastian; Pederson, Taylor; Bernacchi, Carl J.
- Remote Sensing, Vol. 13, Issue 9
Remote sensing-based crop lodging assessment: Current status and perspectives
journal, May 2019
- Chauhan, Sugandh; Darvishzadeh, Roshanak; Boschetti, Mirco
- ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 151
The Extraction of Wheat Lodging Area in UAV’s Image Used Spectral and Texture Features
journal, September 2014
- Liu, Hai Ying; Yang, Gui Jun; Zhu, Hong Chun
- Applied Mechanics and Materials, Vol. 651-653
Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery
journal, June 2017
- Yang, Ming-Der; Huang, Kai-Siang; Kuo, Yi-Hsuan
- Remote Sensing, Vol. 9, Issue 6
Wide Dynamic Range Vegetation Index for Remote Quantification of Biophysical Characteristics of Vegetation
journal, January 2004
- Gitelson, Anatoly A.
- Journal of Plant Physiology, Vol. 161, Issue 2
Estimating the leaf inclination angle distribution of the wheat canopy using a portable scanning lidar
journal, January 2009
- Hosoi, Fumiki; Nakai, Yohei; Omasa, Kenji
- Journal of Agricultural Meteorology, Vol. 65, Issue 3
Spectral–Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network
journal, January 2017
- Li, Ying; Zhang, Haokui; Shen, Qiang
- Remote Sensing, Vol. 9, Issue 1
Assessing Lodging Severity over an Experimental Maize (Zea mays L.) Field Using UAS Images
journal, September 2017
- Chu, Tianxing; Starek, Michael; Brewer, Michael
- Remote Sensing, Vol. 9, Issue 9
UAV-Based Biomass Estimation for Rice-Combining Spectral, TIN-Based Structural and Meteorological Features
journal, April 2019
- Jiang, Qi; Fang, Shenghui; Peng, Yi
- Remote Sensing, Vol. 11, Issue 7
Convolutional neural networks: an overview and application in radiology
journal, June 2018
- Yamashita, Rikiya; Nishio, Mizuho; Do, Richard Kinh Gian
- Insights into Imaging, Vol. 9, Issue 4
Semantic Segmentation Using Deep Learning with Vegetation Indices for Rice Lodging Identification in Multi-date UAV Visible Images
journal, February 2020
- Yang, Ming-Der; Tseng, Hsin-Hung; Hsu, Yu-Chun
- Remote Sensing, Vol. 12, Issue 4
Improving Lodging Resistance: Using Wheat and Rice as Classical Examples
journal, August 2019
- Shah, Liaqat; Yahya, Muhammad; Shah, Syed Mehar Ali
- International Journal of Molecular Sciences, Vol. 20, Issue 17