DOI: 10.31220/agriRxiv.2022.00120

•  

  Abstract: 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 across a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow improved estimation of crop traits, as well as the effects of genetics and the environment upon them. 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. 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 (R 2 ) of 0.76. This was a significant improvement over the best 2D-CNN analysis with 11.84% MAE, 14.91% RMSE, and 0.63 R 2 . Success of the improved 3D-CNN analysis approach depended on inclusion of before and after data i.e. images collected on dates before and after the lodging event. Integration of geometric and spectral features with 3D-CNN architecture was also key to 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.

  Key words: dates; 3d-cnn; lodging; collected; imagery; 1

  Submit time: 1 January 2022

  Copyright: The copyright holder for this preprint is the author/funder, who has granted agriXiv a license to display the preprint in perpetuity.
• html

• 图表

• Sebastián Varela, Xuying Zheng, Joyce Njuguna, Erik J. Sacks, Dylan Allen, Jeremy Ruhter, Andrew D. B. Leake. Deep convolutional neural networks exploit high spatial and temporal resolution aerial imagery to predict key traits in miscanthus.. 2022. doi: 10.31220/agriRxiv.2022.00155

  Ines Adriaens, W. Ouweltjes, Matti Pastell, C. Kamphui. Detecting dairy cows' lying behavior using noisy 3D ultra-wide band positioning data.. 2022. doi: 10.31220/agriRxiv.2022.00132

  Munir Zia, A. Lodhi, Muhammad Zahid Aziz, Aftab Naseem, Waqar Ahmad, R. Murray Lark, Michael J. Watts, Martin R. Broadley, E.L. Ande. Soil fertility mapping and agronomic advice at the regional scale using private sector data.. 2021. doi: 10.31220/agriRxiv.2021.00113

  Rajeev Kumar, Bimlendra Kumari, Shikha Yashveer, Prashant Kaushi. Assessment of genetic diversity among poplar ( Populus deltoides Marsh.) clones from India using RAPD markers.. 2020. doi: 10.31220/agriRxiv.2020.00014

  Estelle Leroux, I. Llach, Gaelle Besche, Eliel González García, D. Montier, D. Montier, Pierre Marie Bouque. Growth and behaviour of post-weaned Mérinos d'Arles ewe lambs, as measured by a Walk-over-Weighing system under Mediterranean grazing conditions.. 2021. doi: 10.31220/agriRxiv.2021.00109

  Raunak Jahan, Mohammad Monirul Hasan Tipu, Mohammad Mahfujul Haque, Md. Abdus Sala. Black soldier fly (Hermetia illucens) larvae meal as a fish meal replacement in diets for 1 nursing common carp (Cyprinus carpio) fry.. 2021. doi: 10.31220/agriRxiv.2021.00030

  Midian Nascimento dos Santos, Daniel Rothschild, Tina M. Widowski, Shai Barbut, E. Kiarie, I. B. Mandell, Michele T. Guerin, A. Michelle Edwards, Stephanie Torre. In pursuit of a better broiler: carcass traits and muscle myopathies in conventional and slower-growing strains of broiler chickens.. 2021. doi: 10.31220/agriRxiv.2021.00037

  Nuriel Shalom Mor, Tigabo Asras, Eli Gal, Tesfahon Demasia, Ezra Tarab, Nathaniel Ezekiel, Osher Nikapros, Oshri Semimufar, Eva Gladky, Maria Karpenko, Daniel Sason, Д. Н. Маслов, Omri Mo. Wine quality and type prediction from physicochemical properties using neural networks for machine learning: a free software for winemakers and customers.. 2022. doi: 10.31220/agriRxiv.2022.00125

  John Fredy Ramírez-Agudelo, Carlos Santiago Escobar-Restrepo, Rafael Muñoz Tamayo, Sandra L. Posada-Ochoa, Ricardo Rosero-Noguer. Intake time as potential predictor of methane emissions from cattle.. 2022. doi: 10.31220/agriRxiv.2022.00134

  Tashin Ahmed, Chowdhury Rafeed Rahman, Md. Faysal Mahmud Abi. Rice grain disease identification using dual phase convolutional neural network based system aimed at small dataset.. 2021. doi: 10.31220/agriRxiv.2021.00062

• ID	Submit time	Number	Download
  1	2022-01-01	10.31220/agriRxiv.2022.00120V1	Download

• Public  Anonymous  To author only Submit Comments