Deep Convolutional Neural Networks Exploit High-Spatial- and -Temporal-Resolution Aerial Imagery to Phenotype Key Traits in Miscanthus
Open Access
- 25 October 2022
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 14 (21) , 5333
Abstract
Miscanthus is one of the most promising perennial crops for bioenergy production, with high yield potential and a low environmental footprint. The increasing interest in this crop requires accelerated selection and the development of new screening techniques. New analytical methods that are more accurate and less labor-intensive are needed to better characterize the effects of genetics and the environment on key traits under field conditions. We used persistent multispectral and photogrammetric UAV time-series imagery collected 10 times over the season, together with ground-truth data for thousands of Miscanthus genotypes, to determine the flowering time, culm length, and biomass yield traits. We compared the performance of convolutional neural network (CNN) architectures that used image data from single dates (2D-spatial) versus the integration of multiple dates by 3D-spatiotemporal architectures. The ability of UAV-based remote sensing to rapidly and non-destructively assess large-scale genetic variation in flowering time, height, and biomass production was improved through the use of 3D-spatiotemporal CNN architectures versus 2D-spatial CNN architectures. The performance gains of the best 3D-spatiotemporal analyses compared to the best 2D-spatial architectures manifested in up to 23% improvements in R2, 17% reductions in RMSE, and 20% reductions in MAE. The integration of photogrammetric and spectral features with 3D architectures was crucial to the improved assessment of all traits. In conclusion, our findings demonstrate that the integration of high-spatiotemporal-resolution UAV imagery with 3D-CNNs enables more accurate monitoring of the dynamics of key phenological and yield-related crop traits. This is especially valuable in highly productive, perennial grass crops such as Miscanthus, where in-field phenotyping is especially challenging and traditionally limits the rate of crop improvement through breeding.Keywords
Funding Information
- U.S. Department of Energy (DE-SC0018420)
This publication has 60 references indexed in Scilit:
- Estimation of biomass in wheat using random forest regression algorithm and remote sensing dataThe Crop Journal, 2016
- Progress in upscaling Miscanthus biomass production for the European bio‐economy with seed‐based hybridsGCB Bioenergy, 2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Genetic structure ofMiscanthus sinensisandMiscanthus sacchariflorusin Japan indicates a gradient of bidirectional but asymmetric introgressionJournal of Experimental Botany, 2015
- Accelerating the domestication of a bioenergy crop: identifying and modelling morphological targets for sustainable yield increase in MiscanthusJournal of Experimental Botany, 2013
- Assessment of variability in biomass yield and quality: what is an adequate size of sampling area for miscanthus?GCB Bioenergy, 2012
- High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithmInternational Journal of Applied Earth Observation and Geoinformation, 2012
- A LIDAR-based crop height measurement system for Miscanthus giganteusComputers and Electronics in Agriculture, 2012
- A review of remote sensing methods for biomass feedstock productionBiomass and Bioenergy, 2011
- Wide Dynamic Range Vegetation Index for Remote Quantification of Biophysical Characteristics of VegetationJournal of Plant Physiology, 2004