Understanding growth dynamics and yield prediction of sorghum using high temporal resolution UAV imagery time series and machine learning

Authors: VARELA, SEBASTIAN - University Of Illinois; PEDERSON, TAYLOR - University Of Illinois; Bernacchi, Carl; LEAKEY, ANDREW D B - University Of Illinois

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/28/2021
Publication Date: 5/1/2021
Citation: Varela, S., Pederson, T., Bernacchi, C.J., Leakey, A.D.B. 2021. Understanding growth dynamics and yield prediction of sorghum using high temporal resolution UAV imagery time series and machine learning. Remote Sensing. 13(9). Article 1763. https://doi.org/10.3390/rs13091763.
DOI: https://doi.org/10.3390/rs13091763

Interpretive Summary: There is a growing need to make fast measurements over entire agricultural fields. This need is driven by a requirement that food security is maintained as population grows, agricultural demands increase, and climate changes pressure crops. This research sought to measure whole fields representing a large variety of crops over multiple measurement dates throughout a growing season. The goal was to see whether frequent measurements were better able to predict final yield, and whether final yields could be predicted early in the growing season. The results showed that good prediction of final yield was available with five measurements of plant height all in the first 50 days of the growing season. The results were not much improved with 10 measurement days, suggesting that frequent measurements are very useful for predicting yields but above a certain threshold more does not necessarily mean better.

Technical Abstract: Unmanned aerial vehicles (UAV) carrying multispectral cameras are increasingly being used for high-throughput phenotyping (HTP) of above-ground traits of crops to study genetic diversity, resource use efficiency and responses to abiotic or biotic stresses. There is significant unexplored potential for repeated data collection through a field season to reveal information on the rates of growth and provide predictions of the final yield. Generating such information early in the season would create opportunities for more efficient in-depth phenotyping and germplasm selection. This study tested the use of high-resolution time-series imagery (5 or 10 sampling dates) to understand the relationships between growth dynamics, temporal resolution and end-of-season above-ground biomass (AGB) in 869 diverse accessions of highly productive (mean AGB = 23.4 Mg/Ha), photoperiod sensitive sorghum. Canopy surface height (CSM), ground cover (GC), and five common spectral indices were considered as features of the crop phenotype. Spline curve fitting was used to integrate data from single flights into continuous time courses. Random Forest was used to predict end-of-season AGB from aerial imagery, and to identify the most informative variables driving predictions. Improved prediction of end-of-season AGB (RMSE reduction of 0.24 Mg/Ha) was achieved earlier in the growing season (10 to 20 days) by leveraging early- and mid-season measurement of the rate of change of geometric and spectral features. Early in the season, dynamic traits describing the rates of change of CSM and GC predicted end-of-season AGB best. Late in the season, CSM on a given date was the most influential predictor of end-of-season AGB. The power to predict end-of-season AGB was greatest at 50 days after planting, accounting for 63% of variance across this very diverse germplasm collection with modest error (RMSE 1.8 Mg/ha). End-of-season AGB could be predicted equally well when spline fitting was performed on data collected from five flights versus 10 flights over the growing season. This demonstrates a more valuable and efficient approach to using UAVs for HTP, while also proposing strategies to add further value.