Effect of high-resolution satellite and UAV imagery plot pixel resolution in wheat crop yield prediction

ABSTRACT

Accurate crop performance assessment and yield prediction in plant breeding programmes can aid decision-making to improve productivity and product quality during crop selection and management. Grain yield is a complex trait, which is a function of the genotype-environment interaction. While using digital remote sensing traits to assess crop performance and predict yield, the characteristics of the sensing tools and approaches can influence prediction performance. In this study, two sensing scales, an unmanned aerial vehicle (UAV) equipped with a ten-band multispectral camera and high-resolution (~0.31 m) WorldView-3 satellite imagery, were used to monitor spring and winter wheat breeding trails in two growing seasons (2020 and 2021). The breeding plots were planted in three different plot sizes (about 1.5 × 5.0 m, 3.0 × 11.0 m, and 4.5 × 11.0 m in spring wheat, and about 1.5 × 3.0 m, 3.0 × 7.3 m, and 4.5 × 7.3 m in winter wheat), with each having 12 varieties and three replications per variety. The spectral and vegetation indices (VI) were extracted from the datasets, and machine learning models for yield prediction (partial least squares regression, least absolute shrinkage selector operator regression, and random forest regression) were evaluated. With multiscale approaches, a moderate to strong correlation of VI data between high-resolution satellite and UAV data (0.42 ≤ r ≤ 0.99, p < 0.01) was found in most cases. The yield prediction accuracies using the extracted data from the high-resolution satellite (6.26 ≤ RMSE% ≤ 25.49; 5.11 ≤ MAE% ≤ 20.95; 0.17 ≤ r ≤ 0.78) and UAV imagery (5.53 ≤ RMSE% ≤ 17.20; 4.28 ≤ MAE% ≤ 14.20; 0.43 ≤ r ≤ 0.92) were also comparable. These findings inform the applications of high-resolution satellite imagery in breeding programmes, considering that the plot size would influence yield prediction accuracies.

KEYWORDS:

• Remote sensing
• WorldView-3
• wheat breeding
• machine learning
• phenomics

Acknowledgements

The authors greatly appreciate the assistance from Dr. Kumar Navulur and Mr. Mark Andel from Maxar Technologies for providing this study’s very high-resolution satellite imagery.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data Availability statement

Data will be available upon reasonable request.

Supplementary Material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/01431161.2024.2313997

Correction Statement

This article has been corrected with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

This study was funded by the Emerging Research Issues Internal Competitive Grant from the College of Agricultural, Human, and Natural Resource Sciences Office of Research at Washington State University under Grant [20-04]; the United States Department of Agriculture (USDA)—National Institute for Food and Agriculture (NIFA) Competitive Projects [accession number 1018562, 1028108]; the USDA-AFRI grant number 2022-68013-36439 (WheatCAP); and HatchProject [accession number 1014919].