Agronomy (May 2023)

Evaluation of Field Germination of Soybean Breeding Crops Using Multispectral Data from UAV

  • Rashid Kurbanov,
  • Veronika Panarina,
  • Andrey Polukhin,
  • Yakov Lobachevsky,
  • Natalia Zakharova,
  • Maxim Litvinov,
  • Nazih Y. Rebouh,
  • Dmitry E. Kucher,
  • Elena Gureeva,
  • Ekaterina Golovina,
  • Pavel Yatchuk,
  • Victoria Rasulova,
  • Abdelraouf M. Ali

DOI
https://doi.org/10.3390/agronomy13051348
Journal volume & issue
Vol. 13, no. 5
p. 1348

Abstract

Read online

The use of multispectral aerial photography data contributes to the study of soybean plants by obtaining objective data. The evaluation of field germination of soybean crops was carried out using multispectral data (MSD). The purpose of this study was to develop ranges of field germination of soybean plants according to multispectral survey data from an unmanned aerial vehicle (UAV) for three years (2020, 2021, and 2022). As part of the ground-based research, the number of plants that sprang up per unit area was calculated and expressed as a percentage of the seeds sown. A DJI Matrice 200 Series v2 unmanned aerial vehicle and a MicaSense Altum multispectral camera were used for multispectral aerial photography. The correlation between ground-based and multispectral data was 0.70–0.75. The ranges of field germination of soybean breeding crops, as well as the vegetation indices (VIs) normalized difference vegetation index (NDVI), normalized difference red edge index (NDRE), and chlorophyll index green (ClGreen) were calculated according to Sturges’ rule. The accuracy of the obtained ranges was estimated using the mean absolute percentage error (MAPE). The MAPE values did not exceed 10% for the ranges of the NDVI and ClGreen vegetation indices, and were no more than 18% for the NDRE index. The final values of the MAPE for the three years did not exceed 10%. The developed software for the automatic evaluation of the germination of soybean crops contributed to the assessment of the germination level of soybean breeding crops using multispectral aerial photography data. The software considers data of the three vegetation indices and calculated ranges, and creates an overview layer to visualize the germination level of the breeding plots. The developed method contributes to the determination of field germination for numerous breeding plots and speeds up the process of breeding new varieties.

Keywords