EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping

Canh Nguyen, Vasit Sagan iD, Sourav Bhadra iD, Stephen Moose iD

Sensors · 06.02.2023 · 23 (4) · 1827

DOI: 10.3390/s23041827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.02.2023. Verfasst von Canh Nguyen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Taylor Geospatial Institute, St. Louis, MO 63108, USA. Hauptthemen laut MEDLINE: Zea mays, Deep Learning. Die Arbeit wurde bisher 72-mal zitiert (Crossref) und nennt 135 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United States Geological Survey, National Science Foundation, USGS AmericaView.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in unmanned aerial vehicles (UAV), mini and mobile sensors, and GeoAI (a blend of geospatial and artificial intelligence (AI) research) are the main highlights among agricultural innovations to improve crop productivity and thus secure vulnerable food systems. This study investigated the versatility of UAV-borne multisensory data fusion within a framework of multi-task deep learning for high-throughput phenotyping in maize. UAVs equipped with a set of miniaturized sensors including hyperspectral, thermal, and LiDAR were collected in an experimental corn field in Urbana, IL, USA during the growing season. A full suite of eight phenotypes was in situ measured at the end of the season for ground truth data, specifically, dry stalk biomass, cob biomass, dry grain yield, harvest index, grain nitrogen utilization efficiency (Grain NutE), grain nitrogen content, total plant nitrogen content, and grain density. After being funneled through a series of radiometric calibrations and geo-corrections, the aerial data were analytically processed in three primary approaches. First, an extended version normalized difference spectral index (NDSI) served as a simple arithmetic combination of different data modalities to explore the correlation degree with maize phenotypes. The extended NDSI analysis revealed the NIR spectra (750–1000 nm) alone in a strong relation with all of eight maize traits. Second, a fusion of vegetation indices, structural indices, and thermal index selectively handcrafted from each data modality was fed to classical machine learning regressors, Support Vector Machine (SVM) and Random Forest (RF). The prediction performance varied from phenotype to phenotype, ranging from R2 = 0.34 for grain density up to R2 = 0.85 for both grain nitrogen content and total plant nitrogen content. Further, a fusion of hyperspectral and LiDAR data completely exceeded limitations of single data modality, especially addressing the vegetation saturation effect occurring in optical remote sensing. Third, a multi-task deep convolutional neural network (CNN) was customized to take a raw imagery data fusion of hyperspectral, thermal, and LiDAR for multi-predictions of maize traits at a time. The multi-task deep learning performed predictions comparably, if not better in some traits, with the mono-task deep learning and machine learning regressors. Data augmentation used for the deep learning models boosted the prediction accuracy, which helps to alleviate the intrinsic limitation of a small sample size and unbalanced sample classes in remote sensing research. Theoretical and practical implications to plant breeders and crop growers were also made explicit during discussions in the studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Zea maysDeep LearningArtificial IntelligenceUnmanned Aerial DevicesEdible GrainNitrogen

Stichwörter der Autor:innen

GeoAILiDARUAVdata fusionhigh-throughput phenotypinghyperspectralmulti-task deep learning

Substanzen

Nitrogen

Autor:innen und Institutionen

  • Taylor Geospatial Institute, St. Louis, MO 63108, USA.
  • Department of Earth and Atmospheric Sciences, Saint Louis University, St. Louis, MO 63108, USA.
  • Department of Aviation, University of Central Missouri, Warrensburg, MO 64093, USA.
  • Department of Crop Science and Technology, University of Illinois, Urbana, IL 61801, USA.

ORCID-Profile: Vasit Sagan, Sourav Bhadra, Stephen Moose

Förderung

  • United States Geological Survey
  • National Science Foundation
  • USGS AmericaView
  • National Science Foundation Plant Genome Research

Zitieren

APA

Nguyen, C., Sagan, V., Bhadra, S., & Moose, S. (2023). UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping. Sensors, 23(4), 1827. https://doi.org/10.3390/s23041827

Vancouver

Nguyen C, Sagan V, Bhadra S, Moose S. UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping. Sensors. 2023;23(4):1827. doi:10.3390/s23041827

BibTeX
@article{Nguyen2023,
  author = {Nguyen, Canh and Sagan, Vasit and Bhadra, Sourav and Moose, Stephen},
  title = {UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {4},
  pages = {1827},
  doi = {10.3390/s23041827}
}
Kostenlos starten →