|ZHANG, CHONYUAN - Purdue University|
|LANE, BRENDEN - Purdue University|
|FERNANDEZ-CAMPOS, MARIELA - Purdue University|
|CRUZ-SANCAN, ANDRES - Purdue University|
|LEE, DA-YOUNG - Purdue University|
|GONGORA-CANUL, CARLOS - Purdue University|
|TELENKO, DARCY - Purdue University|
|Goodwin, Stephen - Steve|
|Scofield, Steven - Steve|
|OH, SUNGCHAN - Purdue University|
|CRUZ, CHRISTIAN - Purdue University|
Submitted to: Frontiers in Plant Science
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/21/2022
Publication Date: 1/23/2023
Citation: Zhang, C., Lane, B., Fernandez-Campos, M., Cruz-Sancan, A., Lee, D.-Y., Gongora-Canul, C., Ross, T.J., Da Silva, C.R., Telenko, D.E.P., Goodwin, S.B., Scofield, S.R., Oh, S, Jung, J., Cruz, C.D. 2023. Monitoring tar spot disease in corn at different canopy and temporal levels using aerial multispectral imaging and machine learning. Frontiers in Plant Science. 13. Article 1077403. https://doi.org/10.3389/fpls.2022.1077403.
Interpretive Summary: Tar spot of maize is an emerging disease problem for US corn growers. The ability to detect and measure the disease is critical for growers and researchers. The disease first develops on lower leaves of growing plants, which makes it very hard and labor intensive to score. This article describes progress in developing a high-throughput scoring system using aerial drones equipped with mult-spectral cameras. The drone data when combined with machine learning has led to the development of an effective disease detection and measurement system. This development may lead to significant improvement in the ability of growers to make disease management decisions and for researchers to improve resistance.
Technical Abstract: Tar spot is a high-profile disease, causing various degrees of yield losses on corn in several countries throughout the Americas. Disease symptoms usually appear at the lower canopy in corn fields with a history of tar spot infection, making it difficult to monitor the disease using unmanned aircraft systems (UAS). UAS-based multispectral imaging and machine learning were used to monitor tar spot disease at the different canopy and temporal levels and extract epidemiological parameters from multiple treatments. Disease severity was visually assessed from three canopy levels within micro plots, while aerial images were gathered by UASs equipped with multispectral cameras. Both disease severity and multispectral images were collected from five to 11 time points each year for two years. Image-based features, such as single band reflectance, vegetation indices (VIs), and their statistics, were extracted from ortho-mosaic images and used as inputs for machine learning to develop disease quantification models. The developed models showed encouraging performance in estimating disease severity at different canopy levels in both trials (R2 up to 0.93 during testing and Lin’s concordance correlation coefficient up to 0.97). Epidemiological parameters, including y0 or area under the disease progress curve, were modeled using data derived from multispectral imaging. In addition, results illustrated that digital phenotyping technologies could be used to monitor the onset of tar spot when disease severity was relatively low (< 5%) and evaluate the efficacy of disease management tactics under micro plot conditions. Further studies are required to scale up the results to large corn fields.