Abstract
Satellite Image Time Series (SITS) have been used to build models for predicting Potato (Solanum tuberosum L.) yields at regional scales, but evidence of extension of such models to local field scale for practical use in precision agriculture is lacking. In this study, multispectral data from the Sentinel-2 satellite were used to interpolate continuous spectral signatures of potato canopies and generate vegetation indices and the red edge inflection point (REIP) to relate to marketable yield and stem density. The SITS data were collected from 94 sampling locations across five potato fields in England, United Kingdom. The sampling locations were georeferenced and the number of stems per square meter, as well as marketable yield, were determined at harvest. The first principal components of the temporal variation of each SITS wavelength were extracted and used to generate 54 vegetation indices to relate to the response variables. Marketable yield was negatively related to the overall seasonal reflectance (first principal component) at 559 nm with a beta coefficient of −0.53 (±0.18 at p = 0.05). Seasonal reflectance at 703 nm had a positive significant relationship with Marketable yield. Marketable yield was modeled with a normalized root mean square error (nRMSE) of 0.16 and R2 of 0.65. On the other hand, Stem density was significantly related to the Specific Leaf Area Vegetation Index (β = 1.66 ± 1.59) but the REIP’s farthest position during the season was reached later in dense canopies (β = 1.18 ± 0.79) with a higher reflectance (β = 3.43 ± 1.9). This suggested that denser canopies took longer to reach their maximum chlorophyll intensity and the intensity was lower than in sparse canopies. Potato stem density was modeled with an nRMSE of 0.24 and R2 of 0.51. These results reinforce the importance of SITS analysis as opposed to the use of single-instance intrinsic indices.
Highlights
The variation in reflectance of electromagnetic radiation between plants of different species and physiological health conditions has enabled the development of remote sensing applications for crop health monitoring, high throughput phenotyping, and precision agriculture
The reflectance pattern of individual wavelengths was typical of the spectral signature of vegetation, showing low reflectance in λ492 and λ665 with higher reflectance in the Near Infra-Red (NIR) bands of λ703, λ740, λ780, and λ864
The temporal profiles of the spectral reflectance of individual bands were revealed to have a significant relationship with potato harvest yield that can be traced to physiological principles related to the spectral properties of plants
Summary
The variation in reflectance of electromagnetic radiation between plants of different species and physiological health conditions has enabled the development of remote sensing applications for crop health monitoring, high throughput phenotyping, and precision agriculture. Satellite image data are often used to derive vegetation indices, most notably the Normalized Difference Vegetation Index (NDVI). Since the launch of the Landsat satellite, a highly active research area has emerged to attempting the use of spectral reflectance values of canopies to predict or infer plant-level dependent variables of interest through traditional linear regression models or machine learning approaches. Very little crop-specific published literature exists on the successful use of vegetation indices from satellite image data to model yield attributes. More studies are required to establish methods for robust transformation of remotely sensed spectral reflectance measurements or the different vegetation indices derived from them in order to provide reliable explanatory variables for the crop biomass or yield variables of interest
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
