Early season prediction of within-field crop yield variability by assimilating CubeSat data into a crop model
Name:
1-s2.0-S0168192321004226-main.pdf
Size:
20.89Mb
Format:
PDF
Description:
Publisher's version
Type
ArticleAuthors
Ziliani, Matteo G.Altaf, Muhammad
Aragon, Bruno
Houburg, Rasmus
Franz, Trenton E.
Lu, Yang
Sheffield, Justin
Hoteit, Ibrahim

McCabe, Matthew

KAUST Department
Biological and Environmental Science and Engineering (BESE) DivisionBiological and Environmental Science and Engineering (BESE), King Abdullah University of Science and Technology, Kingdom of Saudi Arabia.
Earth Fluid Modeling and Prediction Group
Earth Science and Engineering Program
Earth System Observation and Modelling
Environmental Science and Engineering Program
Physical Science and Engineering (PSE) Division
Water Desalination and Reuse Research Center (WDRC)
KAUST Grant Number
OSR-2017-CRG6Date
2021-11-29Submitted Date
2021-07-02Permanent link to this record
http://hdl.handle.net/10754/673866
Metadata
Show full item recordAbstract
Accurate early season predictions of crop yield at the within-field scale can be used to address a range of crop production, management, and precision agricultural challenges. While the remote sensing of within-field insights has been a research goal for many years, it is only recently that observations with the required spatio-temporal resolutions, together with efficient assimilation methods to integrate these into modeling frameworks, have become available to advance yield prediction efforts. Here we explore a yield prediction approach that combines daily high-resolution CubeSat imagery with the APSIM crop model. The approach employs APSIM to train a linear regression that relates simulated yield to simulated leaf area index (LAI). That relationship is then used to identify the optimal regression date at which the LAI provides the best prediction of yield: in this case, approximately 14 weeks prior to harvest. Instead of applying the regression on satellite imagery that is coincident, or closest to, the regression date, our method implements a particle filter that integrates CubeSat-based LAI into APSIM to provide end-of-season high-resolution (3 m) yield maps weeks before the optimal regression date. The approach is demonstrated on a rainfed maize field located in Nebraska, USA, where suitable collections of both imagery and in-situ data were available for assessment. The procedure does not require in-field data to calibrate the regression model, with results showing that even with a single assimilation step, it is possible to provide yield estimates with good accuracy up to 21 days before the optimal regression date. Yield spatial variability was reproduced reasonably well, with a strong correlation to independently collected measurements (R2 = 0.73 and rRMSE = 12%). When the field averaged yield was compared, our approach reduced yield prediction error from 1 Mg/ha (control case based on a calibrated APSIM model), to 0.5 Mg/ha (using satellite imagery alone), and then to 0.2 Mg/ha (results with assimilation up to three weeks prior to the optimal regression date). Such a capacity to provide spatially explicit yield predictions early in the season has considerable potential to enhance digital agricultural goals and improve end-of-season yield predictions.Citation
Ziliani, M. G., Altaf, M. U., Aragon, B., Houburg, R., Franz, T. E., Lu, Y., … McCabe, M. F. (2022). Early season prediction of within-field crop yield variability by assimilating CubeSat data into a crop model. Agricultural and Forest Meteorology, 313, 108736. doi:10.1016/j.agrformet.2021.108736Sponsors
Research was supported by the King Abdullah University of Science and Technology (Grant number OSR-2017-CRG6) and in collaboration with Planet Labs corporation and the Eastern Nebraska Research and Extension Center at the University of Nebraska-Lincoln (Lincoln, United States), who provided datasets for model calibration and validation. Funding for the AmeriFlux core site was provided by the U.S. Department of Energy's Office of Science. Field data used within this research was a contribution from the Long-Term Agroecosystem Research (LTAR) network. LTAR is supported by the United States Department of Agriculture. T.E.F. acknowledges the financial support of the USDA National Institute of Food and Agriculture, Hatch project #1009760, #1020768 and project #2019–67021–29312. The author would like to thank Prof. Scott Chapman (University of Queensland) and Dr. BangYou Zhang (CSRIO) for their advice with the APSIM crop model simulations.Publisher
Elsevier BVAdditional Links
https://linkinghub.elsevier.com/retrieve/pii/S0168192321004226ae974a485f413a2113503eed53cd6c53
10.1016/j.agrformet.2021.108736
Scopus Count
Except where otherwise noted, this item's license is described as This is an open access article under the CC BY license.