Nitrogen prediction model of rice plant at panicle initiation stage using ground-based hyperspectral imaging: growing degree-days integrated model

• Published in: Precision agriculture Vol. 16; no. 5; pp. 558 - 570
• Main Authors: Onoyama, Hiroyuki, Ryu, Chanseok, Suguri, Masahiko, Iida, Michihisa
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2015; Springer Nature B.V
• Subjects: Agricultural production; Agriculture; Analytical chemistry; Atmospheric Sciences; Biomedical and Life Sciences; Chemistry and Earth Sciences; Computer Science; Crop science; Digital cameras; equations; heat sums; hyperspectral imagery; inflorescences; Irrigation water; least squares; Life Sciences; Nitrogen; nitrogen content; Physics; prediction; Prediction models; reflectance; Regression analysis; Remote sensing; Remote Sensing/Photogrammetry; Rice; soil; Soil conditioners; Soil Science & Conservation; Statistics for Engineering; Studies; temperature; variance; Vegetation; Japan; Paddy rice; Nitrogen content; Growing degree-days integrated model; Panicle initiation stage; Growing degree-days; Ground-based hyperspectral imaging
• ISSN: 1385-2256; 1573-1618
• DOI: 10.1007/s11119-015-9394-9

Ground-based hyperspectral imaging was applied to rice plants at the panicle initiation stage to estimate nitrogen content. We developed a partial least squares regression (PLSR) model that incorporated both the reflectance and growing degree-days (GDD) to account for differences in growing temperature conditions across a 3-year period. The acquired images were divided into two components: (1) the rice plant and (2) other elements (e.g., irrigation water, soil background) by using the GreenNDVI − NDVI equation. Rice plant reflectance (Ref RICE) was calculated as the ratio of rice plant reflectance to that of a reference board. Three types of PLSR models were constructed: 1-year, 2-year, and 2-year GDD. Mutual estimation was used to infer the predictive power of the three models, which was calculated by estimating the values for the other years. The root mean square error of prediction (RMSE) of the mutual estimation for the 1- and 2-year PLSR models was high because of overestimation and underestimation. In contrast, the RMSE of the mutual estimation for the 2-year GDD PLSR models clearly decreased. It was inferred that hyperspectral imaging at 400–1000 nm could not predict variation in the amount of growth caused by weather variation expressed as GDD. This study indicates that the combination of reflectance and temperature data could be used to potentially construct an adaptable model to identify variance in growing conditions.