FI-R model, a novel remote sensing method for fine-scale extraction of vegetation
Published 08 April, 2026
The fine-scale characterization of vegetation surface information serves as a basis for studying the spatial distribution of resources and the dynamic patterns of environmental responses. Accurately extracting the distributions of different crop species is important for improving agricultural production efficiency and ensuring food security. Traditional fine-scale vegetation extraction methods, however, have limited applicability across large areas due to the presence of spectrally similar features and the substantial influence of background interference. As a key phenological stage of angiosperms, flowering is characterized by distinctive flowering times, floral morphology, and canopy spectral signatures, so it is an effective pathway for fine-scale vegetation extraction using remote sensing.
In a new study published in the Journal of Integrative Agriculture, team of researchers from China developed the FI-R model, a novel flowering spectral index for the fine-scale extraction of angiosperms over large areas in complex multi-regional backgrounds, using rapeseed as an example. FI-R shows low sensitivity to background complexity and rapeseed varieties, and has good applicability to multiple multi-spectral sensor images.
"Using rapeseed as an example, we developed a spectral index model for precise flowering vegetation extraction (FI-R) based on Landsat OLI imagery," shares corresponding author Taixia Wu, a professor at Hohai University. "The model integrates a yellowness index (Blue, Green) and a peak index (Red, Nir and SWIR1) while leveraging the NDVI to mitigate background interference from spectrally similar objects."
Notably, the model successfully enables the rapid and accurate large-scale mapping of flowering vegetation under complex background conditions. "It was tested in five rapeseed cultivation regions worldwide with diverse backgrounds and validation datasets were generated using GF imagery and the U.S. CDL dataset," says Wu. "The FI-R model demonstrated superior capability in distinguishing flowering rapeseed from other vegetation, and achieved overall accuracies exceeding 94% in all study areas."
"Furthermore, FI-R is compatible with other multispectral sensors that have similar band configurations, so it is applicable to rapeseed extraction in broader contexts," adds co-corresponding author Hongzhao Tang, a Professor at Land Satellite Remote Sensing Application Center. "It also shows strong potential for the fine-scale extraction of other types of flowering angiosperm vegetation."
Contact Authors:
Sixian Yin, E-mail: yinsx@hhu.edu.cn; Correspondence Taixia Wu, E-mail: wutx@hhu.edu.cn; Hongzhao Tang, E-mail: tanghz@pku.edu.cn
Funder:
This research was supported by the National Natural Science Foundation of China (42201339), and the "Science for a Better Development of Inner Mongolia" Program of the Bureau of Science and Technology of the Inner Mongolia Autonomous Region, China (2022EEDSKJXM003).
Conflict of Interest:
The authors declare that they have no conflict of interest.
See the Article:
Yin S X et al. 2026. Development of the FI-R model, a novel remote sensing method for fine-scale extraction of vegetation, using rapeseed as an example. Journal of Integrative Agriculture, 25(3): 1223-1242.