Mapping Leaf Area Index With a Smartphone and Gaussian Processes Article Swipe
YOU?
·
· 2015
· Open Access
·
· DOI: https://doi.org/10.1109/lgrs.2015.2488682
Leaf area index (LAI) is a key biophysical parameter used to determine\nfoliage cover and crop growth in environmental studies. Smartphones are\nnowadays ubiquitous sensor devices with high computational power, moderate\ncost, and high-quality sensors. A smartphone app, called PocketLAI, was\nrecently presented and tested for acquiring ground LAI estimates. In this\nletter, we explore the use of state-of-the-art nonlinear Gaussian process\nregression (GPR) to derive spatially explicit LAI estimates over rice using\nground data from PocketLAI and Landsat 8 imagery. GPR has gained popularity in\nrecent years because of their solid Bayesian foundations that offers not only\nhigh accuracy but also confidence intervals for the retrievals. We show the\nfirst LAI maps obtained with ground data from a smartphone combined with\nadvanced machine learning. This work compares LAI predictions and confidence\nintervals of the retrievals obtained with PocketLAI to those obtained with\nclassical instruments, such as digital hemispheric photography (DHP) and LI-COR\nLAI-2000. This letter shows that all three instruments got comparable result\nbut the PocketLAI is far cheaper. The proposed methodology hence opens a wide\nrange of possible applications at moderate cost.\n
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/lgrs.2015.2488682
- OA Status
- green
- Cited By
- 30
- References
- 22
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W2010423750