Quantcast

Leaf Area Index Estimation Using Time-Series MODIS Data in Different Types of Vegetation

Research paper by Shenghui Fang, Yuan Le, Qi Liang, Xiaojun Liu

Indexed on: 20 May '14Published on: 20 May '14Published in: Journal of the Indian Society of Remote Sensing



Abstract

The aim of this study is to estimate leaf area index (LAI) in different type of plants using vegetation indices (VIs) and neural network algorithms retrieved from MODIS data. Four VI were calculated, and neural networks were built up based on MODIS surface reflectance products. Among the tested VIs, normalized difference vegetation index (NDVI) and chlorophyll index (CI) appeared to be the best candidate indices in estimating LAI across sites with different vegetation types. The models having the highest accuracy were CI for grassland and deciduous broad leaf forest with determination coefficients (R-square above 0.70, and NDVI for crop R-square = 0.78). Neural network showed better results than VI methods except in grassland sites. The added VI information showed no significant improvement of model accuracy for the neural networks in most sites.