Spatio-temporal prediction of leaf area index of rubber plantation using HJ-1A/1B CCD images and recurrent neural network.

Rubber ( Hevea brasiliensis ) plantations are one of the most important economic forest in tropical area. Retrieving leaf area index (LAI) and its dynamics by remote sensing is of great significance in ecological study and production management, such as yield prediction and post-hurricane damage evaluation. Thirteen HJ-1A/1B CCD images, which possess the spatial advantage of Landsat TM/ETM+ and 2-days temporal resolution of MODIS, were introduced to predict the spatial–temporal LAI of rubber plantation on Hainan Island by Nonlinear AutoRegressive networks with eXogenous inputs (NARX) model. Monthly measured LAIs at 30 stands by LAI-2000 between 2012 and 2013 were used to explore the LAI dynamics and their relationship with spectral bands and seven vegetation indices, and to develop and validate model. The NARX model, which was built base on input variables of day of year (DOY), four spectral bands and weight difference vegetation index (WDVI), possessed good accuracies during the model building for the data set of training ( N = 202, R 2 = 0.98, RMSE = 0.13), validation ( N = 43, R 2 = 0.93, RMSE = 0.24) and testing ( N = 43, R 2 = 0.87, RMSE = 0.31), respectively. The model performed well during field validation ( N = 24, R 2 = 0.88, RMSE = 0.24) and most of its mapping results showed better agreement ( R 2 = 0.54–0.58, RMSE = 0.47–0.71) with the field data than the results of corresponding stepwise regression models ( R 2 = 0.43–0.51, RMSE = 0.52–0.82). Besides, the LAI statistical values from the spatio-temporal LAI maps and their dynamics, which increased dramatically from late March (2.36 ± 0.59) to early May (3.22 ± 0.64) and then gradually slow down until reached the maximum value in early October (4.21 ± 0.87), were quite consistent with the statistical results of the field data. The study demonstrates the feasibility and reliability of retrieving spatio-temporal LAI of rubber plantations by an artificial neural network (ANN) approach, and provides some insight on the application of HJ-1A/1B CCD images, and data and methods for productivity study of rubber plantation in future. [ABSTRACT FROM AUTHOR]