Predicting plant water content in Eucalyptus grandis forest stands in KwaZulu-Natal, South Africa using field spectra resampled to the Sumbandila Satellite Sensor

The measurement of plant water content is essential to assess stress and disturbance in forest plantations. Traditional techniques to assess plant water content are costly, time consuming and spatially restrictive. Remote sensing techniques offer the alternative of a non-destructive and instantaneous method of assessing plant water content over large spatial scales where ground measurements would be impossible on a regular basis. In the context of South Africa, due to the cost and availability of imagery, studies focusing on the estimation of plant water content using remote sensing data have been limited. With the scheduled launch of the South African satellite SumbandilaSat evident in 2009, it is imperative to test the utility of this satellite in estimating plant water content. This study resamples field spectral data measured from a field spectrometer to the band settings of the SumbandilaSat in order to test its potential in estimating plant water content in a Eucalyptus plantation. The resampled SumbandilaSat wavebands were input into a neural network due to its ability to model non-linearity in a dataset and its inherent ability to perform better than conventional linear models. The integrated approach involving neural networks and the resampled field spectral data successfully predicted plant water content with a correlation coefficient of 0.74 and a root mean square error (RMSE) of 1.41% on an independent test dataset outperforming the traditional multiple regression method of estimation. The best-trained neural network algorithm that was chosen for assessing the relationship between plant water content and the SumbandilaSat bands was based on a few points only and more research is required to test the robustness and effectiveness of this sensor in estimating plant water content across different species and seasons. This is critical for monitoring plantation health in South Africa using a cheaply available local sensor containing key vegetation wavelengths.

[1]  William J. Ripple,et al.  Spectral reflectance relationships to leaf water stress , 1986 .

[2]  M. Scholes,et al.  Application of the 3-PG model to a Eucalyptus grandis stand subjected to varying levels of water and nutritional constraints in KwaZulu-Natal, South Africa , 2005 .

[3]  J. Pulliainen,et al.  Application of an empirical neural network to surface water quality estimation in the Gulf of Finland using combined optical data and microwave data , 2002 .

[4]  B. Turner,et al.  Performance of a neural network: mapping forests using GIS and remotely sensed data , 1997 .

[5]  D. South,et al.  Pine Mortality after Planting on Post- Agricultural Lands in South Africa , 1998 .

[6]  J. Paruelo,et al.  How to evaluate models : Observed vs. predicted or predicted vs. observed? , 2008 .

[7]  Philip J. Howarth,et al.  Hyperspectral remote sensing for estimating biophysical parameters of forest ecosystems , 1999 .

[8]  S. Ustin,et al.  Multi-temporal vegetation canopy water content retrieval and interpretation using artificial neural networks for the continental USA , 2008 .

[9]  Bisun Datt,et al.  Remote Sensing of Water Content in Eucalyptus Leaves , 1999 .

[10]  A. Skidmore,et al.  Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa , 2004 .

[11]  S. Tarantola,et al.  Detecting vegetation leaf water content using reflectance in the optical domain , 2001 .

[12]  Wenjiang Huang,et al.  Estimating winter wheat plant water content using red edge parameters , 2004 .

[13]  L. Kumar,et al.  Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral image data , 2007 .

[14]  Lee Annamalai.  CSIR imaging expertise propels SA to a science high , 2006 .

[15]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[16]  I. Hung.  Assessment of Kriging Accuracy in the GIS Environment , 2001 .

[17]  O. Mutanga,et al.  Integrating remote sensing and spatial statistics to model herbaceous biomass distribution in a tropical savanna , 2006 .

[18]  C. Özkan,et al.  Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities , 2004 .