摘要
Drought Monitoring by remotely sensed moisture vegetation indexes is being an active research subject as the vegetation spectral responses are showed to be highly correlated to water content. The MODIS (MODerate resolution Imaging Spectro-radiometer) sensor of the Terra satellite provides MOD09A1 product of BRDF (Bidirectional Reflectance Distribution Function) used in computing moisture vegetation indexes (MVI). The exploration of an MVI time-series in the Kroumirie forest in Northern Tunisia showed important noise due to both clouds contamination and sensor defaults that had to be removed. Amongst methods for removing these imperfections, TIMESAT tool was designed for correcting time-series of satellite data and also to retrieve seasonal parameters from smoothed vegetation indexes. The methodology of smoothing functions to fit the time series data is based on two stages. First, a least square fit to the upper envelope of the vegetation indices series is applied. The second stage is achieved by local and adaptive fitting functions. The corrections have been made by spikes removal due to abrupt change of MVI variations and by fitting the MVI time-series to the upper envelop to correct the negative biases of remote sensing vegetation indexes. The adaptive Savitsky-Golay function filter compared to local filtering process produces variations that conserve local variations for all the tested MVI. Seasonal vegetation parameters were extracted for each year of the time-series analysis and compared to the Standardized Precipitation Index (SPI) calculated at meteorological station level and for different time scales. Positive relations were found between SPI and the seasonal parameters expressed by the length and the amplitude of the season, indicating MODIS derived MVI sensitivity to water deficit or surplus conditions. The 6-month SPI showed the best performance when related to water sensitive indexes suggesting that MODIS derived indexes are more correlated to the precipitation variations over seasons.
Drought Monitoring by remotely sensed moisture vegetation indexes is being an active research subject as the vegetation spectral responses are showed to be highly correlated to water content. The MODIS (MODerate resolution Imaging Spectro-radiometer) sensor of the Terra satellite provides MOD09A1 product of BRDF (Bidirectional Reflectance Distribution Function) used in computing moisture vegetation indexes (MVI). The exploration of an MVI time-series in the Kroumirie forest in Northern Tunisia showed important noise due to both clouds contamination and sensor defaults that had to be removed. Amongst methods for removing these imperfections, TIMESAT tool was designed for correcting time-series of satellite data and also to retrieve seasonal parameters from smoothed vegetation indexes. The methodology of smoothing functions to fit the time series data is based on two stages. First, a least square fit to the upper envelope of the vegetation indices series is applied. The second stage is achieved by local and adaptive fitting functions. The corrections have been made by spikes removal due to abrupt change of MVI variations and by fitting the MVI time-series to the upper envelop to correct the negative biases of remote sensing vegetation indexes. The adaptive Savitsky-Golay function filter compared to local filtering process produces variations that conserve local variations for all the tested MVI. Seasonal vegetation parameters were extracted for each year of the time-series analysis and compared to the Standardized Precipitation Index (SPI) calculated at meteorological station level and for different time scales. Positive relations were found between SPI and the seasonal parameters expressed by the length and the amplitude of the season, indicating MODIS derived MVI sensitivity to water deficit or surplus conditions. The 6-month SPI showed the best performance when related to water sensitive indexes suggesting that MODIS derived indexes are more correlated to the precipitation variations over seasons.
