全球变化知识资源中心

The current study attempts to extract the phenological variables of alluvial plain Shorea robusta-dominated tropical moist deciduous forest of Northeast India using threshold-based method. A total of 230 Moderate Resolution Imaging Spectroradiometer (MODIS) MOD13Q1 time series normalized difference vegetation index (NDVI) datasets (year 2006-2015) has been used. Time series NDVI datasets were fitted to an adaptive Savitzky-Golay filter for smoothing. Important phenological matrices, namely start of season (SOS), end of season (EOS), length of season (LOS), peak of season (POS), seasonal amplitude, seasonally integrals (large and small integral), were evaluated. SOS varied from 106 to 120 day of year (DOY) (average of 110 +/- 17.6), and EOS varied from 425 to 441 DOY (average of 431 +/- 14.33). POS reaches in the month of September and October (average 262 +/- 15). In the current study, a mean amplitude of 0.35, lower value of small integral (4.70 +/- 0.34) and higher value of large integral (16.24 +/- 0.25) signify that the studied forest is highly productive ecosystem, with semievergreen or moist deciduous canopy. Strong linear relationship of NDVI with temperature and rainfall was witnessed, particularly with a 1-2 month time lag. Also, NDVI-temperature correlation was found stronger than NDVI-precipitation correlation, suggesting that the area being a humid subtropical region, temperature plays a greater role in the timing of phenological events than rainfall and can act as a crucial factor for growth of the species under the climate changing scenario.