Time series analysis of phenometrics and long-term vegetation trends for the Flint Hills ecoregion using moderate resolution satellite imagery

Abstract

Grasslands of the Flint Hills are often burned as a land management practice. Remote sensing can be used to help better manage prairie landscapes by providing useful information about the long-term trends in grassland vegetation greenness and helping to quantify regional differences in vegetation development. Using MODIS 16-day NDVI composite imagery between the years 2001-10 for the entire Flint Hills ecoregion, BFAST was used to determine trend, seasonal, and noise components of the image time series. To explain the trend, 4 factors were considered including hydrologic soil group, burn frequency, and precipitation deviation from the 30 year normal. In addition, the time series data was processed using TIMESAT to extract eight different phenometrics: Growing season length, start of season, end of season, middle of season, maximum value, small integral, left derivative, and right derivative. Phenometrics were produced for each year of the study and an ANOVA was performed on the means of all eight phenometrics to assess if significant differences existed across the study area. A K-means cluster analysis was also performed by aggregating pixel-level phenometrics at the county level to identify administrative divisions exhibiting similar vegetation development. For the study period, the area of negatively and positively trending grassland were similar (41-43%). Logistic regression showed that the log odds of a pixel experiencing a negative trend were higher in sites with clay soils and higher burning frequencies and lower for pixels having higher than normal precipitation and loam soils. Significant differences existed for all phenometrics when considering the ecoregion as a whole. On a phenometric-by-phenometric basis, unexpected groupings of counties often showed statistically similar values. Similarly, when considering all phenometrics at the same time, counties clustered in surprising patterns. Results suggest that long-term trends in grassland conditions warrant further attention and may rival other sources of grassland change (e.g., conversion, transition to savannah) in importance. Analyses of phenometrics indicates that factors other than natural gradients in temperature and precipitation play a significant role in the annual cycle of grassland vegetation development. Unanticipated, and sometimes geographically disparate, groups of counties were shown to be similar in the context of specific phenology metrics and this may prove useful in future implementations of smoke management plans within the Flint Hills.