A Simple Method for Detecting Phenological Change From Time Series of Vegetation Index

Abstract

Remote sensing is a valuable way to retrieve spatially continuous information on vegetation phenological changes, which are widely used as an indicator of climate change. We propose a simple method called weighted cross-correlogram spectral matching—phenology (CCSM-P), which combines CCSM and a weighted correlation system, for detecting vegetation phenological changes by using multiyear vegetation index (VI) time series. In experiments with simulated enhanced VI (EVI) for various scenarios, CCSM-P exhibited high accuracy and robustness to noise and the potential to capture long-term phenological change trends. For a temperate grassland in northern China, CCSM-P retrieved more reasonable vegetation spring phenology from Moderate Resolution Imaging Spectroradiometer (MODIS) EVI images than the MODIS phenology product (MCD12Q2). When validated against field phenological observations in five of the AmeriFlux Network sites in the U.S. (four deciduous broadleaf forest sites and a closed shrublands site), and a cropland site in China, CCSM-P exhibited mean absolute differences (MADs) ranging from 2 to 10 days (median: 4.2 days), whereas MAD of non-CCSM methods showed larger variations, ranging from 5 to 58 days (median: 21.3 days). This is because CCSM-P integrates field phenological observations. Compared with non-CCSM methods, which are widely used to identify phenological events, CCSM-P is more accurate and less dependent on prior knowledge (thresholds or predefined functions), which indicates its effectiveness and applicability for detecting year-to-year variations and long-term change trends in phenology, and should facilitate more reliable assessments of phenological changes in climate change studies.