Regional NDVI Attribution Analysis and Trend Prediction Based on the Informer Model: A Case Study of the Maowusu Sandland

Abstract

Terrestrial ecosystems depend heavily on their vegetation; it is possible to forecast future growth trends of regional vegetation by keeping an eye on changes in vegetation dynamics. To circumvent the potential reduction in prediction accuracy caused by the non-stationarity of meteorological changes, we analyzed the characteristics of NDVI (Normalized Difference Vegetation Index) spatial and temporal changes and the influencing factors over the past 20 years in the Maowusu Sandland of China via attribution analysis. We also constructed a comprehensive analysis system for vegetation pre-restoration. Moreover, we combined meteorological data from 2000 to 2018 and presented a deep-learning NDVI-Informer prediction model with a self-attentive mechanism. We also used distillation operation and fusion convolutional neural network for NDVI prediction. Incorporating a probsparse self-attention method successfully overcomes Transformer weaknesses by lowering the memory use and complexity of large time series. It significantly accelerates the inference speed of long time series prediction and works well with non-smooth data. The primary findings were: (1) the Maowusu Sandland’s 20-year average showed a consistent increasing trend in the NDVI at 0.0034 a−1, which was mostly caused by climate change, with a relative contribution rate of 55.47%; (2) The Informer-based model accurately forecasted the NDVI in the research region based on meteorological elements and conducted a thorough analysis of the MAPE (mean absolute percentage error) (2.24%). This suggests that it can effectively lower the data’s volatility and increase prediction accuracy. The anticipated outcomes indicate that the trend will stabilize during the following ten years. To attain more sustainable and efficient agricultural production, the results of this study may be used to accurately estimate future crop yields and NDVI using previous data.