Beyond monthly composites: maximizing information retention in satellite image time series for forest stand classification

This study investigates the effectiveness of data pre-processing and classifier selection in forest stand classification using Satellite Image Time Series (SITS). We compare the performance of Random Forest (RF) and Light Gradient Boosting Machine (LightGBM) on monthly composites and dense time series. While the monthly RF achieves an average accuracy of 74.1%, the use of LightGBM results in lower performance on monthly composites. Our approach, which utilizes synthetic bands generated based on the available Sentinel−2 SITS, improved RF performance by 13.2 percentage points, exceeding the improvement observed when using 10-day composites. This highlights the loss of information that occurs when using composites. LightGBM improved the results by an additional 1.9 percentage points. However, without additional pre-processing, LightGBM can use the raw SITS and outperform these results with an F1 score of 0.906. The generated map was further improved by using margin values to highlight uncertainties and mask areas of uncertainty. Overall, while monthly composites provide a good starting point, the best results are obtained with raw SITS, which allows efficient processing for larger regions without additional pre-processing.