Improving the consistency of multi-temporal land cover mapping of Laguna lake watershed using light gradient boosting machine (LightGBM) approach, change detection analysis, and Markov chain

Abstract

The enhanced temporal capability of today's satellite sensors gives us large volumes of data to be processed, analysed, and visualized. Most of the conventional remote sensing software and land cover classification approaches, however, are only designed for single-date observations. To fully utilize the amount of data we receive and to improve land use/land cover mapping (LULC), technological advancements in machine learning, open-source processing, and GPU-accelerated hardware should be utilized. In this paper, a methodology for classification of temporal sequence of Sentinel-2 images was developed using open-source Python libraries. Light Gradient Boosting Machine, a machine learning algorithm that uses tree-based learning, was used to classify different land cover types based on a temporal sequence of Sentinel-2 satellite images. Although the use of powerful machine learning algorithm resulted to more accurate land cover maps, temporal inconsistencies are still pervasive when dealing with time series outputs. To remove these temporal inconsistencies that resulted from misclassifications, temporal land cover filter based on transition probability matrix was applied on the time series land cover maps to modify the illogical land cover transitions. Accuracy assessment revealed good performance of the approach, which produced higher overall accuracy.