Enabling Regular Map Updates and Identification of Impervious Surfaces Through Satellite Data Fusion, Machine Learning and Cloud Platforms

Abstract. Frequent cloud cover is a common impediment deterring many countries from employing optical earth observation data for the purposes of national map updates. A decision-level data fusion approach allows the inclusion of SAR satellite imagery in such locations and therefore has potential to assist in this task. In this study we test a combination of cloud penetrating Sentinel-1 and multispectral Sentinel-2 to enhance the delineation of impervious surfaces from other land cover types, impervious surfaces being a key component of hydro-climatological models in urban and semi-urbanised areas. Using machine learning techniques and leveraging the Copernicus archive in the Google Earth Engine (GEE) platform, a post-classification change detection approach was explored to assess impervious surface expansion between 2017 and 2023 across the urban centre of Dublin, Ireland. Image classification, conducted using a random forest classifier, achieved overall accuracies of 93% and 91% and kappa coefficients of 0.91 and 0.89 for 2017 and 2023 data, respectively for key classes. The potential of multispectral and RADAR indices such as NDVI, NDBI and PRISI was tested and proved generally effective, but showed limitations in areas adjacent to the coast and inland water bodies, with indications of confusion between land cover types. The inclusion of NDWI in the fused dataset was shown to help differentiate waterbodies from impervious surfaces, highlighting the importance of integrating a water-specific index. NDVI outperformed other indices in feature importance, though PRISI was shown to helpfully cluster impervious surfaces.