Towards Spatial Variability Aware Deep Neural Networks (SVANN): A Summary of Results
This work provides an incremental improvement for remote sensing and geospatial analysis practitioners by offering a method to account for spatial variability in deep learning models, potentially leading to more accurate mapping of geo-phenomena.
This paper addresses the issue of spatial variability in geo-phenomena by proposing a Spatial Variability Aware Deep Neural Network (SVANN) approach, where distinct models are trained for different geographic areas. When applied to mapping urban gardens using aerial imagery from two areas, SVANN demonstrated improved precision, recall, and F1-score compared to the traditional spatial-one-size-fits-all (OSFA) method.
Spatial variability has been observed in many geo-phenomena including climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all(OSFA) approach to train single deep neural network models that do not account for spatial variability. In this work, we propose and investigate a spatial-variability aware deep neural network(SVANN) approach, where distinct deep neural network models are built for each geographic area. We evaluate this approach using aerial imagery from two geographic areas for the task of mapping urban gardens. The experimental results show that SVANN provides better performance than OSFA in terms of precision, recall,and F1-score to identify urban gardens.