D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

Abstract

LIDAR (light detection and ranging) is an optical remote-sensing technique that measures the distance between sensor and object, and the reflected energy from the object. Over the years, LIDAR data has been used as the primary source of Digital Elevation Models (DEMs). DEMs have been used in a variety of applications like road extraction, hydrological modeling, flood mapping, and surface analysis. A number of studies in flooding suggest the usage of high- resolution DEMs as inputs in the applications improve the overall reliability and accuracy. Despite the importance of high-resolution DEM, many areas in the United States and the world do not have access to high-resolution DEM due to technological limitations or the cost of the data collection. With recent development in Graphical Processing Units (GPU) and novel algorithms, deep learning techniques have become attractive to researchers for their performance in learning features from high-resolution datasets. Numerous new methods have been proposed such as Generative Adversarial Networks (GANs) to create intelligent models that correct and augment large-scale datasets. In this paper, a GAN based model is developed and evaluated, inspired by single image super-resolution methods, to increase the spatial resolution of a given DEM dataset up to 4 times without additional information related to data.

A Comprehensive Review of Ontologies in the Hydrology Towards Guiding Next Generation Artificial Intelligence Applications

“…Ontologies can power immersive applications to embed environmental behavior and interactions (e.g., water flow, structural integrity, sensor data, populational information, weather conditions) into the simulations which in turn enables analytics in addition to observation in extreme conditions, including context-aware hydrological disaster simulations, mitigation strategy assessment, environmental phenomena development. Machine Learning: The use cases and benefits of deep neural networks in hydrology are wellestablished ranging from data augmentation (Demiray et al, 2021) and realistic image generation (Gautam et al, 2020). Though often black box approaches are taken to let the data determine the priorities and infer the relevant correlations, physics-informed networks have recently gained traction for both during data preparation as well as network design (Baker et al, 2019).…”

Camera-Based Intelligent Stream Stage Sensing for Decentralized Environmental Monitoring

“…The 3D model of the structure on the measurement site is defined before deployment and saved in a relational database accessible via an API with functionality allowing the device to query by location and orientation to retrieve the desired POI in close proximity. The 3D model consists of a combination of geometrical objects with geolocation representing a simplified version of the intersecting structure, location and shape of which can be assessed in a variety of strategies, including retrieving structure plans and data from building owners or from the city, manual on-site measurements using precise land surveying equipment, and utilizing high-accuracy or upscaled digital elevation models (DEM) (Demiray et al, 2021). However, for the sake of rapid prototyping, worldwide applicability, convenience, and low cost, Google Earth has been used to extract the geolocations of the objects of interest and define the POI.…”

Real-World DEM Super-Resolution Based on Generative Adversarial Networks for Improving InSAR Topographic Phase Simulation

“…In addition, some researchers have attempted to address the problem based on GAN methods. Demiray, et al [10] proposed D-SRGAN to increase the resolution up to four times based on the SRGAN method. Wu and Ma [9] introduced ESRGAN to specifically address the limited DEM resolution of landslide areas, which achieved tangible results and validated the practicability of the ESRGAN method on DEM SR.…”

“…Deep learning (DL) models have shown promising results on both image SR and DEM SR [7][8][9][10][11]. The generative adversarial network (GAN) models achieved the state-of-art performance for image SR [12,13].…”