Satellite DEM Improvement Using Multispectral Imagery and an Artificial Neural Network

A Neural Network-Based Fusion Approach for Improvement of SAR Interferometry-Based Digital Elevation Models in Plain and Hilly Regions of India

Interferometry Synthetic Aperture Radar (InSAR) is an advanced remote sensing technique for studying the earth’s surface topography and deformations; it is used to generate high-quality Digital Elevation Models (DEMs). DEMs are a crucial and primary input to various topographical quantification and modelling applications. The quality of input DEMs can be further improved using fusion methods, which combine multi-sensor or multi-temporal datasets intelligently to retrieve the best information from the input data. This research study is based on developing a Neural Network-based fusion approach for improving InSAR-based DEMs in plain and hilly terrain parts of India. The study areas comprise relatively plain terrain from Ghaziabad and hilly terrain of Dehradun and their surrounding regions. The training dataset consists of DEM elevations and derived topographic attributes like slope, aspect, topographic position index (TPI), terrain ruggedness index (TRI), and vector roughness measure (VRM) in different land use land cover classes of the study areas. The spaceborne altimetry ICESat-2 ATL08 photon data are used as a reference elevation. A Feed Forward Neural Network with a backpropagation algorithm is trained based on the prepared training samples. The trained model produces fused DEMs by learning the relationship between the input and target samples; this is used to predict elevations for the test areas. The accuracy of results from the models is assessed with TanDEM-X 90 m DEM. The fused DEMs show significant improvement in terms of RMSE (Root Mean Square Error) over the input DEMs with an improvement factor of 94.65% in plain areas and 82.62% in hilly areas. The study concludes that the ANN with its universal approximation property can significantly improve the fused DEM.

A Method for SRTM DEM Elevation Error Correction in Forested Areas Using ICESat-2 Data and Vegetation Classification Data

The past decade has witnessed the rapid development of the SRTM (Shuttle Radar Topography Mission) DEM (digital elevation model) in engineering applications and scientific research. The near-global SRTM DEM was generated based on radar interference theory. The latest version of the SRTM DEM with a resolution of 1 arc-second has been widely used in various applications. However, many studies have shown the poor elevation accuracy of the SRTM DEM in forested areas. Recent developments in the field of spaceborne lidar have provided an additional chance to correct the elevation error of the SRTM DEM in forested areas. We developed an easy-to-use method to correct the elevation error of the SRTM DEM based on the spatial interpolation method using the recent Ice, Cloud and land Elevation Satellite-2 data. First, an ICESat-2 terrain control point selection criterion was proposed to reject some erroneous ICESat-2 terrains caused by many factors. Second, we derived the elevation correction surface based on the interpolation method using the refined ICESat-2 terrain. Finally, a corrected SRTM DEM of forested areas was generated through the obtained elevation correction surface. The proposed method was tested in the typical forested area located in Massachusetts, USA. The results show that the RMSE of the selected terrain control points in vegetation areas and non-vegetation areas are 1.03 and 0.68 m, respectively. The corrected SRTM DEM have an RMSE of 4.2 m which is significantly less than that of the original SRTM DEM with an RMSE of 9.8 m, which demonstrates the proposed method is feasible to correct the elevation error in forested areas. It can be concluded that the proposed method obviously decreases the elevation error of the original SRTM DEM.

Application of Multi-Channel Convolutional Neural Network to Improve DEM Data in Urban Cities

A digital elevation model (DEM) represents the topographic surface of the Earth and is an indispensable source of data in many applications, such as flood modeling, infrastructure design and land management. DEM data at high spatial resolution and high accuracy of elevation data are not only costly and time-consuming to acquire but also often confidential. In this paper, we explore a cost-effective approach to derive good quality DEM data by applying a multi-channel convolutional neural network (CNN) to enhance free resources of available DEM data. Shuttle Radar Topography Mission (SRTM) data, multi-spectral imaging Sentinel-2, as well as Google satellite imagery were used as inputs to the CNN model. The CNN model was first trained using high-quality reference DEM data in a dense urban city—Nice, France—then validated on another site in Nice and finally tested in the Orchard Road area (Singapore), which is also an equally dense urban area in Singapore. The CNN model not only shows an impressive reduction in the root mean square error (RMSE) of 50% at validation site in Nice and 30% at the test site in Singapore, but also results in much clearer profiles of the land surface than input SRTM data. A comparison between CNN performance and that of an earlier conducted study using artificial neural networks (ANN) was conducted as well. The comparison within this limited study shows that CNN yields a more accurate DEM.