Earth Imagery Segmentation on Terrain Surface with Limited Training Labels: A Semi-supervised Approach based on Physics-Guided Graph Co-Training

Given earth imagery with spectral features on a terrain surface, this paper studies surface segmentation based on both explanatory features and surface topology. The problem is important in many spatial and spatiotemporal applications such as flood extent mapping in hydrology. The problem is uniquely challenging for several reasons: first, the size of earth imagery on a terrain surface is often much larger than the input of popular deep convolutional neural networks; second, there exists topological structure dependency between pixel classes on the surface, and such dependency can follow an unknown and non-linear distribution; third, there are often limited training labels. Existing methods for earth imagery segmentation often divide the imagery into patches and consider the elevation as an additional feature channel. These methods do not fully incorporate the spatial topological structural constraint within and across surface patches and thus often show poor results, especially when training labels are limited. Existing methods on semi-supervised and unsupervised learning for earth imagery often focus on learning representation without explicitly incorporating surface topology. In contrast, we propose a novel framework that explicitly models the topological skeleton of a terrain surface with a contour tree from computational topology, which is guided by the physical constraint (e.g., water flow direction on terrains). Our framework consists of two neural networks: a convolutional neural network (CNN) to learn spatial contextual features on a 2D image grid, and a graph neural network (GNN) to learn the statistical distribution of physics-guided spatial topological dependency on the contour tree. The two models are co-trained via variational EM. Evaluations on the real-world flood mapping datasets show that the proposed models outperform baseline methods in classification accuracy, especially when training labels are limited.

Handling of railway superstructure material at the end of the life cycle

This article deals with the recycling of railway bed aggregates. It briefly describes the methods of handling of the obtained material. It evaluates new possibilities of processing gravel from railway superstructure. It describes the development of the maintenance and reconstruction of railway lines. Furthermore, this article deals with the possibilities of using old materials for new purposes. It presents the results of analyzes of railway aggregate extracts and their comparison with the limit values for deposition on the terrain surface.

A Digital Terrain Modeling Method in Urban Areas by the ICESat-2 (Generating precise terrain surface profiles from photon-counting technology)

The ICE, Cloud and land Elevation Satellite-2 (ICES at-2) can provide new measurements of the Earth's elevations through photon-counting technology. Most research has focused on extracting the ground and the canopy photons in vegetated areas. Yet the extraction of the ground photons from urban areas, where the vegetation is mixed with artificial constructions, has not been fully investigated. This article proposes a new method to estimate the ground surface elevations in urban areas. The ICES at-2 signal photons were detected by the improved Density-Based Spatial Clustering of Applications with Noise algorithm and the Advanced Topographic Laser Altimeter System algorithm. The Advanced Land Observing Satellite-1 PALSAR –derived digital surface model has been utilized to separate the terrain surface from the ICES at-2 data. A set of ground-truth data was used to evaluate the accuracy of these two methods, and the achieved accuracy was up to 2.7 cm, which makes our method effective and accurate in determining the ground elevation in urban scenes.

The Impact of the Accuracy of Terrain Surface Data on the Navigation of Off-Road Vehicles

Current soil and surface data are not detailed enough to obtain accurate analyses of cross-country movement. The reason for the research presented in this article was the absence of a methodology for the synthetic assessment of the influence of the terrain surface on the movement of military vehicles. The study is based on analyses of data and information sources of soils and surface conditions primarily with the aim to determine their reliability, availability and precision when used for analyses of terrain traversability by off-road vehicles. The key method to achieve the set objective is the employment of tractive charts of military vehicles and utilized coefficients, the coefficient of rolling resistance and the coefficient of adhesion. Input data and information is tested with a comparative method of cross-country movement analyses. Conversion of soil and surface types to tractive chart coefficients is currently not optimal. For the most part, evaluation of soil type is very inaccurate with a wide range of possible values. Results of the analysis propose developing a methodology of evaluating surface and soils for vehicle traversability.

Prediction of Wide Range Two-Dimensional Refractivity Using an IDW Interpolation Method from High-Altitude Refractivity Data of Multiple Meteorological Observatories

This article proposes a method for the prediction of wide range two-dimensional refractivity for synthetic aperture radar (SAR) applications, using an inverse distance weighted (IDW) interpolation of high-altitude radio refractivity data from multiple meteorological observatories. The radio refractivity is extracted from an atmospheric data set of twenty meteorological observatories around the Korean Peninsula along a given altitude. Then, from the sparse refractive data, the two-dimensional regional radio refractivity of the entire Korean Peninsula is derived using the IDW interpolation, in consideration of the curvature of the Earth. The refractivities of the four seasons in 2019 are derived at the locations of seven meteorological observatories within the Korean Peninsula, using the refractivity data from the other nineteen observatories. The atmospheric refractivities on 15 February 2019 are then evaluated across the entire Korean Peninsula, using the atmospheric data collected from the twenty meteorological observatories. We found that the proposed IDW interpolation has the lowest average, the lowest average root-mean-square error (RMSE) of ∇M (gradient of M), and more continuous results than other methods. To compare the resulting IDW refractivity interpolation for airborne SAR applications, all the propagation path losses across Pohang and Heuksando are obtained using the standard atmospheric condition of ∇M = 118 and the observation-based interpolated atmospheric conditions on 15 February 2019. On the terrain surface ranging from 90 km to 190 km, the average path losses in the standard and derived conditions are 179.7 dB and 182.1 dB, respectively. Finally, based on the air-to-ground scenario in the SAR application, two-dimensional illuminated field intensities on the terrain surface are illustrated.