Answers are grounded in this paper and cite their sources.
The completion of the Five‐hundred‐metre Aperture Spherical radio Telescope (FAST) has demonstrated the advantages of utilizing large natural depressions for astronomical facility siting in karst regions. However, efficiently and automatically identifying terrain‐morphological candidates for FAST‐type installations remains challenging in geomorphological and geospatial analyses, especially in highly fragmented and scale‐variable karst terrains. In this study, we develop an AI‐oriented, knowledge‐guided DEM‐based framework that integrates multi‐scale spherical‐cap template matching with multidimensional computer‐vision similarity assessment. Spherical‐cap DEM templates at multiple scales are matched to real terrain using a sliding‐window scheme and similarity is quantified using Pearson correlation, structural similarity index measure (SSIM) and mutual information (MI). Depth thresholds, area–depth ratios and local‐minima conditions, combined with spatial clustering, are applied to extract representative depressions. When applied to a typical karst region in Southwest China, the method identified 245 depressions with composite matching scores above 0.70, which cluster at mid‐elevations (800–1500 m) and show strong spatial associations with regional fault zones. High‐scoring depressions generally exhibit high circularity, low edge‐relief variability and geometrically regular outlines, indicating favourable terrain‐morphological conditions for preliminary FAST‐type candidate screening. Further analyses suggest potential linkages among depression size, morphometric attributes, lithological assemblages, structural setting and hydrogeomorphic evolution. Overall, this study provides an efficient, interpretable and transferable DEM‐based workflow for terrain‐based preliminary screening of FAST‐type karst depressions. The identified depressions should be regarded as geomorphological candidates rather than final engineering sites, because practical FAST‐type site selection also requires further evaluation of geological stability, transportation accessibility, meteorological conditions, hydrological safety, electromagnetic environment and construction feasibility.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: