I'd like to try machine learning / computer vision / deep learning approaches for detecting artifacts in Digital Surface Models, and am specifically interested in doing this for common artifacts like spikes and craters. So far, I haven't found very helpful research papers or datasets for this, and am looking for any pointers related to this.
Edit: I'm unable to directly share data or direct examples since the data is proprietary and I don't have permission to share it, and also because it's (largely) unlabeled. Some links that could provide more context/examples of what I'm trying to do:
"Errors in DEMs are usually classified as either sinks or peaks. A sink is an area surrounded by higher elevation values and is also referred to as a depression or pit. This is an area of internal drainage. Some of these may be natural, particularly in glacial or karst areas (Mark 1988), although many sinks are imperfections in the DEM. Likewise, a spike, or peak, is an area surrounded by cells of lower value. These are more commonly natural features and are less detrimental to the calculation of flow direction." - source