https://andrewsenogles.com/Andrew SenoglesPersonal portfolio and blog of Andrew Senogles 2023-04-05T15:41:07-07:00 Andrew Senogles https://andrewsenogles.com/ Jekyll © 2023 Andrew Senogles /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png LADI2023-04-05T12:00:00-07:00 2023-04-05T12:00:00-07:00 https://andrewsenogles.com/posts/ladi/ Andrew Senogles Landslides are a 4D problem varying across both space and time. At the present landslide monitoring solutions provide either high-spatial resolution data (such as remote-sensing methods), or high-temporal resolution data (such as in-situ monitoring data). I developed LADI (LAndslide Displacement Interpolation) as a method of performing high-spatial, high-temporal data fusion of remote-sensing a... SlideSim2022-06-18T12:00:00-07:00 2022-06-18T12:00:00-07:00 https://andrewsenogles.com/posts/slidesim/ Andrew Senogles I have recently been working on a new approach to measuring spatially dense 3D landslide displacement using lidar DEMs. By using simulation powered self-supervised learning, we can train a site specific optical flow predictor capable of accurately computing the dense 2D horizontal displacement. The vertical component of displacement can then be computed via a remapping technique. Overall, this ... SlidePy2022-06-04T12:00:00-07:00 2022-06-04T12:00:00-07:00 https://andrewsenogles.com/posts/slidepy/ Andrew Senogles I developed a fast, multithreaded python library for performing 3D landslide modelling and simulation. This was developed as part of my recent work to train optical flow predictors for landslide change detection using simulation powered self-supervised learning. However, the library could also potentially be used for modelling or back analysis of landslides. You can find the libraries github p... Faster Raster2022-03-13T12:00:00-07:00 2022-03-13T12:00:00-07:00 https://andrewsenogles.com/posts/fasterraster/ Andrew Senogles Recently, I’ve been working on developing self-supervised deep learning models for raster processing (specifically processing DEMs). Generating labelled training data as part of the self-supervised learning process involves the manipulation of 10s to 100s of thousands of rasters. In the Python ecosystem (which is currently the dominant language for developing deep learning methodologies) curren... Real-time landslide monitoring with GNSS2022-01-01T11:00:00-08:00 2022-01-01T11:00:00-08:00 https://andrewsenogles.com/posts/slide_detector/ Andrew Senogles I designed, developed, built, and deployed a network of real-time RTK-GNSS sensors for monitoring two landslides on the Oregon Coast. A demo, which includes access to real-time data over the previous 24 hours is available at the following webpage.