Dr. Karen Chen’s recent publication as co-lead author is featured in UW News in a story entitled “Q&A: UW-led research identifies migration, housing quality as risk factors in earthquake deaths.” Dr. Chen is an assistant professor in the department of Urban Design & Planning. Read more here.
Person: Tzu-Hsin Karen Chen
Identifying recurrent and persistent landslides using satellite imagery and deep learning: A 30-year analysis of the Himalaya
Tzu-Hsin Karen Chen, Mark E. Kincey, Nick J. Rosser, Karen C. Seto, Identifying recurrent and persistent landslides using satellite imagery and deep learning: A 30-year analysis of the Himalaya, Science of The Total Environment, Volume 922, 2024, 171161, ISSN 0048-9697, https://doi.org/10.1016/j.scitotenv.2024.171161.
Abstract
This paper presents a remote sensing-based method to efficiently generate multi-temporal landslide inventories and identify recurrent and persistent landslides. We used free data from Landsat, nighttime lights, digital elevation models, and a convolutional neural network model to develop the first multi-decadal inventory of landslides across the Himalaya, spanning from 1992 to 2021. The model successfully delineated >265,000 landslides, accurately identifying 83 % of manually mapped landslide areas and 94 % of reported landslide events in the region. Surprisingly, only 14 % of landslide areas each year were first occurrences, 55–83 % of landslide areas were persistent and 3–24 % had reactivated. On average, a landslide-affected pixel persisted for 4.7 years before recovery, a duration shorter than findings from small-scale studies following a major earthquake event. Among the recovered areas, 50 % of them experienced recurrent landslides after an average of five years. In fact, 22 % of landslide areas in the Himalaya experienced at least three episodes of landslides within 30 years. Disparities in landslide persistence across the Himalaya were pronounced, with an average recovery time of 6 years for Western India and Nepal, compared to 3 years for Bhutan and Eastern India. Slope and elevation emerged as significant controls of persistent and recurrent landslides. Road construction, afforestation policies, and seismic and monsoon activities were related to changes in landslide patterns in the Himalaya.
Keywords
Landslide inventory; Landslide evolution; Vegetation recovery; Multi-temporalSpatiotemporal analysis; Machine learning
Assistant Professor Karen Chen awarded NASA early career investigator award
Assistant Professor Karen Chen is awarded the NASA early career investigator award for the program in earth science. Chen’s project will explore heat impacts on health in urban settings in the Mediterranean. Chen is also affiliated with the Department of Environmental and Occupational Health, and CSDE at UW. Read more here.
Detecting Subpixel Human Settlements in Mountains Using Deep Learning: A Case of the Hindu Kush Himalaya 1990–2020
Chen, T.-H. K., Pandey, B., & Seto, K. C. (2023). Detecting subpixel human settlements in mountains using deep learning: A case of the Hindu Kush Himalaya 1990–2020. Remote Sensing of Environment, 294, 113625–. https://doi.org/10.1016/j.rse.2023.113625
Abstract
The majority of future population growth in mountains will occur in small- and medium-sized cities and towns and affect vulnerable ecosystems. However, mountain settlements are often omitted from global land cover analyses due to the low spatial resolution of satellite images, which cannot resolve the small scale of mountains settlements. This study demonstrates, for the first time, the potential of deep learning to detect human settlements in mountains at the sub-pixel level, based on Landsat satellite imagery. We hypothesized that adding spatial and temporal features could improve the detection of mountain settlements since spectral information alone led to inaccurate results. For spatial features, we compared a U-shaped neural network (U-Net), a deep learning algorithm that automatically learns spatial features, with a simple random forest (RF) algorithm. Then, we assessed whether temporal features would increase accuracy by comparing two input datasets, multispectral imagery and temporal features from the Continuous Change Detection and Classification (CCDC) algorithm. We evaluated each method by calculating the accuracies of (1) the binary settlement footprint, (2) the subpixel estimates of impervious surfaces, and (3) urban growth. We tested the accuracies using visually interpreted datasets from time-series Google Earth images across the Hindu Kush Himalaya that were not used for training to evaluate model transferability. The U-Net successfully improved mountain settlement mapping compared to the random forest, with a substantial discrepancy in small settlements. The time-series results from the U-Net successfully captured long-term urban growth but fewer short-term changes. Contrary to expectations, the CCDC temporal features reduced the accuracy of mountain settlement mapping due to frequent cloud cover in hilly areas. Our subpixel analysis reveals that the built-up area of the Hindu Kush Himalaya has expanded at a rate of 61 km2 per year from 1990 to 2020, which is about twice the estimate of the Global Human Settlement Layer using binary urban/non-urban classifications.
Keywords
Urban land cover; Land cover fraction; Peri-urban; Built-up area; Subpixel mapping; Machine learning; Time-series; Himalaya; CCDC
Higher Depression Risks in Medium- Than in High-Density Urban Form Across Denmark
Chen, T.-H. K., Horsdal, H. T., Samuelsson, K., Closter, A. M., Davies, M., Barthel, S., Pedersen, C. B., Prishchepov, A. V., & Sabel, C. E. (2023). Higher depression risks in medium- than in high-density urban form across Denmark. Science Advances, 9(21), eadf3760–eadf3760. https://doi.org/10.1126/sciadv.adf3760
Abstract
Urban areas are associated with higher depression risks than rural areas. However, less is known about how different types of urban environments relate to depression risk. Here, we use satellite imagery and machine learning to quantify three-dimensional (3D) urban form (i.e., building density and height) over time. Combining satellite-derived urban form data and individual-level residential addresses, health, and socioeconomic registers, we conduct a case-control study (n = 75,650 cases and 756,500 controls) to examine the association between 3D urban form and depression in the Danish population. We find that living in dense inner-city areas did not carry the highest depression risks. Rather, after adjusting for socioeconomic factors, the highest risk was among sprawling suburbs, and the lowest was among multistory buildings with open space in the vicinity. The finding suggests that spatial land-use planning should prioritize securing access to open space in densely built areas to mitigate depression risks.
Tzu-Hsin Karen Chen
UW Department of Urban Design and Planning in the College of Built Environments.