ATAmanda Tan

Amanda Tan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Amanda Tan has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    High-Resolution Snow-Covered Area Mapping in Forested Mountain Ecosystems Using PlanetScope Imagery

    by Aji John, Anthony F. Cannistra, Kehan Yang, Amanda Tan, David Shean, Janneke Hille Ris Lambers, Nicoleta Cristea

    Improving high-resolution (meter-scale) mapping of snow-covered areas in complex and forested terrains is critical to understanding the responses of species and water systems to climate change. Commercial high-resolution imagery from Planet Labs, Inc. (Planet, San Francisco, CA, USA) can be used in environmental science, as it has both high spatial (0.7–3.0 m) and temporal (1–2 day) resolution. Deriving snow-covered areas from Planet imagery using traditional radiometric techniques have limitations due to the lack of a shortwave infrared band that is needed to fully exploit the difference in reflectance to discriminate between snow and clouds. However, recent work demonstrated that snow cover area (SCA) can be successfully mapped using only the PlanetScope 4-band (Red, Green, Blue and NIR) reflectance products and a machine learning (ML) approach based on convolutional neural networks (CNN). To evaluate how additional features improve the existing model performance, we: (1) build on previous work to augment a CNN model with additional input data including vegetation metrics (Normalized Difference Vegetation Index) and DEM-derived metrics (elevation, slope and aspect) to improve SCA mapping in forested and open terrain, (2) evaluate the model performance at two geographically diverse sites (Gunnison, Colorado, USA and Engadin, Switzerland), and (3) evaluate the model performance over different land-cover types. The best augmented model used the Normalized Difference Vegetation Index (NDVI) along with visible (red, green, and blue) and NIR bands, with an F-score of 0.89 (Gunnison) and 0.93 (Engadin) and was found to be 4% and 2% better than when using canopy height- and terrain-derived measures at Gunnison, respectively. The NDVI-based model improves not only upon the original band-only model’s ability to detect snow in forests, but also across other various land-cover types (gaps and canopy edges). We examined the model’s performance in forested areas using three forest canopy quantification metrics and found that augmented models can better identify snow in canopy edges and open areas but still underpredict snow cover under forest canopies. While the new features improve model performance over band-only options, the models still have challenges identifying the snow under trees in dense forests, with performance varying as a function of the geographic area. The improved high-resolution snow maps in forested environments can support studies involving climate change effects on mountain ecosystems and evaluations of hydrological impacts in snow-dominated river basins.


  • Open Access

    Arctic-Boreal Lake Phenology Shows a Relationship between Earlier Lake Ice-Out and Later Green-Up

    by Catherine Kuhn, Aji John, Janneke Hille Ris Lambers, David Butman, Amanda Tan

    Satellite remote sensing has transformed our understanding of Earth processes. One component of the Earth system where large uncertainties remain are Arctic and boreal freshwater lakes. With only short periods of open water due to annual ice cover, lake productivity in these regions is extremely sensitive to warming induced changes in ice cover. At the same time, productivity dynamics in these lakes vary enormously, even over short distances, making it difficult to understand these potential changes. A major impediment to an improved understanding of lake dynamics has been sparsely distributed field measurements, in large part due to the complexity and expense of conducting scientific research in remote northern latitudes. This project overcomes that hurdle by using a new set of ‘eyes in the sky’, the Planet Labs CubeSat fleet, to observe 35 lakes across 3 different arctic-boreal ecoregions in western North America. We extract time series of lake reflectance to identify ice-out and green-up across three years (2017–2019). We find that lakes with later ice-out have significantly faster green-ups. Our results also show ice-out varies latitudinally by 38 days from south to north, but only varies across years by ~9 days. In contrast, green-up varied between years by 22 days in addition to showing significant spatial variability. We compare PlanetScope to Sentinel-2 data and independently validate our ice-out estimates, finding an ice-out mean absolute difference (MAD) ~9 days. This study demonstrates the potential of using CubeSat imagery to monitor the timing and magnitude of ice-off and green-up at high spatiotemporal resolution.


  • Open Access

    Detecting Montane Flowering Phenology with CubeSat Imagery

    by Aji John, Justin Ong, Elli J. Theobald, Julian D. Olden, Amanda Tan, Janneke HilleRisLambers

    Shifts in wildflower phenology in response to climate change are well documented in the scientific literature. The majority of studies have revealed phenological shifts using in-situ observations, some aided by citizen science efforts (e.g., National Phenology Network). Such investigations have been instrumental in quantifying phenological shifts but are challenged by the fact that limited resources often make it difficult to gather observations over large spatial scales and long-time frames. However, recent advances in finer scale satellite imagery may provide new opportunities to detect changes in phenology. These approaches have documented plot level changes in vegetation characteristics and leafing phenology, but it remains unclear whether they can also detect flowering in natural environments. Here, we test whether fine-resolution imagery (<10 m) can detect flowering and whether combining multiple sources of imagery improves the detection process. Examining alpine wildflowers at Mt. Rainier National Park (MORA), we found that high-resolution Random Forest (RF) classification from 3-m resolution PlanetScope (from Planet Labs) imagery was able to delineate the flowering season captured by ground-based phenological surveys with an accuracy of 70% (Cohen’s kappa = 0.25). We then combined PlanetScope data with coarser resolution but higher quality imagery from Sentinel and Landsat satellites (10-m Sentinel and 30-m Landsat), resulting in higher accuracy predictions (accuracy = 77%, Cohen’s kappa = 0.39). The model was also able to identify the timing of peak flowering in a particularly warm year (2015), despite being calibrated on normal climate years. Our results suggest PlanetScope imagery holds utility in global change ecology where temporal frequency is important. Additionally, we suggest that combining imagery may provide a new approach to cross-calibrate sensors to account for radiometric irregularity inherent in fine resolution PlanetScope imagery. The development of this approach for wildflower phenology predictions provides new possibilities to monitor climate change effects on flowering communities at broader spatiotemporal scales. In protected and tourist areas where the flowering season draws large numbers of visitors, such as Mt. Rainier National Park, the modeling framework presented here could be a useful tool to manage and prioritize park resources.


  • Open Access

    The Pangeo Platform: a community-driven open-source big data environment

    by Joseph Hamman, Scott Henderson, Anthony Arendt, Amanda Tan, Dennis Fatland, Andrew Pawloski, Daniel Pilone, Matthew Hanson, Tom Augspurger, Ryan Abernathey, et al.

    In this presentation, we will describe the [Pangeo Project](http://pangeo.io), a coordinated community effort with support from NASA, NSF, AWS, Microsoft Azure and Google Cloud, to develop interactive and reproducible open source workflows for discovery, visualization, and quantitative analysis of large datasets used for research in the Earth Sciences. The Pangeo computational platform is based on JupyterHub and deployed wherever the data is stored. Python libraries such as Xarray, Rasterio, and Dask enable distributed parallel computations on HPC and Kubernetes clusters. We will discuss the design concepts central to the Pangeo platform and highlight specific applications using NASA satellite data archives on AWS. We will discuss recent progress in the integration of data discovery tools (e.g. STAC, CMR, Intake) with cloud-native storage formats for multidimensional data types (Cloud-Optimized Geotiff, Zarr, etc.) and highlight how they can be used to construct elegant, robust and reproducible scientific workflows. Finally, we will discuss performance, security, transferability across public cloud platforms, cost to operate, and approaches to encourage a cultural shift in scientific computation through educational events.


  • Open Access

    Data science for urban equity: Making gentrification an accessible topic for data scientists, policymakers, and the community

    by Bernease Herman, Gundula Proksch, Rachel Berney, Hillary Dawkins, Jacob Kovacs, Yahui Ma, Jacob Rich, Amanda Tan

    The University of Washington eScience Institute runs an annual Data Science for Social Good (DSSG) program that selects four projects each year to train students from a wide range of disciplines while helping community members execute social good projects, often with an urban focus. We present observations and deliberations of one such project, the DSSG 2017 'Equitable Futures' project, which investigates the ongoing gentrification process and the increasingly inequitable access to opportunities in Seattle. Similar processes can be observed in many major cities. The project connects issues usually analyzed in the disciplines of the built environment, geography, sociology, economics, social work and city governments with data science methodologies and visualizations.