Bio

Luwen is a Postdoctoral Fellow with the Stanford Institute for Human-Centered Artificial Intelligence, working with Dr. Kate Maher, Professor at Stanford University in the Department of Earth System Science. Her postdoctoral research focuses on developing tools for tracking the recovery and activity of the North American beaver from a computer version and evaluating beaver as a tool for fostering sustainable waterways. She received her Ph.D. in Earth and Environmental Science from Michigan State University, where she worked on nutrient transport modeling across the Great Lakes Basin and agricultural tile drainage mapping across the US Midwest region.

Institute Affiliations

Honors & Awards

  • HAI Postdoctoral Fellowship, Stanford Institute for Human-Centered Artificial Intelligence (2023)
  • Dissertation Completion Fellowship, Michigan State University (2022)
  • The best student presentation in the Session, AGU Fall 2021 Meeting (2021)
  • KBS LTER Summer Research Fellowship, KBS LTER (2021)
  • Lucile Drake Pringle and Gordon H. Pringle Endowed Fellowship, EES, Michigan State University (2020)

Stanford Advisors

Contact

  • Academic
    luwenwan@stanford.edu
    University - Scholar Department: Department of Earth System Science Position: Postdoctoral Scholar

Additional Info

Links

All Publications

  • Mapping agricultural tile drainage in the US Midwest using explainable random forest machine learning and satellite imagery. The Science of the total environment Wan, L., Kendall, A. D., Rapp, J., Hyndman, D. W. 2024: 175283

    Abstract

    There has been an increase in tile drained area across the US Midwest and other regions worldwide due to agricultural expansion, intensification, and climate variability. Despite this growth, spatially explicit tile drainage maps remain scarce, which limits the accuracy of hydrologic modeling and implementation of nutrient reduction strategies. Here, we developed a machine-learning model to provide a Spatially Explicit Estimate of Tile Drainage (SEETileDrain) across the US Midwest in 2017 at a 30-m resolution. This model used 31 satellite-derived and environmental features after removing less important and highly correlated features. It was trained with 60,938 tile and non-tile ground truth points within the Google Earth Engine cloud-computing platform. We also used multiple feature importance metrics and Accumulated Local Effects to interpret the machine learning model. The results show that our model achieved good accuracy, with 96 % of points classified correctly and an F1 score of 0.90. When tile drainage area is aggregated to the county scale, it agreed well (r2 = 0.69) with the reported area from the Ag Census. We found that Land Surface Temperature (LST) along with climate- and soil-related features were the most important factors for classification. The top-ranked feature is the median summer nighttime LST, followed by median summer soil moisture percent. This study demonstrates the potential of applying satellite remote sensing to map spatially explicit agricultural tile drainage across large regions. The results should be useful for land use change monitoring and hydrologic and nutrient models, including those designed to achieve cost-effective agricultural water and nutrient management strategies. The algorithms developed here should also be applicable for other remote sensing mapping applications.

    View details for DOI 10.1016/j.scitotenv.2024.175283

    View details for PubMedID 39111449

  • Important Role of Overland Flows and Tile Field Pathways in Nutrient Transport. Environmental science & technology Wan, L., Kendall, A. D., Martin, S. L., Hamlin, Q. F., Hyndman, D. W. 2023

    Abstract

    Nitrogen and phosphorus pollution is of great concern to aquatic life and human well-being. While most of these nutrients are applied to the landscape, little is known about the complex interplay among nutrient applications, transport attenuation processes, and coastal loads. Here, we enhance and apply the Spatially Explicit Nutrient Source Estimate and Flux model (SENSEflux) to simulate the total annual nitrogen and phosphorus loads from the US Great Lakes Basin to the coastline, identify nutrient delivery hotspots, and estimate the relative contributions of different sources and pathways at a high resolution (120 m). In addition to in-stream uptake, the main novelty of this model is that SENSEflux explicitly describes nutrient attenuation through four distinct pathways that are seldom described jointly in other models: runoff from tile-drained agricultural fields, overland runoff, groundwater flow, and septic plumes within groundwater. Our analysis shows that agricultural sources are dominant for both total nitrogen (TN) (58%) and total phosphorus (TP) (46%) deliveries to the Great Lakes. In addition, this study reveals that the surface pathways (sum of overland flow and tile field drainage) dominate nutrient delivery, transporting 66% of the TN and 76% of the TP loads to the US Great Lakes coastline. Importantly, this study provides the first basin-wide estimates of both nonseptic groundwater (TN: 26%; TP: 5%) and septic-plume groundwater (TN: 4%; TP: 2%) deliveries of nutrients to the lakes. This work provides valuable information for environmental managers to target efforts to reduce nutrient loads to the Great Lakes, which could be transferred to other regions worldwide that are facing similar nutrient management challenges.

    View details for DOI 10.1021/acs.est.3c03741

    View details for PubMedID 37871005

  • Forming the Future of Agrohydrology EARTHS FUTURE Smidt, S. J., Haacker, E. K., Bai, X., Cherkauer, K., Choat, B., Crompton, O., Deines, J. M., Groh, J., Guzman, S. M., Hartman, S., Kendall, A. D., Safeeq, M., Kustas, W., McGill, B. M., Nocco, M. A., Pensky, J., Rapp, J., Schreiner-Mcgraw, A., Sprenger, M., Wan, L., Weldegebriel, L., Zipper, S., Zoccatelli, D. 2023; 11 (12)

    View details for DOI 10.1029/2022EF003410

    View details for Web of Science ID 001118948500001

  • Making China’s water data accessible, usable and shareable Nature Water Lin, J., Bryan, B. ., Zhou, X., Lin, P., Do, H. X., Gao, L., Gu, X., Liu, Z., Wan, L., Tong, S., Huang, J., Wang, Q., Zhang, Y., Gao, H., Yin, J., Chen, Z., Duan, W., Xie, Z., Cui, T., Liu, J., Li, M., Li, X., Xu, Z., Guo, F., Shu, L. 2023

    View details for DOI 10.1038/s44221-023-00039-y

  • The land use legacy effect: looking back to see a path forward to improve management ENVIRONMENTAL RESEARCH LETTERS Martin, S. L., Hamlin, Q. F., Kendall, A. D., Wan, L., Hyndman, D. W. 2021; 16 (3)

    View details for DOI 10.1088/1748-9326/abe14c

    View details for Web of Science ID 000619147800001

  • The effects of landscape pattern evolution on runoff and sediment based on SWAT model ENVIRONMENTAL EARTH SCIENCES Zhang, Z., Chen, S., Wan, L., Cao, J., Zhang, Q., Yang, C. 2021; 80 (1)

    View details for DOI 10.1007/s12665-020-09315-6

    View details for Web of Science ID 000606914700001

  • Impacts of international trade on global sustainable development NATURE SUSTAINABILITY Xu, Z., Li, Y., Chau, S. N., Dietz, T., Li, C., Wan, L., Zhang, J., Zhang, L., Li, Y., Chung, M., Liu, J. 2020; 3 (11): 964-971

    View details for DOI 10.1038/s41893-020-0572-z

    View details for Web of Science ID 000548446500002

  • Spatially explicit quantification of the interactions among ecosystem services LANDSCAPE ECOLOGY Li, Y., Zhang, L., Qiu, J., Yan, J., Wan, L., Wang, P., Hu, N., Cheng, W., Fu, B. 2017; 32 (6): 1181-1199

    View details for DOI 10.1007/s10980-017-0527-6

    View details for Web of Science ID 000401663900005

https://orcid.org/0000-0002-6414-4500