I work at the intersection of machine learning, remote sensing, and ecology to understand our functioning natural environment. The ability to capture high temporal, spatial, and spectral resolution imagery has advanced much more rapidly than algorithms for processing, visualizing, and interpreting these images. In my work, I aim to develop algorithms and methodologies for image processing that transform the data into manageable and applicable information for future applications. Additionally, monitoring ecosystem function with high resolution over large spatial scale is extremely difficult due to the inherent cost and complexity managing ground-based operations and sensors. To overcome these challenges, I use computational spatial methods to characterize the vegetation function and the effect of physiology on the optical and thermal properties of plants. 

Office hours

• Tuesdays and Thursdays between 3:00 p.m. and 4:30 p.m.
• By appointment

Research interests

• Remote sensing
• Machine learning
• Terrestrial ecology

Prospective graduate students

I am looking for 1-2 MA or PhD students who are interested in developing remote sensing methodologies and machine learning algorithms for quantifying ecosystem response. Some areas of research could include:

• Mapping vegetation and monitoring seasonal changes in vegetation
• Measuring vegetation response to disturbances such as drought
• Developing algorithms and methodologies for image processing that transform the data into manageable and applicable information
• Exploring synergies between optical, thermal, and active remote sensing data sources

In addition to the above research interests, students should have, or be interested in developing, skills in programming/statistical computing (in MATLAB, Python, R, etc.), remote sensing, GIS, ecology.

Selected publications

• Kibler, C. L., Parkinson, A. L., Peterson, S. H., Roberts, D. A., Antonio, C. M. D., Meerdink, S. K., & Sweeney, S. H. (2019). Monitoring post-fire recovery of chaparral and conifer species using field surveys and Landsat time series. Remote Sensing, 11(2963), 1–25. https://doi.org/10.3390/rs11242963 Open Access
• Dennison, P. E., Qi, Y., Meerdink, S. K., Kokaly, R. F., Thompson, D. R., Daughtry, C. S. T., Quemada, M., Roberts, D.A., Gader, P.D., Wetherley, E.B., Numata, I., & Roth, K. L. (2019). Comparison of methods for modeling fractional cover using simulated satellite hyperspectral imager spectra. Remote Sensing, 11(2072), 1–23. https://doi.org/10.3390/rs11182072
• Meerdink, S.K., Roberts, D.A., Roth, K.L., King, J.Y., Gader, P.D., & Koltunov, A. (2019). Classifying California plant species temporally using airborne hyperspectral imagery. Remote Sensing of Environment, 232, 111308. https://doi.org/10.1016/j.rse.2019.111308
• Meerdink, S. K., Hook, S. J., Roberts, D. A., & Abbott, E. A. (2019). The ECOSTRESS spectral library version 1.0. Remote Sensing of Environment, 230(111196), 1–8. https://doi.org/10.1016/j.rse.2019.05.015
• Meerdink, S.K., Roberts, D. A., Hulley, G., Pisek, J., Raabe, K., King, J., & Hook, S. J. (2019). Plant species’ spectral emissivity and temperature using the Hyperspectral Thermal Emission Spectrometer (HyTES) sensor. Remote Sensing of Environment, 224, 421–435. https://doi.org/10.1016/j.rse.2019.02.009
• Roberts, D.A., Roth, K.L, Wetherley, E.B., Meerdink, S.K., & Perroy, R.L. (2018). Chapter 1: Hyperspectral Vegetation Indices, in: Hyperspectral Remote Sensing of Vegetation. 
• Meerdink, S. K., Roberts, D. A., King, J. Y., Roth, K. L., Dennison, P. E., Amaral, C. H., & Hook, S. J. (2016). Linking seasonal foliar traits to VSWIR-TIR spectroscopy across California ecosystems. Remote Sensing of Environment, 186, 322-338. http://dx.doi.org/10.1016/j.rse.2016.08.003

View CV

View publications