Matthew J Cashman, Ph.D.

Matthew's research interests are in the interdisciplinary interactions between surface water hydrology, geomorphology, and ecology, particularly as it relates to habitat conditions. His current work primarily focuses on regional and national water availability and ecological assessments, with an emphasis on detangling the impact of multiple, co-occurring stressors. 

​He approaches problems through leveraging big-data, machine-learning, custom application development, and the use of causal inference statistical techniques to quantify causal effects in complex, multi-stressor environments. 

​His previous work has involved machine-learning modeling of ecological and habitat conditions, geomorphic and habitat trend analysis via analysis of gage data, paleoecological reconstruction of river corridors, erosion and habitat mapping using Unmanned Aerial Systems and lidar, developing tools to identify the sources of sediment degrading river habitat, including sediment fingerprinting, restoration monitoring, detection of harmful algal blooms with remote sensing, and the development of cloud-based automated deep learning tools to assist in the maintenance and detection of sensor anomalies at USGS continuous water quality stations.