Samuel N Araya

Postdoctoral Research Fellow

Stanford University


I am a postdoctoral researcher working in Professor Scott Fendorf’s lab at Stanford University. I am interested in using machine learning and spatial analysis methods to address soil and environmental problems across scales.

My current research is focused on predicting subsurface soil biogeochemistry at landscape scale through machine learning assisted analysis of surface data. I am currently involved in two research projects. I’m involved in research aimed at deciphering arsenic concentrations within and impacts on rice using unmanned aircraft systems based remote sensing. I am also working on research aimed at determining the links between surface characteristics and subsurface biogeochemistry (particularly heavy metal transport and redox) in heavy metal contaminated floodplain environment in Riverton, Wyoming. More details are available on my projects.

I did my Ph.D. under Professor Teamrat Ghezzehei at the University of California, Merced Soil Physics group. My doctoral dissertation work was on linking soil structure and land surface characteristics with soil hydrology by using machine learning, unmanned aircraft systems, and observations from long-term conservation agriculture management.


  • Soil science
  • Machine learning
  • Spatial analysis


  • PhD in Environmental Systems, 2019

    University of California, Merced

  • MSc in Environmental Systems, 2014

    University of California, Merced

  • BSc in Land Resources and Environment, 2007

    Asmara University


R | Python | JavaScript

Machine Learning




Linking sub-subsurface biogeochemistry with surface observations

Using data science methods to understand sub-surface biogeochemistry from surface observations

Rice arsenic contamination from a drone

Arsenic detection in rice from drone images using machine learning

Machine Learning Pedotransfer

Unsaturated hydraulic conductivity pedotransfer using machine learning.

Long-term conservation agriculture impact on soil hydrology

Impact of long-term conservation agriculture on soil hydraulic properties and moisture storage

Soil moisture observation from a drone

High resolution soil moisture prediction from drone images using machine learning


  • 367 Panama Street, Stanford, CA, 94305, United States
  • Green Earth Sciences, Room 323