Graduate Thesis Or Dissertation
 

Predicting the spatial variability in soil properties using DSM across Malheur National Forest

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/zs25xb871

Descriptions

Attribute NameValues
Creator
Abstract
  • Soil properties may hold the key to improved predictions of soils during digital soil mapping (DSM), which has developed with a focus on environmental factors external to soil. The spatial variability in soil properties was modeled across Malheur National Forest in eastern Oregon as an approach to improve DSM. The resulting preliminary maps are to be used as a potential source of information to support soil survey efforts in the region. Soil properties predicted using DSM included surface and subsurface soil pH, cation exchange capacity (CEC), base saturation, organic matter content, and percent clay content. A Random Forest (RF) classification model, a data mining algorithm that uses many rule-based decision trees to generate predictions, was used to generate predictive maps for each of the listed soil properties from a limited training dataset. Regression kriging was also attempted using the same dataset, but the distribution and density of sample locations made for a more complicated process and the procedure was only successful when applied to log-transformed subsurface organic matter content data in a smaller area within the forest. Random Forest classification models of soil pH, organic matter content, clay content, and CEC performed reasonably well, although the models could not reliably predict base saturation variability. However, the RF modeling process provides a place to begin determining new avenues for improving our understanding of how soil properties vary across the landscape, and the resulting predictive maps highlight areas in the region that should be more heavily sampled during future soil survey mapping.
License
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Replaces

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details SeenoElizabethA2016.pdf 2017-08-07 Public Download