Related Experiment Video
Updated: Oct 3, 2025
08:09
Measuring and Mapping Patterns of Soil Erosion and Deposition Related to Soil Carbonate Concentrations Under Agricultural Management
Published on: September 12, 2017
11.9K
Assessing the contemporary status of Nebraska's eastern saline wetlands by using a machine learning algorithm on the
Ligang Zhang1, Qiao Hu1, Zhenghong Tang2
1School of Natural Resources, University of Nebraska-Lincoln, Lincoln, NE, 68583-0961, USA.
Environmental Monitoring and Assessment
|February 16, 2022
Summary
Nebraska
Area of Science:
- Ecology
- Remote Sensing
- Machine Learning
Background:
- Eastern Nebraska's saline wetlands are globally unique and vulnerable inland salt marshes.
- These ecosystems require continuous monitoring to inform conservation efforts.
Purpose of the Study:
- To evaluate the status of saline wetlands in eastern Nebraska.
- To assess wetland hydrology, hydrophytes (vegetation), and soil salinity conditions.
Main Methods:
- Utilized machine learning and Google Earth Engine for image classification.
- Classified Sentinel-2 imagery for water and vegetation, and NAIP imagery for salinity.
- Applied and compared six machine learning models for detection tasks.
Main Results:
- Achieved high accuracy in water (99.95%) and vegetation (94.07%) classification using optimal models.
- Saline soil classification accuracy varied annually; soil area fluctuated with water and vegetation.
- Identified consistent annual water cover patterns and peak vegetation season (June-July).
Conclusions:
- Demonstrated the feasibility of an observational approach for continuous monitoring of these wetlands.
- Provided scientific data crucial for informed conservation decision-making for Nebraska's saline wetlands.
