The rectangular tile classification model based on Sentinel integrated images enhances grassland mapping accuracy: A
Fuchen Guo1, Liangxin Fan1,2, Weinan Chen3
1School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, Henan, China.
Plos One
|April 16, 2024
Summary
Mapping arid zone grasslands is challenging due to diverse landscapes. A new rectangular tile model using Sentinel-1A and Sentinel-2 data significantly improved grassland mapping accuracy, outperforming traditional methods.
Area of Science:
- Remote Sensing
- Ecology
- Geospatial Analysis
Background:
- Arid zone grasslands are vital for ecosystem health and soil stability.
- Accurate spatial mapping of these grasslands is difficult due to spectral variability in diverse landscapes.
- Existing remote sensing methods struggle with the complexity of arid zone environments.
Purpose of the Study:
- To enhance the accuracy of grassland mapping in arid and semi-arid regions using integrated satellite imagery.
- To evaluate the effectiveness of a novel rectangular tile classification model compared to traditional global models.
- To identify optimal data synthesis strategies for combining radar and optical satellite data.
Main Methods:
- Utilized Sentinel-1A (radar) and Sentinel-2 (optical) imagery for grassland mapping.
- Developed a rectangular tile classification model incorporating the random forest algorithm.
- Synthesized monthly Sentinel-1A data and used MODIS vegetation indices to determine optimal Sentinel-2 image synthesis windows.
- Compared the rectangular tile model with a traditional global classification model across multiple experimental schemes.
Main Results:
- The integration of Sentinel-1A and Sentinel-2 data, along with vegetation and texture features, significantly improved grassland mapping accuracy.
- The best performing scheme (EXP7-2) achieved an overall accuracy of 88.23%, surpassing single-sensor accuracies (Sentinel-1A: 53.52%, Sentinel-2: 86.53%).
- The rectangular tile classification model consistently improved overall accuracy by 1.20% to 13.99% over the global classification model in all experimental groups.
Conclusions:
- The rectangular tile classification model, combined with multi-sensor satellite data, offers a robust solution for accurate grassland mapping in complex arid landscapes.
- This approach provides a flexible and scalable framework, adaptable for various locations and time periods within the Google Earth Engine.
- The study offers valuable guidance for improving land cover classification accuracy in challenging remote sensing applications.
Related Concept Videos
01:25Selected Data About Geographic Locations
27
Geographic Information Systems (GIS) rely on two core types of data: spatial data and attribute data.Spatial DataSpatial data defines the physical location of features within a coordinate system, typically expressed in terms of latitude and longitude. It provides precise positioning for elements like roads, rivers, or buildings.Attribute DataAttribute data complements spatial data by adding descriptive information about these features. For example, a road's spatial data includes its start and...
27
01:30Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
28
Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point...
28