Title | Detecting landscape changes in high latitude environments using Landsat trend analysis: 2. classification |
| |
Author | Olthof, I; Fraser, R H |
Source | Remote Sensing vol. 6, issue 11, 2014 p. 11558-11578, https://doi.org/10.3390/rs61111558 Open Access |
Image |  |
Year | 2014 |
Alt Series | Natural Resources Canada, Contribution Series 20190181 |
Publisher | MDPI AG |
Document | serial |
Lang. | English |
Media | paper; on-line; digital |
Related | This publication is related to Detecting landscape changes
in high latitude environments using Landsat trend analysis: 1. visualization |
File format | pdf (Adobe® Reader®); html |
Province | Northwest Territories |
NTS | 75; 85; 95; 86; 96; 97; 105; 106; 107; 115; 116; 117 |
Lat/Long WENS | -140.0000 -110.0000 70.0000 60.0000 |
Subjects | environmental geology; hydrogeology; regional geology; LANDSAT; LANDSAT imagery; environmental studies; environmental impacts; fires |
Illustrations | location maps; Landsat images; schematic diagrams; graphs; photographs; aerial photographs |
Program | Remote Sensing Science |
Released | 2014 11 20 |
Abstract | Mapping landscape dynamics is necessary to assess cumulative impacts due to climate change and development in Arctic regions. Landscape changes produce a range of temporal reflectance trajectories that
can be obtained from remote sensing image time-series. Mapping these changes assumes that their trajectories are unique and can be characterized by magnitude and shape. A companion paper in this issue describes a trajectory visualization method for
assessing a range of landscape disturbances. This paper focusses on generating a change map using a time-series of calibrated Landsat Tasseled Cap indices from 1985 to 2011. A reference change database covering the Mackenzie Delta region was created
using a number of ancillary datasets to delineate polygons describing 21 natural and human-induced disturbances. Two approaches were tested to classify the Landsat time-series and generate change maps. The first involved profile matching based on
trajectory shape and distance, while the second quantified profile shape with regression coefficients that were input to a decision tree classifier. Results indicate that classification of robust linear trend coefficients performed best. A final
change map was assessed using bootstrapping and cross-validation, producing an overall accuracy of 82.8% at the level of 21 change classes and 87.3% when collapsed to eight underlying change processes. |
Summary | (Plain Language Summary, not published) This paper presents a comparison of methods to classify change processes in the Mackenzie Delta region, NWT for the Cumulative Impacts Monitoring Program
(CIMP). Examples of change processes include erosion, fire, regeneration, succession and development, among others. Landsat time-series reflectance trajectories are classified using a number of different curve matching techniques based on distance
and shape similarity. A product is generated and validated using a reference change database that was developed from ancillary information. The method and product are intended to allow historical cumulative environmental impact assessment from
Landsat due to natural and anthropogenic causes. |
GEOSCAN ID | 315349 |
|
|