| Title | Influence of sample distribution and prior probability adjustment on land cover classification
|
| Download | Downloads |
| |
| Licence | Please note the adoption of the Open Government Licence - Canada
supersedes any previous licences. |
| Author | Pouliot, D; Latifovic, R; Parkinson, W |
| Source | Geomatics Canada, Open File 23, 2016, 13 pages, https://doi.org/10.4095/297517  Open Access |
| Year | 2016 |
| Publisher | Natural Resources Canada |
| Document | open file |
| Lang. | English |
| Media | on-line; digital |
| File format | pdf |
| Province | Alberta |
| NTS | 74D; 74E; 84A; 84H |
| Area | Fort McMurray; Athabasca River |
| Lat/Long WENS | -114.0000 -110.0000 58.0000 56.0000 |
| Subjects | geophysics; mathematical and computational geology; modelling; analytical methods; LANDSAT; landform classification |
| Illustrations | satellite images; plots |
| Program | Remote Sensing Science |
| Released | 2016 01 28 |
| Abstract | Machine learning algorithms are widely used for remote sensing land surface characterization. Successful implementation requires a representative training sample for the domain it will applied in (i.e.
area of interest or validation domain). However, accessibility and cost strongly limit the acquisition of suitable training samples for large regional applications. Further, it is often desirable to use previously developed datasets where significant
resources have been invested, such as data developed from extensive field survey or high resolution remotely sensed imagery. These data often only partially represent the domain of interest and can lead to various forms of sample bias (land cover
distribution or class properties). Classifier spatial extension is an extreme case, where a sample is trained from one region (i.e. sample domain) and applied in another (i.e. application domain). This approach is desirable from a cost perspective,
but achieving acceptable accuracy is often difficult. In this research we investigate two approaches to account for possible differences between the sample and application domain land cover distributions. The first is an iterative resampling approach
to predict the application distribution and adjust the sample distribution to match. The second is the use of prior probabilities to adjust class memberships. Results reinforce the importance of the land cover distribution on accuracy for algorithms
that are designed to minimize the classification error with training data. Of the adjustments methods tested resampling was superior if the application domain distribution was well known. However, if it is not then the use of prior probabilities
performed similarly overall. A generic model was developed to predict if resampling or prior adjustment should be applied to enhance accuracy. |
| Summary | (Plain Language Summary, not published)
Open file is a technical document examining the role of sampling and correction mechanisms to sampling for enhancement of land cover mapping from remote
sensing data using machine learning algorithms that seek to minimize the training data error. |
| GEOSCAN ID | 297517 |
|
|