Digital Classification of LANDAST TM for Land Cover Mapping of the Pa Wang Phloeng-Khom-Lam Narai National Forest Reserve,
Lop Buri Province, Thailand
Results and Discussions
The Supervised Classification Approach
A total of 10 resource classes were identified based on the supervised classification scheme. Table 2 below show the area and percentage distribution of each resource class.
Table 2. Resource Classes from Supervised Classification.
| |
Resource Class |
Area (in hectares) |
% |
| 1. |
Paddy fields |
1,447.38 |
18.83 |
| 2. |
Cropland |
893.94 |
11.62 |
| 3. |
Tree plantation |
514.50 |
7.09 |
| 4. |
Bareland |
235.26 |
3.06 |
| 5. |
Grassland |
915.12 |
11.91 |
| 6. |
Shrubs |
259.83 |
3.38 |
| 7. |
Bushland |
989.28 |
12.87 |
| 8. |
Forest |
1,449.50 |
18.86 |
| 9. |
Mixed vegetation |
936.00 |
12.18 |
| 10. |
Water bodies |
14.49 |
0.19 |
| |
Total |
7,684.74 |
|
The Unsupervised Classification Approach
In the unsupervised classification approach, spectrally separable classes are first determined and their informational utility is then defined. Clustering algorithms are used to determine the natural spectral groupings present in a data set. The basic premise is that values within a given cover type should come close together in measurement of space, whereas data in different classes should also be well separated (lillesand and Kiefer, 1987)
For this study, the sequential method for clustering was employed, and the classification results, based on the final 12 resource classes are shown in Table 3 below. The Table shows the spectral classes represented from the clustering method for unsupervised classification and its corresponding area-wise distribution.
Table 3. Representations of the Spectral Classes from Unsupervised Clustering.
| |
Resource Class |
Area (in hectares) |
% |
| 1. |
Paddy Field |
1,171.53 |
16.24 |
| 2. |
Newly-planted cropland |
504.18 |
5.56 |
| 3. |
Older Cropland |
239.22 |
3.11 |
| 4. |
Tree plantations |
542.52 |
7.06 |
| 5. |
Bareland (upland) |
301.23 |
3.92 |
| 6. |
Bareland (lowland) |
347.85 |
4.53 |
| 7. |
Grassland |
654.93 |
8.52 |
| 8. |
Shrubs |
382.41 |
4.98 |
| 9. |
Bushland |
993.87 |
12.93 |
| 10. |
Forest |
1,363.23 |
17.74 |
| 11. |
Water bodies |
20.16 |
0.26 |
| 12. |
Mixed vegetation |
1,163.61 |
15.14 |
| |
Total |
7,681.74 |
|
The Modified Clustering Classification Approach
This approach, commonly termed hybrid classification, involves elements of both unsupervised and supervised analysis. A hybrid classifier is on which incorporates two or more decision rules (Mather, 1987) such as the independent clustering of the pixels (unsupervised method) which are then subject to analysis for spectral separability and normality (supervised method). Five training areas were statistically clustered into 100 spectrally separate clusters and an evaluation of the statisics of the signatures derived from each cluster was performed. The final Classification using Maximum likelihood classifier shows the results in the Table 4 which presents the area distribution and percentage of various resource classes that have been identified.
Table 4. Area Distribution Derived from the Modified Clustering Approach.
| |
Resource class |
Area (in hectares) |
% |
| 1. |
Paddy Field |
1,538.82 |
20.02 |
| 2. |
Newly-planted cropland |
675.99 |
8.80 |
| 3. |
Older Cropland |
228.15 |
2.97 |
| 4. |
Tree plantations |
533.16 |
6.94 |
| 5. |
Bareland |
651.78 |
8.48 |
| 6. |
Grassland |
602.64 |
7.84 |
| 7. |
Shrubs |
410.31 |
5.34 |
| 8. |
Bushland |
871.56 |
11.34 |
| 9. |
Forest |
1,069.20 |
13.91 |
| 10. |
Water bodies |
15.48 |
0.20 |
| 12. |
Mixed vegetation |
1,087.65 |
11.15 |
| |
Total |
7,684.74 |
|
Classification Performance for the Three Classification Approaches
To evaluate the results of the classifications and to verify the degree to which the land cover maps derived would meet users' needs, classification accuracy assessment was done through machine-assisted procedure. One basic constraint in the study is the lack of in depth ground truth data for the study area and thus accuracy assessment is based mainly on spectral analysis of the digital data. The derivation of accuracy figures are based on the following definitions:
| Overall accuracy = |
# of correctly classified areas/total # of areas |
| Procedure accuracy = |
Total # of correct areas in each resource class
----------------------------------------------------
Total # of reference areas in each resource class |
| User accuracy = |
Total # of correct areas in each resource class
--------------------------------------------------------
Total # of classified areas in each class
|
Using the above resoning, the following figures compare the performance of the three approaches:
| |
Supervised approach |
Unsupervised |
Modified Clustering |
| Overall Classification Accuracy |
80% |
85.7% |
90.9% |
Conclusions
Where areas are characterized by topographic and vegetation complexity as in the case of the Pa wang Phloeng-Muang Khom-Lam Narai National Forest Reserve, an effective method for the classification process suited for the environment results in a significant improvement in identification of various individual cover types. Among the different approaches to classification, the study shows that the modified clustering approach to classification is the best technique to employ since it allows for a high degree of interaction between the analyst and the machine, there by complementing the inadequacies of either party. The difficulty in derivating signatures is effeciently executed through the methodology of hybrid classification, at lesser processing time.
The analyst on the one hand, is also given the opportunity to "control" which signatures best qualify to represent a certain resource class considering the fact that he or she holds the reference data from which to base the fine decision for classification. The results of the study also show that the modified clustering approach gives the highest overall classification accuracy of 90.9% for level II resource class.
The capability of ERDAS for man-machine interaction also facilities the various steps in digital analysis and the use of Landsat TM data for vegetation mapping has produced reasonableaccuracy results. Its main limitation however, is therefor, is the presence of cloud cover in the image, which constrains the interpretation of some areas. It is therefore recommend that further studies on the area with use of remote sensing data be realized in conjunction with the use of radar digital data whose capabilities allow the user to 'see' through the clouds (aschbacher, 1991)
Acknowldgements
The authors are grateful for the advice and assistance given by many people involved, especially Mr. Yian Kawan Ang, Manager of the Remote Sensing Laboratory (RSL), Mr. Than Naing, and Mr Quang Instrumentation Engineer and System Analyst, respectively. Also sincere thanks are due to Mr. More Myint, a doctral candidate of the STAR Program of AIT.
References
-
Anderson, J. R. et al. 1976. A Land Use and Land Cover Classification System for Use with Remote Sensing Data. U. S. Geological Survey Professional Paper 964. U. S. Gov. Printing Office, Washington, D. C.
- Aschbacher, J. 1991. Application of Microwave remote Sensing for Tropical Forest Management Paper Presented at the "International Workshop on Conservation and Sustainable Development" 22-26 April 1991, Kho Yai, Thailand.
