• Normal Difference Vegetation Index(NDVI)
NDVI is an index that is widely used for evaluating vegetation conditions over
the land surface (Tarpley et al. 2010; Townshend et al. 1985). NDVI can be
calculated as follows:
NDVI ¼ NIR À Red
ð
Þ = NIR þ Red
ð
Þ
ð 17:2Þ
where Red is the surface reflectance of the red band (band 3 in this study) and NIR is
the surface reflectance in the near-infrared band (band 4 in this study). Similar to
NWDI, we use normalized spectral radiance instead of surface reflectance in this
study.
• PML Index (PMLI).
Landsat band 3 (b3) locates at the chlorophyll absorption band. Bare land has
high reflectance in this band, while the heavily vegetated area has low reflectance in
this band. Saline land barely has any vegetation. Therefore, it has high reflectance in
this band. In the early growing season, transparent PML has high reflectance in this
band too since the newly plowed land with cotton seedlings has little vegetation. On
other hand, bare land and fallow land also grow some weeds. Therefore, there is no
big difference in reflectance among PML, bare land, and fallow land in b3.
The band 5 (b5) locates at the water absorption band (1.4–1.9μm). Therefore, it is
sensitive to the water content on the surface layer of soil. Saline land has high surface
reflectance on b5 since its surface usually is very dry. Because the water contents in
the surface layers of PML, bare land, and fallow land have no much difference, their
reflectances in b5 also have no significant difference (see Fig. 17.3a). Therefore, a
PML index (PMLI) by using the reflectances of Landsat TM b3 and b5 was
proposed:
PMLI ¼ b5 À b3
ð
Þ = b5 þ b3
ð
Þ
ð 17:3Þ
By examining the PMLI, we found that at an index value of 0.28, PML and saline
land classes can be separated from bare land, fallow land, and vegetation classes.
The further separation between PML and saline land classes can be done by using the
property that saline land has much higher reflectance in b5 than PML.
17.2.1.2 Construction of the Decision-Tree Classifier
A decision tree is a nonparametric classifier involving a recursive partitioning of the
feature space, based on a set of rules learned through analyzing the training set
(Kumar et al. 2010). A decision tree, known as a top-down classification approach, is
composed of a root node (containing all data), a set of internal nodes (splits), and a
set of terminal nodes (leaves) (Friedl and Brodley 1997; Xu et al. 2005). Due to their
relatively simple, explicit, and intuitive classification structure (Friedl and Brodley
358
L. Lu
NDVI is an index that is widely used for evaluating vegetation conditions over
the land surface (Tarpley et al. 2010; Townshend et al. 1985). NDVI can be
calculated as follows:
NDVI ¼ NIR À Red
ð
Þ = NIR þ Red
ð
Þ
ð 17:2Þ
where Red is the surface reflectance of the red band (band 3 in this study) and NIR is
the surface reflectance in the near-infrared band (band 4 in this study). Similar to
NWDI, we use normalized spectral radiance instead of surface reflectance in this
study.
• PML Index (PMLI).
Landsat band 3 (b3) locates at the chlorophyll absorption band. Bare land has
high reflectance in this band, while the heavily vegetated area has low reflectance in
this band. Saline land barely has any vegetation. Therefore, it has high reflectance in
this band. In the early growing season, transparent PML has high reflectance in this
band too since the newly plowed land with cotton seedlings has little vegetation. On
other hand, bare land and fallow land also grow some weeds. Therefore, there is no
big difference in reflectance among PML, bare land, and fallow land in b3.
The band 5 (b5) locates at the water absorption band (1.4–1.9μm). Therefore, it is
sensitive to the water content on the surface layer of soil. Saline land has high surface
reflectance on b5 since its surface usually is very dry. Because the water contents in
the surface layers of PML, bare land, and fallow land have no much difference, their
reflectances in b5 also have no significant difference (see Fig. 17.3a). Therefore, a
PML index (PMLI) by using the reflectances of Landsat TM b3 and b5 was
proposed:
PMLI ¼ b5 À b3
ð
Þ = b5 þ b3
ð
Þ
ð 17:3Þ
By examining the PMLI, we found that at an index value of 0.28, PML and saline
land classes can be separated from bare land, fallow land, and vegetation classes.
The further separation between PML and saline land classes can be done by using the
property that saline land has much higher reflectance in b5 than PML.
17.2.1.2 Construction of the Decision-Tree Classifier
A decision tree is a nonparametric classifier involving a recursive partitioning of the
feature space, based on a set of rules learned through analyzing the training set
(Kumar et al. 2010). A decision tree, known as a top-down classification approach, is
composed of a root node (containing all data), a set of internal nodes (splits), and a
set of terminal nodes (leaves) (Friedl and Brodley 1997; Xu et al. 2005). Due to their
relatively simple, explicit, and intuitive classification structure (Friedl and Brodley
358
L. Lu