Shuozhang insights

From Visual Analytics and Applications
Jump to navigation Jump to search
ShuozhangRosebreastedgrosbeak.jpg
Vast Mini-Challenge 3

Introduction

Data Preparation

Insights

Deliverables

 


Boonsong Lake

ShuozhangQ1bs.JPG
ShuozhangQ1points.jpg

As X=0, Y=0 refers to the pixel in the upper-left corner of the image, the Y-coordinate should be reversed.

The B1 penetrates water and B5 absolutely absorbed by the water, the area that shows a large number of B1 and B5 is more likely to be the water body. The chart of B1 and B5 shows that the Boonsong Lake is roughly in the upper middle of the image. The length of the lake approximately covers from upper-left of the lake: X=150.1, Y=474.9 to bottom-right of the lake: X=158.9, Y=502.4. Then the length of the pixel is around 28.9 which means 28.9 is corresponding to 3000 feet in the real situation which means 1 pixel-length is 103.8 feet.

Therefore, one pixel covers 103.8*103.8=10774 square feet, nearly 10.8 thousand square feet.

Features in the Image

Multi-spectral bands and their utility:

Band Color Wavelength (nm) Useful for Mapping
B1 Blue 450-520 Penetrates water, shows thin clouds and general visible brightness.
B2 Green 520-600 Shows different types of plants and general visible brightness.
B3 Red 630-690 Vegetation color and certain mineral deposits.
B4 Near Infrared (NIR) 770-900 Partially absorbed by water, sensitive to vegetation structure and chlorophyll.
B5 Short-wave Infrared (SWIR) 1 1550-1750 Completely absorbed by liquid water. Sensitive to moisture content of soil and vegetation; penetrates thin clouds.
B6 Short-wave Infrared (SWIR) 2 2090-2350 Insensitive to vegetation color or vigor, shows differences in soil mineral content.

Since the B1 band only shows thin clouds and visible lights, there is no use to perform clustering on B1. B2 shows different types of plants and it is useful to see the plant health when combining B2, B3 and B4. Therefore clustering analysis is done on B2 and the combination of those three bands. The following images are the results. Here five clusters are considered.

ShuozhangB2 cluster.jpg

Clearly, the cluster 1 collects the features that B2 cannot identify, as it is the largest group and the water body - lakes are also counted into it. Then the rest of the clusters are different types of plants.

ShuozhangCluster on B2 B3 B4.jpg


B5 and B6 capture much detailed information.

ShuozhangB5 cluster.jpg
ShuozhangB6 cluster.jpg
ShuozhangQ2 Dashboard 1.jpg

Changes in the Features

Compare the Images of June:

Shuozhang06 NDVI COMPARE.jpg
Shuozhang06 BAND COMPARE.jpg


Compare the Images of September:

Shuozhang09 ndvi compare.jpg
Shuozhang09 band compare.jpg