.embed-container {position: relative; padding-bottom: 80%; height: 0; max-width: 100%;} .embed-container iframe, .embed-container object, .embed-container iframe{position: absolute; top: 0; left: 0; width: 100%; height: 100%;} small{position: absolute; z-index: 40; bottom: 0; margin-bottom: -15px;}

Multi-scale Information Extraction

Project Summary: 

One of the most useful applications of remote sensing is extracting thematic information and recognize patterns from raster images using image classification techniques (Jensen, 2016). Due to the low-cost and large-area coverage forest information, satellite remote sensing has been considered best for mapping broad scale forestry, as there are various methods for identifying patterns and various for such as classification, statistical analysis etc. (Franklin et al., 2003). Different objects on the earth’s surface have a different spectral reflectance and remittance properties (Al-doski, Mansor, & Shafri, 2013). Based on this idea, image classification is defined as the process of categorizing all pixels in an image or raw remotely sensed satellite data to obtain a given set of labels or land cover classes or themes (Kiefer, Lillesand, & Chipman, 2015).
There has always been a major concern with the scale issue, in the field of remote sensing as the level of spatial scale can influence the image attraction process and output (Wu & Li, 2009). When image pixels are smaller than the objects of interest, information extraction techniques like classification can be applied (Department of Geography, 2017). However, when image pixels are larger than the objects of interest the user has to choose alternate approaches, like statistical analysis/ regression analysis (Department of Geography, 2017). This assignment discusses about the application of classification technique on Landsat 5 image, exploring the statistical relationship among different variables for predicting leaf area index (LAI) and crown closure, and creating composite maps by combining classified layer and continuous variable information. The overall objective of this assignment can be summarized as :
1. To perform a multi-scale information extraction of landcover and vegetation structure from Landsat TM imagery and DEM data, using classification and statistical modelling techniques
2. To evaluate and communicate the results of your analysis through accuracy statistics, construction of map products, and production of a formal lab report.



This assignment aimed at performing the supervised classification on Landsat 5 image based on the land cover data, creating two continuous variable maps of LAI index and crown closure, and creating two composite maps. In the supervised classification map, the overall accuracy was 60.667%, which was not high enough. The confusion matrix table showed that there were overlapping of land cover classes. Statistical analysis like regression analysis was useful in understanding which variable was a good predictor. The result obtained from the multiple regression analysis using six variables showed that the wetness variable had the highest coefficient of determination with LAI (R2 = 0.69) and crown closure (R2 = 0.52). However, while checking the assumption of the regression it was found out that the dependent variables (LAI and crown closure) were not normally distributed and the variance of the residuals were not homoscedastic. Hence, the result of the regression model cannot be entirely trusted. Two composite maps, produced by combining broadleaf forest land cover and LAI index and coniferous forest and crown closure, provided information regarding the distribution of LAI and crown closure ranges for the mentioned forest vegetation classes. For future studies, it is suggested to collect more ground truth data and use imagery of higher resolution. In addition, composites map can be created for multiple forest vegetation classes by combining those with Lai and crown closure. Different other indices like RSR, SAVI and MSAVI or slope and aspect could be also used in the regression model to see if those can make the model better, if time and resource permits.


Principal Components and Tasselled Cap Transformations

Project Summary: 

Image classification is a useful technique for obtaining information by categorizing all pixels in a digital raster image into several “themes”. Among different classification techniques, Principal Components Analysis (PCA) and Tasseled Cap Transformation (TCA) are used to compress image information for image analysis purpose. In this assignment Landsat 7 Image has been used for PCA and TCA analysis. In this assignment, PCA has been applied using principal Component Analysis tool and TCA has been applied using the Raster calculator tool of PCI Geomatica. The results show that the RGB combination image of PCA and TCA is almost same. The PC1 and PC2 is similar to TC brightness and TC greenness. But there is a difference between PC3 and TC wetness.



Loadings PC1 PC2 PC3 PC4 PC5 PC6
Band 1 0.599727 -0.597500 0.514843 0.046685 0.110932 -0.059132
Band 2 0.745017 -0.467524 0.465573 0.009689 0.026291 0.093750
Band 3 0.728307 -0.569635 0.362937 -0.077148 -0.081119 -0.023480
Band 4 0.814056 0.568476 0.115292 0.016122 -0.004708 -0.003039
Band 5 0.927949 -0.160576 -0.328297 -0.067790 0.023239 0.001729
Band 7 0.811837 -0.488516 -0.280233 0.150037 -0.030689 -0.002198

Spatial Analysis: Interpolation and Viewsheds

Project Summary

This week’s assignment was about learning different interpolation methods and application of viewshed analysis. The whole task was divided into 2 parts. Part A talks about using interpolation methods to predict the mean temperature data for the whole Canada. The second part is about applying viewshed analysis for a cell phone company who wants to provide coverage for the city of the Calgary. Placing three cell phone towers the company wants to know which neighborhoods receive cell phone coverage and have a young population. The results show that the mean temperature for the month of October, 2015 of whole Canada ranged from -18. 5 °C to 14.9 °C and southern regions of the country enjoyed the warmest temperatures. Considering the market criteria, the three towers located in the town can 106 neighborhoods of the city, which are of 200. 89 km2. The land use class type of these neighborhoods are mostly residential (92.45%) with few having (5.66%) industrial use. However, with 8Km buffer the cell tower cannot cover 15 neighborhoods which met the market criteria.

Result Maps :

Part A


Part B:

Park Accessibility

Measuring the Parks and Open Space Accessibility for the Elderly People of the City of Calgary

Project Summary:

Parks and open spaces are vital organs of a city. Apart from many environmental benefits of parks and open spaces, they also promote physical activity and mental well-being among the people. This research work looks in the park accessibility of elderly people of Calgary city within 10-minute walking distance. Service area analysis layer of Network analyst tool has been used in this work to determine the service areas of the parks along the street network.  The results show that 65% of the area where elderly people live in the city of Calgary, have access to urban parks and open spaces within 10-minute walking distance. The results also reveal that north-western part of the town is the best place live in terms of parks and open space accessibility, as 76% of the NW area where elderly people live has accessibility to a park within a 10-minute walking distance.  Southeastern part of the of the town is the worst place to live in, as 47.7% its area where elderly people live has accessibility to parks and open space within a 10-minute walking distance. For future study, it is recommended to use access points of the parks and open spaces as service area facility in the network analysis, rather than centroids of the parks and open spaces.