Embedded Files
Using Remote Sensing to Track Changes in Land Use and Cover in Kutupalong.pdfGIST 501B_ S2024_TriptyR_Lab 1.docxClass Project_ Lab 1
Class Project_ Lab 1
Processing Raster Data Using ArcGIS Pro
Lab2_TriptyRresubmission.pdfClass Project_ Lab 2
Class Project_ Lab 2
Two different Remote Sensing Indices_ the NDWI and the MNDWI used for detecting and mapping water features, such as open water bodies, wetlands, and moisture content in soils or vegetation. Although they are both designed to highlight water features, they differ in their formulations and the specific features they emphasize, leading to differences in their appearance and the features they make more or less apparent.
RabeyaT_Lab3.pdfProducing False color composites in Landsat_ Class Project_ Lab 3
Producing False color composites in Landsat_ Class Project_ Lab 3
Landsat 8/9 has the highest Spatial resolution
Landsat 8/9 has the highest Temporal resolution
Landsat 8/9 has the highest Spectral resolution
Landsat 8/9 has the highest Radiometric resolution
Higher spatial resolution provides more detail and allows for more precise identification of land covers and features. For example, different types of vegetation or land use can be more easily distinguished with higher resolution imagery. In lower resolution imagery, a single pixel may represent a mix of different land covers within its area. This can lead to confusion in land cover classification, especially in areas with diverse land cover types. Higher spatial resolution generally leads to higher mapping accuracy, as it allows for more detailed and accurate delineation of boundaries between different land cover types.
TriptyR_Lab 5.pdfImage without correction and with correction accordingly_ Class Project_ Lab 5
Image without correction and with correction accordingly_ Class Project_ Lab 5
Baltimore LiDAR 3D_TriptyR.pdfBaltimore City LiDAR 3D_ Class Project_ Lab 6
Baltimore City LiDAR 3D_ Class Project_ Lab 6
-Red or pink represents Buildings.
-Shades of Brown represents ground or terrain.
-When buildings and the ground overlap in the point cloud, the resulting overlap area is typically depicted in shades of purple or magenta.
InSlope surface model the TIN surface indicates surface gradient or rate of change across elevation value. The surfaces describe the inclination or steepness of the terrain represented by the LiDAR points.
Lab 6_TriptyR.docxLab 7_TriptyR.docxUnsupervised Classification in ArcGIS Pro_ Class Project_ Lab 6
Unsupervised Classification in ArcGIS Pro_ Class Project_ Lab 6
Increasing the minimum class size should generally lead to clusters where pixels within the cluster tend to be more similar to each other in terms of their reflectance values or pixel values. This is because the minimum class size parameter controls the minimum number of pixels required to form a separate cluster or class.
When the minimum class size is increased, the algorithm becomes more selective in creating new clusters. It will tend to merge smaller groups of pixels with similar values into larger clusters, rather than creating multiple small clusters for those pixels. As a result, the pixels within each cluster will tend to be more homogeneous or similar in their reflectance values or pixel values.
The reason,
By increasing the minimum class size, the algorithm is forced to merge smaller clusters that fall below the specified minimum size into larger clusters. Smaller clusters consisting of a few pixels with outlier or divergent values are more likely to be absorbed into larger clusters when the minimum class size is increased. The minimum class size parameter also promotes spatial coherence within clusters. Pixels that are spatially isolated or scattered are less likely to form separate clusters when the minimum class size is high, as they may not meet the minimum pixel count requirement.
Lab 8_TriptyR.pdfSupervised Classification_ Used Random Tree image Classifier and Maximum Likelihood Image Classifier (Class Project Lab_8)
Supervised Classification_ Used Random Tree image Classifier and Maximum Likelihood Image Classifier (Class Project Lab_8)
Lab_10_TriptyR.pdfSupervised Classification and Validation in R Language_ (Class project_ Lab 10)
Supervised Classification and Validation in R Language_ (Class project_ Lab 10)
Lab11_GIST 501B_S2024_TriptyR (1).pdfTucson AZ Land-Use Land Cover Change Analysis (LULC) in R and producing change analysis in chart and Sankey Diagram_ Class Project_ Lab 11
Tucson AZ Land-Use Land Cover Change Analysis (LULC) in R and producing change analysis in chart and Sankey Diagram_ Class Project_ Lab 11
Lab_12_TriptyR (1).pdfTucson AZ Time series study in Google EARTH ENGINE FOR Median NDVI and Median NDWI and Mann-Kendall trends for both the NDVI and NDWI_ Class Project_ Lab 11
Tucson AZ Time series study in Google EARTH ENGINE FOR Median NDVI and Median NDWI and Mann-Kendall trends for both the NDVI and NDWI_ Class Project_ Lab 11
Page updated
Google Sites
Report abuse