John Kamanga's Course Portfolio
I have learnt a number of concepts throughout this course which has imparted in me a number of skill sets. I have learnt how to covert addresses which are in tabular form into geographic coordinates which can be placed on a map through a process of geocoding; I have also gained skills in integrated AutoCAD data into ArcGIS Pro which involved assigning spatial reference to image layer, and then dragging and assigning control points to the AutoCAD data in order before georeferencing it; I have also learnt data relationships that may exists between two tables and learnt methods of how to join or relate them under Data Cardinality; In addition, I have gained skills in associating events and attributes to linear features through a process called linear referencing. The most interesting part was on identifying patterns that existed in different data sets through pattern and cluster analysis. On this, I gained skills in analyzing data identifying clusters, or dispersions of random patterns hidden within the datasets. Then using various tools, i leant how to display the data through Hot/Cold spots among other things. I also learnt how to extract census data and prepare it for different analysis which would help in solving real life problems. The course has also imparted in me skills for conducting site suitability analysis. This will be handy in analyzing suitable sites for various phenomenon based in different variable characteristics as required by users. Finally, i learnt how to conduct supervised land classification of satellite imagery raster datasets.
I will use the knowledge learnt in my day to day duties. Just to mention a few, I will use the Spatial Autocorrelation (Global Moran’s I) tool to assess whether the Malaria incidence cases in Nkhotakota, Malawi are random or form any clustering patterns. I will first assess the average square kilometers in Nkhotakota villages (Administration boundary level 4) to determine the grid size to use. Using spatial join, I will join the grid data to malaria incidence health facility point dataset. Then will run a definition query to make use I rule out all the grids with no data. Finally will run the Spatial Autocorrelation to determine the spatial pattern of the data. I will use the Cluster and Outlier Analysis (Anselin Local Moran's I) tool to conduct the hotspot analysis for covid19 cases in Malawi. I will use fixed distance band to control the distance at which the tool can search significant neighbours. This will help in informing vaccination efforts in the hotspots, and pandemic control behaviour change messages in cold spots. I will also use Hot Spot Analysis (Getis-Ord Gi*) tool to conduct a hot spot analysis for number of qualified clinical staff in health facilities in Malawi. Malawi Health Facility Staffing layer will be used as input feature class layer, and the number of qualified clinical staff field will be used as target field. This will use fixed distance band as well. The results will be used for relocating staff from areas of high concentration to areas which have facilities with low number of qualified staff. This will also be weighted with catchment population before making any staffing recommendations.
I will also use the weighted overlay system to find a suitable site for my aquaculture farm. The criteria will include near reliable water supply like streams, close to road network for transportation, high temperatures to allow for fish growth, near settlement areas for easy labor and protection, and slope for irrigation. Tools to be used will include distance accumulation, slope, reclassify, and weighted overlays. This data will be collected from the aquaculture department, ministry of lands, and FAO statistics.
I will use the image supervised classification in updating the land cover classification for southern region of Malawi. This area is prone to floods and droughts in different seasons. I would want to assess whether there has been a significant change in land cover over the years which may explain the frequent extreme weather events. I will used supervised classification, by training my samples using training sample manager, and then conducting classification of the imagery, which will be requested from NASA as we have a good working relationship through GeoCenter.