.rst .pdf

Geospatial data analysis with Python

Course Introduction

Geospatial Data Analysis with Python is an online training course provided by GeoSpatialyst to teach you how to programmatically analyze geospatial data with Python. The course consists of six interactive sessions starting from learning general operations on geometric features to analyzing satellite images (i.e. reading and writing raster formats). In this course, students will mostly sit in front of computer since they will learn to program and do pratical exercises in Python language alongside with the course convener. We will focus on applying programming skills to do various tasks without using any tool in GIS but producing the same or better result and faster than GIS.

Course Requirement

To gain the most from the course, it’s necessary to know the basics of ArcGIS or QGIS and Python programming. You don’t need to be very good at it, but at least you should know the main files in GIS such as vector or raster files and have little experience in Python. If you are new to Python, you might find it a bit difficult to follow the lessons, but it doesn’t mean you can’t take this course because you’ll never know until you try.

Course Environment

In this online course, we will use JupyterLab, a web-based user interface, as the main programming environment. It enables you to work with documents and activities such as Jupyter notebooks (.ipynb-files), text editors, terminals, and custom components in a flexible, integrated, and extensible manner. All of the code materials in this course are in .ipynb-files which you can run in JupyterLab on your own computer.

Course Objectives

In this course, you will learn from the basic level of using Python for geospatial data analysis to advanced level of analyzing the satellite image retrieved from dataset in Google Earth Engine. In each session, you are supposed to gain the following knowledge:

Let's get started!

• Session 1: Geometric Objects
  • Overview:
  • Exercises
• Session 2: Vector Data Analysis and Map Projection
  • Overview:
  • 1.a. Reading vector files
  • 1.b. Plotting vector files
  • 1.c. Analyzing vector file
  • 1.c. Exporting Shapefile and GeoJSON
  • Practice
  • Others
• Session 3: Geocoding and Nearest Neighbour Analysis
  • Overview:
  • 1. Introduction to Geocoding in Geopandas
  • a. Geocoding from a name list
  • b. Geocoding from address file
  • c. Table join
  • d. Point in Polygon
  • 2. Nearest Neighbour Analysis
  • a. Nearest point with Shapely
  • b. Nearest point with Geopandas
• Session 4: Geometric operation and Data classification
  • Overview:
  • 1. Geometry operation
  • a. Spatial overlay analysis
  • 2. Data classification
  • a. Pysal classifier
  • b. Custom classifer
• Session 5: Plotting Static and Interactive Map on Leaftlet
  • Overview:
  • 1. Static map
  • a. Plotting Geodataframe
  • c. Adding basemap
  • 2. Interactive map
  • a. Creating a simple interactive map
  • b. Adding custom basemap
  • c. Saving map as html
  • d. Adding layers
  • b. Heatmap
  • c. Choropleth map
  • d. Tooltip
• Session 6: Raster Data Analysis
  • 1. Reading raster file with Rasterio
  • a. Read raster bands
  • 2. Visualizing raster layers
  • a. Band visualization
  • a. Natural and False Color Composites
  • 3. Masking or clipping raster data
  • 4. Exporting raster data
  • 5. Mosaic or merge raster data
  • a. Merge images of different bands
  • b. Merge images of different extent
  • 6. Raster algebra
  • a. NDVI
  • b. NDWI
  • 7. Extracting river cross-session

previous

Building Footprint Prediction on WorldView-3 Satellite Images

next

Session 1: Geometric Objects