Python for Geospatial Data Analysis

Chapter 10. Using Python to Measure Climate Data

Developing technical skills and pathways for learning Python and geospatial analysis is important, but unless you provide context or create a narrative to share, it’s all simply data on a shelf.

In this final chapter, you will explore three approaches to exploring time-series data by accessing satellite image layers from Landsat, China–Brazil Earth Resources Satellite (CBERS), and Sentinel. You will use your geospatial analysis skills to examine questions about climate change and deforestation.

Spatial modeling is a crucial tool for forecasting, predicting, and monitoring the real-time status of global temperature increases and deforestation, which in turn helps us anticipate the consequences of these phenomena and potentially intervene or prepare for them.

Three examples are presented to highlight some powerful Python packages: Xarray, Web Time Series Service (WTSS), and Forest at Risk (FAR). Although these may appear to be new tools, you have been introduced to many of their dependencies in earlier chapters. The last example is a deeper dive into the statistical power of packages designed for predictive modeling, which you’ll use in analyzing deforestation. You can run code in the accompanying notebook, since complete explanations of everything in it is beyond the scope of this book.

Example 1: Examining Climate Prediction with Precipitation Data

Spatial analysis often relies on multidimensional data analysis. Think of a gridded ...