Advanced Geospatial Data Analysis

The spatial and temporal dimensions characterizing the Earth and environmental processes, together with the wealth of available data and the rapid development of analytical models, have become distinctive aspects of Geospatial Data Science (GeoDS). GeoDS encompasses geospatial data manipulation, exploration, analysis, and modeling, from the acquisition phase up to the interpretation of the results. By the end of this course, students will gain a good understanding of the key practical concepts of GeoDS and finish related R programming applications, which is beneficial for mastering various algorithms to analyze complex geo-environmental spatial datasets.

These include but are not limited to:

• Exploratory data analyses and visualization;

• Spatial statistics method, e.g., Geographically Weighted Regression;

• Cluster detection and mapping, e.g., Kernel density function, DBSCAN;

• Unsupervised machine learning, e.g., Self-organizing maps;

• Supervised machine learning, e.g., Random Forest;

• Explainability machine learning, e.g., Geographically Random Forest.