ENVIRONMENTAL DATA SCIENCE

SOILSCI 585

Data science techniques are increasingly important in soil and environmental science, improving the efficiency and repeatability of data analysis and enhancing fundamental understanding of soil and environmental issues. Various R packages will be introduced and used to analyze and process soil and environmental data collected using a variety of in situ, ground-based, and remote sensing platforms. R software will be applied to detailed case studies covering soil and environmental data processing, manipulation, and modeling.

ENVIRST 956

Focuses on the fundamental physical principles of terrestrial remote sensing, followed by an examination of advanced topics in earth observation and digital image processing. Topics include radiation interaction with the atmosphere and the surface; radiative transfer theory; land surface characteristics including energy balance; thermal sensing; atmospheric and radiometric correction of image data; automated cloud detection and removal. Applications of remote sensing data for environmental problems will be explored in depth, including biophysical remote sensing with 3D modeling of vegetation canopies, dense time series analysis, data mining techniques, data fusion, as well as object vs. per-pixel approaches to pattern recognition. Explores all major data types, including optical, RADAR, LiDAR, and hyperspectral data, and provide instruction in hands-on image processing using open source software.

F&WECOL 395

Quantitative tools applicable to the investigation of ecological problems, including but not limited to, statistics, Geographic Information Systems (GIS), Remote Sensing, and spatial analysis. Overview of commonly used quantitative techniques in ecological sciences with an emphasis on GIS and spatial analysis. Introduces spatial tools and practical applications using ecological/environmental data sets.

ENVIRST 506

Systems modeling; applications to environmental problems; systems methods.

ATMOCN 775

Application and analysis of advanced statistical, mathematical, and machine learning tools in Atmospheric, Oceanic, and Climate Sciences. Emphasizes application of statistical techniques to synthetic and real data; analysis of existing research in Atmospheric, Oceanic, and Climate Sciences; and exploration of new applications of statistical and machine learning techniques in relevant scientific literature. Knowledge of basic statistical methods and statistical programming [such as those introduced in 575] is required