 Hi, I'm Eugene Morgan, and I'm an associate teaching professor here at Penn State. I wanted to take a minute to explain why I'm teaching this course on data analytics for energy systems. Well, first and foremost, I am super excited about data. I think there's a lot of cool things you can do with data, a lot of cool tools you can make, a lot of cool visualizations you can make, and ultimately the best thing is telling a very interesting story with data. And so in this course, I'm especially excited to teach you some of these tools that I've come to love and cultivate your voice and telling your own story with data. What I'd like to go through are some examples of ways that I've used data in my past research, ways that I've applied the tools that were learned in this course to real-world exciting things in the energy sphere. So first off, this is from a paper that I did on wind speed probability distributions. It's really important to understand what sorts of wind speeds to expect at a location before you build a wind farm or a wind turbine to generate wind power. And so in this image here, we're looking at a couple of example locations in this study. In the real study, we used hundreds and hundreds of locations, so lots of data, really large data set, and what we're doing here is we are fitting curves, basically doing regression that we'll talk about later in the course, to these wind speed probability distributions. And down here, we've got some comparative box plots. You'll learn how to make those in our visualization segment of the course, comparing how well different kinds of models fit to the wind data and what performs best. Secondly, I want to give an example of some research that I've done in identifying and exploring natural gas in the subsurface. And in this research, I came up with an algorithm for processing data to get estimates of where this gas is located and what its properties are. And so this workflow here demonstrates a pretty complex algorithm for doing that. At its heart, it's using some simulation to simulate what different models would predict. We'll talk about simulation tools in this course. That's really at the core of it in terms of bootstrapping and hypothesis testing. And so we'll do a much simpler version of this sort of algorithm, not nearly as complex as this, but it'll be a good foundation for doing things like this. Lastly, I just want to talk about some more natural gas, but this time in terms of mapping it over a very large area. So in this data analytics project, a student of mine came up with a geographic distribution of natural gas in the Marcella Shale, which we're standing on top of right now here in State College. Maybe you're standing on it too if you're somewhere in Pennsylvania or upstate New York or West Virginia, Ohio, Maryland. We see it here on the map. And these colors represent concentrations of natural gas. Now this is a really cool tool because we can play around with it. We can zoom in on different locations, zoom out, zoom in, and we can change... Here we are close to State College right now, and here we can change what we're looking at, for example, adjusted R squared. We'll learn about adjusted R squared later in the course. And we can also change what metric we're mapping here. For example, proved reserves or P90. And now these are just our estimates. That's a disclaimer for this. In this course, you'll learn about how to take raw data and, again, get some very interesting product of it, because the raw data itself is not so interesting, but what you can do with it is what matters. So I'm hoping this course gets you excited about using tools like this and telling your own story with data. Thank you.