Refactoring and Maintaining Python Code

Feb. 7, 2020

Both the design and the culture of Python are somewhat unique in their focus on readability and comprehensibility when writing code. One of the people responsible for this philosophy is the creator of python, Guido van Rossum. One of his key insights is that code is read more than it...

Calibrating Low-Cost Air Pollution Sensors Using Machine Learning

Feb. 7, 2020

The Rise of Low-Cost Sensors Air pollution measurements are often reported as 24-hour averages, with relatively few monitors from federal and state agencies dispersed over large areas. Especially in the western U.S., there is sparse coverage of air pollution monitoring (see my blog post about mathematically modeling air pollution over...

What is Natural Language Processing and Why is it Hard?

Feb. 7, 2020

Anyone who has ever tried to learn a foreign language can tell you that learning a new language is hard. Languages are layers of complex rules that often break, depending on context. Even if all of the rules were true all of the time, a great deal of brain power...

Remote Sensing Tools: SAM and NDVI

Feb. 6, 2020

If I asked you to highlight the dirt road on the top of this image, you could do it super easily. Aerial photo of a patch of dirt and shrubs. Red pixel marks the source. Now what if I asked you to highlight all the grass and shrubs? Not the...

Cropland State Transition Model

May 24, 2019

Source: USDA NASS CDL Layer Introduction Climate is arguably the most significant force in environmental change. Cropland is directly affected by climatic changes through loss in soil moisture, increases in CO2 levels, changes in temperature, and extreme weather conditions. South-Eastern North Dakota is a widespread producer of spring wheat, corn,...

Machine Learning and Underwater Biomass Characterization

May 16, 2019

Coastal marine ecosystems are of vital interest to the U.S. economy. The California Current System (CCS) provides an ideal natural laboratory for integrating satellite remote sensing, subsurface measurements, and numerical modeling to study physical ecosystem dynamics and the subsequent dynamic biogeography of the marine realm. Satellite data is generally easier...

The Wizards of (O)pen (S)ource (S)oftware

May 14, 2019

Our tips and tricks for contributing to open source software on GitHub This semester, we interned as contributors to the Earth Lab’s package EarthPy, which is an open source package that makes it easier to plot and manipulate spatial data in Python. During our time working on EarthPy, things were...

Mathematical Modeling of Air Pollution Over the Western US

May 14, 2019

In almost every field (and especially in any kind of data science), there will be times when we wish to estimate data we don’t have by using the data that we do have. Given the plethora of machine learning algorithms and the similarly-daunting number of implementations of these algorithms (in...

July 8, 2016 - The Day Hayden Pass Burned

May 14, 2019

One day in the summer of 2016, I was wheeling a heavy stack of chairs into the back of a truck after a long day of work when I decided I needed to go on an adventure. On this particular day, instead of rushing home to relax after a long...

Dialogue Vs. Deficit: Strategies for Science Communication

May 13, 2019

By their nature, scientific fields are constantly in flux, rapidly evolving and publishing new discoveries. While the methods, technologies and theories in these fields are eternally under development, the tools and manners in which they are communicated, both within the scientific community and to those outside of it, seem to...

Pages