If you provide Earth Systems Science learning opportunities at the post-secondary levels or within the workforce, UCAR needs your input! UCAR would love to hear about any learning opportunities that you offer on emerging ESS capabilities — ranging from AI/ML and data management to relationship building, creativity, and more — that are needed in the workplace now and in the future. Help UCAR understand your priorities and any obstacles to providing education, training, and support for these capabilities.

K Nearest Neighbors (KNN) is a supervised machine learning method that 'memorizes' (stores) an entire dataset, then relies on the concepts of proximity and similarity to make predictions about new data. The basic idea is that if a new data point is in some sense 'close' to existing data points, its value is likely to be similar to the values of its neighbors. In the Earth Systems Sciences, such techniques can be useful for small- to moderate-scale classification and regression problems.

Your idea of what's entailed in setting up a supervised Machine Learning (ML) project as an Earth Systems scientist is probably not as fanciful as what an image generation algorithm came up with. But there are many little decisions ML practitioners make along the way when starting an Earth Systems Science (ESS) ML project. This article provides some tips and ideas to consider as you're getting started. These tips are not in any particular order, and like all things related to ML projects they depend on the specific types of data and project goals.

Regression analysis is a fundamental concept in the field of machine learning (ML), in that it helps establish relationships among the variables by estimating how one variable affects the other.

The coefficient of determination, R² (pronounced “R squared”), is a measure that provides information about how well the regression line suggested by a numerical model approximates the actual data (often referred to as “goodness of fit”).

Representation of nodes in a Self Organizing Map.

A self-organizing map (SOM), sometimes known as a Kohonen map after its originator the Finnish professor Teuvo Kohonen, is an unsupervised machine learning technique used to produce a low-dimensional representation of a higher dimensional data set. SOMs are a specific type of artificial neural network, but use a different training strategy compared to more traditional artificial neural networks (ANNs). SOMs can be used for clustering, dimensionality reduction, feature extraction, and classification — all of which suggest that they can be important tools for understanding large Earth Systems Science (ESS) datasets.

Machine Learning systems are often configured around Graphics Processing Units (GPUs) rather than Central Processing Units (CPUs). Why should this be the case, in an era when CPUs are powerful and (relatively) inexpensive? This article provides some insights into what GPUs are and why they provide advantages for certain types of computations, including some commonly used for machine learning and modeling.

There are a lot(!) of free online resources available if you want to learn practical machine learning skills, workflows, and processes. This post highlights some recommendations by Thomas Martin, an AI/ML Software Engineer at the Unidata,

The following are a few of Unidata AI/ML developer Thomas Martin's favorite books on machine learning. These books range from pure theory to hands-on practical Python programming help. They are arranged roughly in order if you are starting your journey into ML, but can also be read out of order.

In this week's AWIPS Tips, we're announcing a new eLearning course, Learn Python-AWIPS. This is an asynchronous web course that can be accessed on demand at Unidata eLearning. All of our educational resources are also available on our website.

Unidata is looking for an Artificial Intelligence/Machine Learning (AI/ML) developer to join our team, helping educators and students learn how to use Unidata software and data services to support their scientific research.

In this role, you'll interact with Unidata's community of researchers and educators to determine how they are harnessing AI/ML approaches to data analysis, and work toward a convention for storing data and metadata in an AI/ML ready way. In addition, you'll help evaluate existing tools such as the MetPy and Siphon python libraries and the netCDF libraries for fitness in the context of AI/ML applications. Your work will help identify and implement improvements that allow for smoother integration of Unidata software into a modern AI/ML pipeline.