tinyML Talks on September 7, 2022 “tinyML Smart Weather Station: Development of Low-Cost Observation Networks to Support Weather and Hydrology Applications” by Paul A. Kucera and Jenny Plunkett

We held our next tinyML Challenge webcast. Paul Kucera from University Corporation for Atmospheric Research and Jenny Plunkett from Edge Impulse presented tinyML Smart Weather Station: Development of Low-Cost Observation Networks to Support Weather and Hydrology Applications on September 7, 2022.

Accurate and reliable real-time monitoring and dissemination of observations of atmospheric and hydrologic conditions in general is critical for a variety of research and decision support applications including flood monitoring, agriculture applications, water resource monitoring, and improving numerical weather prediction. A combination of automatic weather stations, stream gauge, and soil moisture/temperature observations can provide critical information about the atmospheric, hydrological, and soil conditions that is critical for many societal applications. The University Corporation for Atmospheric Research (UCAR) have developed a low-cost, innovate environmental sensors. The sensors that have been developed include atmospheric temperature, pressure, humidity, wind speed and direction, solar light, precipitation, stream level, and soil moisture and temperature. The sensors have been developed using innovative new technologies such as 3D printers, single board computing systems, and wireless communications. The presentation will provide an overview of the new observation technology and experiences with recent network deployments.

During this section of the talk, we will walk you through the easiest way to develop a TinyML sound recognition solution. With the help of Edge Impulse Studio we will cover all the steps required to develop a successful solution for your weather station challenge, from data set creation, to developing and training a model,to deployment on any tiny device of your choice.
During the talk we will provide all the resources necessary alongside a reference project for you to develop the best TinyML solution.

Dr. Kucera is an Assistant Director of the COMET Program at the University Corporation for Atmospheric Research (UCAR) and leads the international capacity development program. He has over 30 years of research and weather application development experience in the fields of atmospheric and hydrological sciences. His technical expertise is in weather radar, development of weather observation networks, satellite meteorology, numerical weather prediction, weather modification assessment and international program development for the modernization of hydrometeorological services. He has led or participated in projects in Africa, Middle East, Southeast Asia, Pacific Islands, Caribbean, Central America, South America, and North America. His recent and current projects include modernizing the weather services through numerical weather prediction, impact-based forecasting, observational network development, training, and developing low cost, reliable observation networks.

Jenny Plunkett is a Texas Longhorn and software engineer, working as a Senior User Success Engineer at Edge Impulse. Since graduating from The University of Texas she has been working in the IoT space, from customer engineering and developer support for Arm Mbed to consulting engineering for the Pelion device management platform.

=========================

Watch on YouTube:
Paul Kucera and Jenny Plunkett

Download presentation slides:
Paul Kucera and Jenny Plunkett

Feel free to ask your questions on this thread and keep the conversation going!