Researchers advance hyperlocal climate modelling

The do-it-yourself climate modeling movement is here.

Researchers from Northwestern University and Argonne National Laboratory have rolled out Nvidia Jetson-powered edge computing waggle devices around the world to collect hyperlocal climate information. Waggle is an open source edge computing sensor platform developed by Argonne.

Based on this, scientists share open-source AI code developed for Edge in an app store within the Sage web portal funded by the National Science Foundation (NSF).

The pioneering work supports environmental studies around the world. As a result, more and more researchers and scientists are jumping in to study climate issues with edge computing and sensors.

Waggle’s installed base studies everything from micro-local Chicago weather to understanding urban heat islands and their impact on residents, to climate impacts on wild rice on land owned by the Ojibwe tribe in Wisconsin.

Recently, the University of Oregon’s Hazards Lab began using edge computing with Waggle. This work aims to understand and identify wildfires as part of the AlertWildfire system, which provides live data streams from smart cameras to residents, firefighters and communities.

Efforts across multiple continents underscore the accessibility of edge computing paired with a digital infrastructure to deliver open AI models for use in these climate-related applications.

“Many climate models focus on large geographic scales – and as such impacts on specific communities can be difficult to understand – but the Department of Energy wants to understand how our changing climate will affect humans, particularly in an urban setting,” says Pete Beckman, an Argonne Distinguished Fellow and Co-Director of Northwestern University’s Argonne Institute of Science and Engineering.

READ :  It's in the budget: new measures for mining companies and a new super flow-through funding tax credit for investors

Nvidia announced the AI ‚Äč‚Äčsupercomputer Earth-2 for global climate research at GTC 2021.

Waggle knots plus Sage AI

It all started in 2015 with an NSF project called Array of Things, or AoT, led by Charlie Catlett, which introduced advanced sensors and edge computing to study urban environments.

The AoT was built using the Waggle Edge Computing platform recently developed in-house at Argonne National Laboratory. Waggle combines powerful edge AI computing like Nvidia Jetson with industry-standard software toolkits like Kubernetes, PyTorch, and TensorFlow to deliver a programmable intelligent platform capable of supporting cameras, microphones, software-defined radios, lidar, and infrared imagers.

To support the rapidly expanding AI and sensor landscape, the NVIDIA platform was the obvious choice as it offers the largest ecosystem, most flexibility, and best-in-class performance.

Jetson’s energy efficiency is critical as waggle nodes are often mounted outside of buildings or on light poles.

The Sage project began with an NSF grant in 2022 to build a nationwide software-defined sensor network to support AI at the edge.

Sage Nodes are open resources for scientific exploration. Scientists can develop new AI models, upload them to the Sage App Store, and then deploy them on Oregon mountaintops or Illinois prairies.

Monitoring Chicago for heat waves

The same core technology is deployed in Chicago, where the Waggle-Sage platform is used.

The US Department of Energy wanted to understand what is happening with climate change in the urban environment. It published a call for proposals for an urban integrated field laboratory. The effort combines the supercomputing of the Waggle nodes with the open source Sage models for hyperlocal data analysis.

READ :  Shield AI is joining a small club with its latest round of funding

Argonne and partners are establishing a city integrated field lab called Community Research on Climate and Urban Science (CROCUS) to focus on the Chicago area. It is planned to gather input from the community to study urban climate change issues and specific areas to ensure that research results directly benefit local residents.

“How do we build hyperlocal AI systems that can give us real insights into an urban environment?” said Beckmann.

Modeling of wild rice migration

In Wisconsin, researchers used a hub with the Ojibwe tribe to help better understand wild rice, a food source with important cultural significance.

“Wild rice is a species that’s changing due to climate change, so they want to understand what’s happening,” says Beckman.

Identify birds by sounds

What else do you get when you combine open AI models, edge computing and researchers on a climate mission?

Many useful applications for many people including bird identification AI.

Now bird watchers can download the Merlin Bird ID app – available for iOS and Android devices – and start identifying birds by their sounds. The models have also been ported to some Waggle devices and can identify birds wherever Sage is deployed.

This AI is music to the ears.