An innovative approach to artificial intelligence (AI) now enables the reconstruction of extensive datasets, such as overall ocean temperature, from a small number of field-deployable sensors using low-powered edge computing. This method holds broad applications across industry, science, and medicine.

“We developed a neural network that allows us to represent a large system in a very compact way,” said Javier Santos, a researcher at Los Alamos National Laboratory. “That compactness means it requires fewer computing resources compared to state-of-the-art convolutional neural network architectures, making it well-suited to field deployment on drones, sensor arrays, and other edge-computing applications that put computation closer to its end use.”

Santos is the lead author of a paper published in Nature Machine Intelligence by a team of Los Alamos researchers on the novel AI technique, dubbed Senseiver. This work, building on an AI model called Perceiver IO developed by Google, applies techniques from natural-language models, such as ChatGPT, to the challenge of reconstructing information about large areas — such as oceans — from relatively few measurements.

The team recognized the model’s broad application due to its efficiency. “Using fewer parameters and less memory requires fewer central processing unit cycles on the computer, so it runs faster on smaller computers,” said co-author Dan O’Malley.

In a first for published literature, Santos and his Los Alamos colleagues validated the model by demonstrating its effectiveness on real-world sets of sparse data, meaning information gathered from sensors that cover only a tiny portion of the field of interest, as well as on complex three-dimensional fluid datasets.

To showcase Senseiver’s real-world utility, the team applied the model to a National Oceanic and Atmospheric Administration sea-surface-temperature dataset. The model integrated a multitude of measurements taken over decades from satellites and sensors on ships, enabling it to forecast temperatures across the entire ocean. This capability provides valuable information for global climate models.

Senseiver is well-suited to a variety of projects and research areas at Los Alamos. “Los Alamos has a wide range of remote sensing capabilities, but it’s not easy to use AI because models are too big and don’t fit on devices in the field, which leads us to edge computing,” said co-author Hari Viswanathan. “Our work brings the benefits of AI to drones, networks of field-based sensors, and other applications currently beyond the reach of cutting-edge AI technology.”

The AI model will be particularly useful in identifying and characterizing orphaned wells, a key focus of the Department of Energy-funded Consortium Advancing Technology for Assessment of Lost Oil & Gas Wells (CATALOG), led by Viswanathan.

This approach offers enhanced capabilities for a range of large, practical applications, including self-driving cars, remote modeling of assets in oil and gas, medical monitoring of patients, cloud gaming, content delivery, and contaminant tracing.

By Impact Lab