(From left) Ph.D. candidate Mohammad Shamsodini Lori and Associate Professor Jiangtao Cheng set up a game of Go—the same game Cheng played against an artificial intelligence opponent that inspired him to develop algorithms to solve spray-cooling problems. Credit: Jiangtao Cheng.

It’s a simple law of physics: When electricity or fuel powers a machine, the machine gets hotter. Finding new ways to cool machines quickly and controllably can mean the difference between a functioning electrical grid and a blackout or a working data center and a widespread outage.

One way to cool things down is to spray a liquid onto a heated surface, which is proven to rapidly reduce heat in precision machines. To analyze and predict the most effective method of spray cooling, a mechanical engineering research team made up of Associate Professor Jiangtao Cheng, Assistant Professor Zhenhua Tian, and Ph.D. candidate Mohammad Shamsodini Lori used artificial intelligence (AI) and inspiration from an ancient board game called Go. The findings were recently published in the journal Artificial Intelligence Review.

A strategy that’s no game

Since high school, Cheng had played Go, an abstract strategy board game for two players in which the player who fences off the most territory wins. The game was invented in China more than 2,500 years ago, but in 2014, the release of a computerized version called AlphaGo allowed humans to play against an AI-powered competitor. With artificial learning to perfect its approach, the original AlphaGo AI beat a professional human player within a year of its creation.

Intrigued by the story of the computer’s victory, Cheng decided to compete against the AlphaGo AI himself. While the computer consistently won, the experience gave Cheng the idea of using AI to build a strategy not for winning games, but for cooling hot machines.

"Go is a game of interconnected dynamics, just as a spray cooling system is a network of interacting parameters," Cheng said. "Success—whether winning the game or optimizing the system—requires a holistic understanding of the network and careful management of its interactions, a task that can be greatly enhanced with AI by analyzing complex patterns, predicting outcomes, and guiding optimal strategies."

Algorithms and fluids

Part of what makes spray cooling so complex is what makes it so effective: the droplets.

Spraying a liquid onto a hot surface deploys an army of tiny liquid orbs that hit the surface and evaporate. Each of those evaporating droplets carries away some heat to regulate the surface temperature and keep it from rising too high.

"The way water changes as it encounters heat is different with droplets," said Lori, the study’s first author. "Droplets pick the heat up more quickly and carry it away because they boil and evaporate so quickly. Because of this fast turnaround cycle, droplets allow a much more effective approach to temperature control."

But many intersecting factors determine spray cooling’s effectiveness. What is the best droplet size to remove heat quickly? What size holes in spray nozzles produce them? What is the best fluid to spray when the options include not just water, but solvents, lubricants, and engineered mixes?

To manage all the variables and find the droplets that would cool most effectively, the Go-inspired researchers brought machine learning into the mix. By creating AI algorithms to analyze publicly shared data from 25 previous studies, they evaluated the basic properties of liquids and how those properties contributed to the formation of a droplet with optimum size and ability to absorb heat.

"Even though AI always wins on the Go board, I never felt frustrated but learned to take advantage of AI to tackle challenges and dilemmas in real life, such as thermal management of high power-density electronics," Cheng said.

What’s next

Using AI to conduct a meta-analysis of existing data allowed researchers to bypass a significant amount of trial and error and offer valuable information ready for physical testing. Future research will determine how the team’s predictions perform in the real world—and ideally lead to more effective ways to keep engines, computers, and turbines from overheating.

Cheng summed up the implications of the data the team collected: "By bridging thermo-fluid science with AI, we’re not just improving spray cooling. We’re actually redefining how we understand and design the thermal systems of the future."

More information: Mohammad Shamsodini Lori et al, Thermohydraulic performance of spray cooling systems: a general model by machine learning, Artificial Intelligence Review (2025). DOI: 10.1007/s10462-025-11446-w

Citation: Ancient board game tactics help AI unlock optimal cooling strategies (2026, January 6) retrieved 6 January 2026 from https://techxplore.com/news/2026-01-ancient-board-game-tactics-ai.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.