Two facilities opening in 2026 will answer the question that the entire cooling industry has been arguing about in conference rooms and on LinkedIn: can you cool a high-density data center without consuming water, in a climate where you actually need cooling?
Phoenix, Arizona is the first test. A zero-water pilot project launching this year in a market where summer temperatures regularly exceed 110 degrees Fahrenheit and the municipal water supply depends on a Colorado River system that has been in sustained decline for two decades. If zero-water cooling works in Phoenix, it works everywhere in the continental United States. The climate offers no margin for error. Every BTU rejected to the atmosphere has to get there without evaporative assist on the worst days of the year.
Mt. Pleasant, Wisconsin is the second. A facility designed to operate without consumptive water use in a humid Midwestern climate where the thermal challenge is different. Humidity limits the effectiveness of certain dry cooling approaches. The engineering has to account for condensation management, ambient temperature swings across seasons, and a heat rejection profile that looks nothing like the arid Southwest.
The technology stack for zero-water cooling is not a mystery. Dry coolers, which are essentially fan-driven radiators, reject heat to ambient air without evaporation. Closed-loop liquid cooling systems circulate coolant through cold plates and CDUs without consumptive loss. The heat collected from the servers transfers to the dry coolers, which dump it outside. No water enters the system. No water leaves.
The tradeoff is capacity and cost. Dry coolers sized for peak ambient temperatures in a place like Phoenix require significantly more radiator surface area and fan power than an equivalent evaporative system. The capital cost per kilowatt of cooling capacity is higher. The footprint is larger. The electrical load for the fans is real, though still far below what a comparable air-cooled CRAC system would draw.
Operators have been deploying dry coolers in Northern Europe and the Nordics for years, where mild ambient temperatures make the economics straightforward. The open question is whether the approach can work in climates that stress-test it. Phoenix and Mt. Pleasant are the stress tests.
The results from these pilots will influence permitting decisions, facility design standards, and vendor selection for the next generation of builds. If zero-water performance holds at commercially viable cost points, the argument for new evaporative installations in water-stressed regions collapses. If the pilots reveal cost or performance penalties that operators cannot absorb, the industry settles into a hybrid model where dry coolers handle the base load and evaporative assist kicks in on peak days. Either outcome reshapes procurement.