Researchers publishing in Nature Sustainability and Cell Patterns have now quantified what the tech sector has long obscured behind vague sustainability pledges. The data is striking.

Carbon emissions: A 2025 study from Cornell University found that U.S. AI data center deployments could generate between 24 and 44 million metric tons of CO₂-equivalent annually by 2030, the emissions equivalent of adding 5 to 10 million cars to American roadways. Globally, the International Energy Agency (IEA) estimated that electricity generation for all data centers produced approximately 182 million tons of CO₂ in 2024 alone.

Water consumption: The same Cornell research determined that U.S. AI server deployments could drain between 731 and 1,125 million cubic meters of water annually by 2030, equivalent to the household water usage of up to 10 million Americans. Research from the University of California, Riverside, found that a single 100-word AI prompt consumes roughly the equivalent of one 500ml bottle of water.

Electricity demand: As of 2024, U.S. data centers accounted for over 4% of total national electricity consumption, with more than half of that electricity sourced from fossil fuels. The country's data centers alone are expected to drive nearly half of all U.S. electricity demand growth between now and 2030, according to the Environmental and Energy Study Institute.

The AI multiplier effect: AI workloads are not just incremental, they are transformative in their resource intensity. The IEA estimates that AI systems accounted for up to 20% of total global data center power demand by the end of 2024, a figure that could approach half of all data center electricity consumption by the end of 2025 as AI infrastructure scales.

What makes this crisis particularly difficult to manage is that it is not merely a question of inefficient buildings. The environmental burden of data centers is baked into three structural layers that interact in compounding ways.

Cornell researchers found that many of the largest new AI data center clusters are being built in water-stressed regions, such as Nevada, Arizona, and parts of Northern Virginia, where rapid concentration strains both local water tables and grid infrastructure. Strategic relocation to low-water-stress regions, combined with cooling efficiency upgrades, could reduce water demand by up to 52%. The decisions being made today will lock in environmental impact for 20 to 30 years.

2. Carbon Intensity That Exceeds the National Average

A study analyzing 2,132 U.S. data centers found that their collective carbon intensity, CO₂ emitted per unit of electricity consumed, exceeded the national average by 48%. This is because many facilities draw power from regional grids where fossil fuels dominate the mix, not because data centers are inherently inefficient. The carbon footprint is a function of where and how power is procured, not just how the facility is operated.

3. Disclosure Gaps That Make ESG Reporting Unreliable

Perhaps the most strategically dangerous issue for real estate portfolio owners is that most major data center operators do not publish AI-specific environmental metrics. A December 2025 analysis in the journalPatterns found that no major operator currently reports AI-specific carbon or water data, making it nearly impossible for investors and tenants to assess ESG exposure accurately. This opacity poses a direct risk to institutional investors with net-zero commitments, GRESB reporting obligations, and corporate sustainability targets.

The lines between commercial real estate and data infrastructure are dissolving rapidly. Office parks are being converted to hyperscale campuses. Industrial portfolios now include colocation facilities. REITs are acquiring data center assets as a hedge against e-commerce displacement. For any real estate organization owner, operator, manager, or advisor, data center ESG exposure is now a portfolio-level risk.

For PropTech-forward organizations managing large or complex portfolios, the gap between regulatory expectations and current ESG capability is widening faster than most internal teams can close it.

The Cornell-led research published in Nature Sustainability not only documents the problem, but it also offers a quantified roadmap. The study found that a combination of smart siting, grid decarbonization, and operational efficiency could reduce carbon emissions by approximately 73% and water consumption by 86% compared to worst-case projections. These are achievable outcomes, not aspirational targets, but they require coordinated action across real estate, technology, and energy systems.

Locating new data infrastructure in regions with abundant renewable energy and lower water stress is the single highest-impact intervention available. States in the Midwest, particularly Texas, Montana, Nebraska, and South Dakota, offer the most favorable combined carbon-and-water profiles, according to the Cornell team. For portfolio managers, this means evaluating future data center investments through an environmental lens from the site-selection stage, rather than retrofitting sustainability after construction.

Advanced Cooling Technology

Transitioning from air-cooled to liquid-cooled or immersion-cooled systems is no longer an emerging option; it is a proven solution. Direct-to-chip and immersion cooling can significantly reduce both energy consumption and water demand simultaneously. Cornell researchers found that deploying energy- and water-efficient cooling technologies could reduce carbon emissions by an additional 7% and water consumption by 29%, in addition to improvements in siting and the grid.

Power Usage Effectiveness and Water Usage Effectiveness Benchmarking

Organizations managing data center assets need to establish systematic baselines for Power Usage Effectiveness (PUE) and Water Usage Effectiveness (WUE) across their portfolio. Without these benchmarks, ESG reporting is guesswork, and optimization is impossible. Real-time monitoring systems, integrated into property management platforms, are increasingly available and scalable.

Renewable Energy Procurement and Green Financing

Power Purchase Agreements (PPAs), on-site generation, and green bond financing are now established pathways for data center operators seeking to decarbonize their energy supply. Digital Realty has become one of the top green bond issuers in the data center industry, specifically to fund this transition. For smaller operators and mixed-use portfolio owners, the structures are replicable.

ESG Reporting Infrastructure

The EU's Omnibus Directive and the CSRD continue to evolve, but core Scope 1 and 2 disclosure requirements are not disappearing. Organizations need purpose-built ESG data management platforms not spreadsheet-based workarounds, to track, benchmark, and report across multiple assets and jurisdictions. Integrating property management data with ESG reporting systems is where technology advisory and PropTech expertise become directly relevant.

The complexity of this challenge sits precisely at the intersection of real estate operations, technology infrastructure, and ESG compliance, three domains that have historically been managed in silos. Organizations that manage data center assets within broader property portfolios are discovering that neither their traditional real estate advisors nor their IT vendors have the integrated fluency to address all three dimensions at once.

This is where the nature of consulting partnerships matters. Firms that combine deep real estate technology expertise, including property management systems, ESG data architecture, automation, and operational analytics with a genuine understanding of sustainability frameworks and reporting standards are positioned to help clients close this gap in practical, measurable terms. The work is not abstract: it involves auditing existing portfolio data, mapping it to GRESB, SFDR, and CSRD requirements, identifying technology solutions that generate the right operational data, and building reporting workflows that satisfy both regulators and investors.

It also involves anticipating what comes next. Regulatory requirements will tighten. Investor scrutiny will intensify. Tenant expectations will escalate. The organizations building integrated ESG capability now, not as a bolt-on to existing operations, but as a foundational element of how their portfolios are managed, will be better positioned in every competitive dimension that follows.

Scientists have now given the real estate and technology industries a clear, data-driven picture of what unmanaged data center growth will cost the planet. The emissions equivalent of 10 million cars. The water demands of 10 million households. A carbon intensity 48% above the national average, powered more than half by fossil fuels.

These are not projections designed to alarm. They are baselines for action. The same research that documents the problem also demonstrates that 73% reductions in carbon and 86% reductions in water are achievable with the right combination of strategy, technology, and operational discipline.

For real estate organizations with data center exposure in their portfolios, the question is no longer whether ESG accountability applies to this asset class. It is how quickly the gap between current practice and the standards investors, regulators, and tenants now expect can be closed.

That gap is closeable. But it requires integrated expertise, the right technology infrastructure, and the organizational will to act before the regulatory and market pressures choose for you.

Data centers currently produce approximately 182 million tons of CO₂ globally per year, according to IEA 2025 estimates. In the United States, 2,132 data centers studied between 2023 and 2024 generated over 105 million tons of CO₂-equivalent, with a carbon intensity 48% higher than the national average. AI workloads are accelerating this impact significantly.

How much water do data centers consume?

U.S. data centers consume an estimated 449 million gallons of water per day, or approximately 163.7 billion gallons annually, with consumption rising sharply. A single large data center can consume up to 5 million gallons of water per day for cooling purposes. AI-driven growth is projected to push U.S. annual data center water use to the equivalent of 10 million Americans' water use by 2030.

How does ESG apply to data centers in real estate portfolios?

Data centers held within real estate portfolios are subject to the same ESG reporting requirements as other property assets, including GRESB benchmarks, SFDR disclosure obligations, CSRD requirements in European markets, and evolving RICS valuation standards. Investors, tenants, and regulators are all increasing pressure for transparent, auditable ESG data from data center assets specifically.

What are the most effective ways to reduce data center environmental impact?

Research from Cornell University and Nature Sustainability identifies three primary levers: strategic siting in low-water-stress, high-renewable-energy regions; advanced cooling technologies such as direct-to-chip and immersion cooling; and grid decarbonization through PPAs and on-site renewable generation. Combining all three can achieve up to 73% reductions in carbon and 86% in water relative to worst-case growth scenarios.

Is AI making the data center environmental problem worse?

Yes, materially. AI accounted for approximately 20% of total global data center electricity demand by the end of 2024, a share that is rising rapidly. The carbon footprint of AI systems alone could reach between 32.6 and 79.7 million tons of CO₂ in 2026, according to research published in Cell Patterns.