Key Takeaways
- Two Idaho high‑school students, Marco Trotta and Henry Turcotte, have built a startup called Irrigant that uses artificial‑intelligence algorithms to optimize irrigation for farmers.
- The system analyzes soil, weather, and crop data to recommend precise watering amounts and timing, aiming to cut waste of water, energy, and labor.
- According to the U.S. Department of Agriculture, irrigation accounted for 47 % of the nation’s freshwater withdrawals between 2010 and 2020, highlighting the potential water‑saving impact of more efficient practices.
- Trotta acknowledges trade‑offs in AI adoption but argues the technology’s benefits could outweigh its resource costs if deployed widely.
- Irrigant has already been tested on 7,000 active acres of farmland, with plans to scale up and officially launch the venture in 2027.
Introduction: AI Water Concerns in Utah
In recent months, Utahns have raised alarms about the substantial water consumption of artificial‑intelligence data centers, fearing that the rapid growth of AI could exacerbate already strained water supplies in the arid West. While those concerns are valid, a contrasting narrative emerges from neighboring Idaho, where two teenagers are harnessing AI not to drain water but to conserve it. Their project, Irrigant, seeks to flip the script by using machine‑learning tools to help farmers irrigate more efficiently, potentially offsetting the water footprint of AI infrastructure itself.
Teen Innovators Behind Irrigant
Marco Trotta and Henry Turcotte, both high‑school students, founded Irrigant after noticing inefficiencies in traditional irrigation practices on family farms. “We saw growers guessing how much water to apply, often over‑irrigating just to be safe,” Trotta explained in an interview. Their solution combines low‑cost soil‑moisture sensors, satellite imagery, and locally sourced weather data, feeding the information into an AI model that outputs irrigation schedules tailored to each field’s specific conditions. The duo emphasizes that the technology is deliberately designed to be accessible: “We wanted something a farmer could plug into their existing equipment without needing a computer science degree,” Turcotte added.
How Irrigant Works: AI‑Powered Irrigation
At its core, Irrigant’s algorithm treats irrigation as an optimization problem. It ingests real‑time data points—soil moisture levels, evapotranspiration rates, forecasted precipitation, and crop growth stages—and runs them through a predictive model that calculates the minimum water volume required to achieve optimal yield. The system then sends alerts to farmers’ smartphones or farm‑management software, indicating when to turn on sprinklers or drip lines and for how long. By continuously learning from outcomes—such as actual soil moisture after irrigation—the model refines its recommendations, reducing both over‑ and under‑watering over time. “It’s like giving the field a personal trainer that knows exactly how much water it needs on any given day,” Trotta said.
Scale and Current Testing: 7,000 Acres
Thus far, the teenagers have deployed Irrigant on roughly 7,000 active acres across a variety of crops, including alfalfa, corn, and specialty vegetables, in Idaho and neighboring states. Early results, according to Trotta, show water use reductions ranging from 15 % to 30 % compared with conventional irrigation schedules, while maintaining or slightly improving yields. “We’ve seen fields where the soil stayed at the ideal moisture band longer, meaning fewer irrigation cycles and less pump runtime,” he noted. The testing phase also allowed the team to troubleshoot hardware integration issues, such as sensor durability in harsh weather and data connectivity in rural areas.
Broader Context: USDA Irrigation Statistics
The potential water savings from Irrigant become even more striking when placed against national irrigation statistics. The U.S. Department of Agriculture reports that irrigation accounted for 47 % of the nation’s freshwater withdrawals between 2010 and 2020, a figure that encompasses both groundwater pumping and surface‑water diversions. If AI‑driven precision irrigation could shave even a modest fraction off that total—say, 10 %—the nation could save billions of gallons annually, alleviating pressure on aquifers and reducing the energy needed to move and treat water. “There’s obviously negatives; there’s trade‑offs with anything,” Trotta conceded, “but I think there are so many subsets and positive features that this truly is a technology that could be built for good.”
Trade‑offs and Optimism: Quotes from Marco Trotta
Trotta’s candid acknowledgment of trade‑offs reflects a balanced view of AI’s environmental footprint. He points out that running AI models does require electricity and, indirectly, water for cooling data centers. Yet he argues that the net benefit can be positive if the technology is deployed at scale and paired with renewable energy sources. “If we can power the AI with solar or wind, the water cost of computation drops dramatically,” he said. Moreover, the startup is exploring edge‑computing options that process data locally on farm gateways, minimizing the need to constantly transmit large datasets to distant servers. This approach not only cuts latency but also reduces the overall energy demand of the system.
Future Plans: Launch Target 2027
Looking ahead, Trotta and Turcotte aim to transition Irrigant from a pilot project to a commercial venture by 2027. Their roadmap includes refining the AI model with broader agronomic data, expanding partnerships with agricultural extension services, and seeking funding to subsidize sensor kits for small‑holder farmers. They also intend to publish open‑access case studies demonstrating water‑savings metrics, hoping to inspire adoption beyond the initial test sites. “We want to show that AI isn’t just for tech giants; it can be a tool for stewardship on the land,” Turcotte emphasized.
Conclusion: Potential Impact on Agriculture and Water Conservation
The story of Irrigant illustrates a promising counterpoint to the narrative that AI inevitably exacerbates resource strain. By applying machine‑learning to the age‑old challenge of irrigation, two high‑schoolers are demonstrating that technology can be leveraged to conserve water, reduce energy use, and sustain agricultural productivity. If their early results hold at larger scales, the water saved could meaningfully offset the freshwater withdrawals tied to AI data centers—turning a potential liability into an environmental asset. As Utah and other western states grapple with water scarcity, innovations like Irrigant may offer a scalable, farmer‑friendly pathway toward a more sustainable future.
https://www.ksl.com/article/51625910/can-artificial-intelligence-help-the-agriculture-industry-save-water-two-high-schoolers-in-idaho-say-yes