Meet Ishaan Dokania, the Indian-origin Beaverton sixth-grader who trained a machine-learning model on satellite data to spot potential lithium deposits with 89% accuracy

Ishaan Dokania, the Indian-origin Beaverton sixth-grader (Image Credit: Society for Science)

A sixth-grade student from Oregon is using satellite images and machine learning to explore a problem that is becoming increasingly important as demand for lithium grows. Ishaan Dokania, a sixth-grader at Willamette Valley Academy in Beaverton, is among the 30 finalists in the 2026 Thermo Fisher Scientific Junior Innovators Challenge. According to the Society for Science, Ishaan developed a project called “Eye in the Sky: From Pixels to Predictions for Lithium and Beyond”, using satellite imagery and geological data to train a machine-learning model that could identify potential lithium deposits. After addressing sources of noise in the data, his model detected lithium deposits with 89% accuracy.

How Ishaan connected satellite images with mineral exploration

Ishaan’s project began with two interests that might initially seem unrelated: remote sensing and rocks and minerals. While participating in a Science Olympiad competition, he studied both subjects and began thinking about whether they could be combined to solve a practical problem. That question led him to lithium exploration.Lithium is an important component in many modern technologies, particularly batteries used in electronics and energy-storage systems. Ishaan became interested in the difficulties involved in finding new lithium resources and wondered whether satellite imagery could make the search more efficient. Rather than examining geological locations one by one, he explored whether computers could identify visual and environmental patterns associated with known lithium deposits. His project was titled “Eye in the Sky: From Pixels to Predictions for Lithium and Beyond.” The title reflects the central idea behind his work: using information captured from above the Earth’s surface and processing it through an artificial intelligence model to identify locations that may warrant further investigation.

Training the model with satellite and geological data

To build the system, Ishaan used satellite-image information from Google Earth Engine along with data from the U.S. Geological Survey’s Mineral Resources Data System. The Society for Science states that he identified features that could help his machine-learning model predict where lithium deposits might occur. He then tested several different machine-learning algorithms rather than relying on a single approach. This was an important part of the project because satellite imagery contains enormous amounts of information. Not every pattern visible in an image is necessarily connected to the mineral a researcher is trying to locate.A model can therefore produce misleading results if it learns to associate lithium deposits with something else that happens to appear in the same locations. Ishaan encountered exactly that problem during his testing.

Why plants and heat could confuse the AI

One of the challenges he discovered involved plants experiencing heat stress. According to the Society for Science, some models produced biased readings when they detected vegetation under heat stress. The system could interpret a hot region as an indication of lithium, even when lithium was not actually present. That created what researchers would describe as noise in the data. If those misleading signals remained in the model, they could reduce its ability to distinguish genuine geological patterns from unrelated features.Ishaan therefore worked on identifying and removing those sources of noise. He used a test called Leave One Feature Out, which allowed him to examine the contribution of individual features and determine whether particular inputs were contributing to inaccurate predictions. Society for Science also reports that he discovered another complication: using different satellites could produce overlapping maps. These problems meant that building the model was not simply a matter of feeding satellite images into an AI system and waiting for an answer. Ishaan had to examine why the model was making particular predictions and adjust the information being used.

The model reached 89% accuracy

After addressing the sources of noise he identified, Ishaan’s model was able to detect lithium deposits with 89% accuracy, according to Society for Science. The figure represents the result of his project rather than evidence that the system can independently confirm an undiscovered lithium deposit. A satellite-based prediction would still need geological investigation and other forms of verification before a location could be established as a lithium resource. The value of the project lies in the approach: using existing satellite and geological datasets to narrow down locations that could potentially deserve closer examination. That could make remote sensing a useful tool for mineral exploration, particularly when researchers need to analyse large geographic areas.

From a school project to a national STEM competition

Ishaan’s research has now taken him beyond the school-level competition where the idea began. He was selected as one of 30 finalists in the 2026 Thermo Fisher Scientific Junior Innovators Challenge, run by Society for Science and sponsored by Thermo Fisher Scientific. The finalists were selected from the competition’s Top 300 Junior Innovators. The competition is designed for students in grades six through eight. Society for Science describes it as a national STEM research competition for middle-school students. The 30 finalists represent 17 U.S. states and Puerto Rico and will travel to Washington, D.C., for Finals Week from October 23 to 28. Each finalist receives a $500 cash award, while the students will compete for more than $100,000 in prizes during the final stage of the competition.For Ishaan, however, the lithium project also reflects a broader interest in engineering. Outside science competitions, he enjoys playing badminton with his father and younger brother. Society for Science says he hopes to become an aeronautical engineer, an ambition that fits with his interest in aircraft and how their systems work. His lithium research shows how a middle-school science project can bring together several fields at once: geology, satellite remote sensing, data analysis and machine learning. Instead of treating those subjects separately, Ishaan used them together to investigate whether information already available from space could help scientists search for resources hidden beneath the Earth’s surface.