Meet Ishaan Dokania, sixth-grader whose AI model spots lithium with 89% accuracy
Ishaan Dokania, a sixth-grader from Oregon, is exploring lithium resource identification using satellite imagery and machine learning. His project reached 89% accuracy in predicting potential lithium deposits after addressing data noise and testing various algorithms. Ishaan's innovative approach combines geology and remote sensing to streamline mineral exploration. He is competing as a finalist…
Sixth-grader Ishaan Dokania from Oregon has developed an AI model that accurately identifies potential lithium deposits with 89% precision using satellite imagery and geological data. The 30 finalists in the 2026 Thermo Fisher Scientific Junior Innovators Challenge, Ishaan's project, "Eye in the Sky: From Pixels to Predictions for Lithium and Beyond," utilizes visual and environmental patterns from satellite images to predict lithium deposit locations.
After addressing sources of noise, such as plants experiencing heat stress and overlapping satellite maps, his model detected lithium deposits with 89% accuracy. Though the system doesn't confirm undiscovered lithium deposits, it narrows down potential locations for further investigation, making remote sensing a valuable tool for mineral exploration.
Written by urgent.news from Times of India's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
