This article examines whether data from remote sensing satellites can be used to predict lithium mine output. We use pixel classification of land cover to measure long-term mine expansion and nightly light emissions to measure short-term operational activities. We find a strong correlation between satellite data in one period and individual lithium mine production volumes in the following period. Our rapid and cost-effective method of forecasting lithium mine production can help decision-makers in companies that rely on lithium, and policymakers seeking to ensure adequate lithium supplies in their countries.