Google is making an expansion of its flood prediction AI for regions in India for the coming monsoon season to cover more than 11,000 square kilometers in areas along the Ganga and Brahmaputra rivers, the company announced today. Approximately 20% of global flood fatalities occur in India.

Since the start of Flood Forecast initiative trials in the Patna region first began about a year ago, 800,000 notifications were sent to smartphone users. Alerts are also sent to a human network of volunteers with the nonprofit SEEDS to spread emergency warning news among people without phones.

The expansion will be supported by new forecast methodologies like a recently made approach to create Digital Elevation Models (DEMs) such as optimizing its inundation model to work with tensor processing units (TPU) and supply predictions 85 times faster than the use of CPUs alone.

“Correlating and aligning the images in large batches, we adjust their camera models (and simultaneously solve for a coarse terrain) to make the images mutually consistent. Then, we create a depth map for each image. To make the elevation map we optimally fuse the depth maps together at each location,” Google said in a blog post. “For additional efficiency improvements, we’re also looking at using machine learning to replace some of the physics-based algorithms, extending data-driven discretization to two-dimensional hydraulic models, so we can support even larger grids and cover even more people.”

In addition to use of TPUs, to continue to improve the accuracy of flood predictions, Google began to use imagery from European Space Agency Sentinel-1 satellite constellation.

In January, Google said flood predictions achieved 75% accuracy. Model prediction levels have remained the same, a company spokesperson told VentureBeat in an email.

Flood prediction systems could become increasingly important as climate change worsens. In other AI models to protect people and property from natural disasters, researchers this week published a paper on machine learning to predict large wildfires.