We are very excited to announce that Digamma.ai was selected to receive Microsoft AI for Earth Innovation Grant to apply Artificial Intelligence to help understand and protect the planet.
AI for Earth awards grants to support projects that use AI to change the way people and organizations monitor, model, and manage Earth’s natural systems. To date, they have awarded 435 grants to projects with impact in 71 countries.
Our team will use the funds to continue and expand their work with U.S. Geological Survey to apply state-of-the-art Machine Learning algorithms towards the study of landslides and other natural hazards.
The main objective of the partnership between Digamma.ai and USGS is not only to find the location of the landslides, but to gain a better understanding of the landscape responses to earthquakes and large storms. This knowledge will assist in response to earthquakes that cause widespread landslides. Digamma.ai is working on producing the algorithms that are capable of automatically recognizing hazardous landscape changes through the interpretation of remote sensing, LiDAR, drone imagery, and satellite imagery data.
Landslides affect all 50 states and U.S. territories. Near populated areas, landslides present major hazards to people and property, they cause an estimated 25 to 50 deaths and $3.5 billion in damage each year in the United States alone. Globally, landslides cause billions of dollars in damages and thousands of deaths and injuries each year.
As people move into new areas of hilly or mountainous terrain, it is important to understand the nature of their potential exposure to landslide hazards, and how cities, towns, and counties can plan for land-use, engineering of new construction and infrastructure which will reduce the costs of living with landslides.
The first step towards this goal was our work on separating exposed bare rock from soil covered areas. Our initial work was focused on mapping exposed rock at eight test sites across the Sierra Nevada Mountains (California, USA) using USDA’s 0.6 m National Aerial Inventory Program (NAIP) orthoimagery. Our approach of land cover classification using convolutional neural network (CNN) showed high accuracy. We published our results in the Special Issue “Applying Earth Surface Monitoring to Investigate Climate and Land Change Interactions” of “Remote Sensing” journal.
“We wanted to expand our work to the whole are of Sierra Nevada Mountains to see how this model would apply to more diverse set of land cover types,” said Vadim Zaliva, Digamma.ai’s CEO “The resulting land cover classification map could be used by other researchers and industries like utilities and agriculture. Processing such large amount of image data requires significant computational resources and we’ve applied for Microsoft AI for Earth Innovation Grant to help us with that.”