Russian Scientists Develop Neural Network Algorithm to Locate Sand and Peat Deposits
Researchers at the Trofimuk Institute of Petroleum Geology and Geophysics of the Siberian Branch of the Russian Academy of Sciences have developed a neural network algorithm that uses 3D seismic survey data to identify sand and peat deposits.
The new algorithm analyzes data from 3D seismic surveys to locate sand and peat deposits. According to the researchers, it is resistant to the noise and artifacts commonly found in seismic recordings and does not require retraining for each new survey area. The system can identify mineral deposits at depths of more than 100 meters (330 feet) without the need for additional field exploration.
The approach is expected to be particularly valuable for resource development projects in Russia's northern regions, where major infrastructure construction requires large volumes of locally sourced building materials. Locating nearby sand quarries can significantly reduce the cost of infrastructure projects.
Using the new method, researchers have already identified promising locations for future sand and peat quarries in the southeastern part of the Yamalo-Nenets Autonomous Okrug, close to planned infrastructure sites.
