Recurrent Neural Network Based IOS Mobile Applications for Slope Safety Assessment

Every year, landslides result in immense casualties and considerable financial losses globally. They are classified as one of the most critical categories of natural disasters. Factors, such as rainfall and earthquakes, can trigger landslides. Generally, practicing engineers use numerical simulations, visual inspections, and in some cases stability charts to assess slopes. However, these techniques are usually not user-friendly for quick assessment of slopes. This study ingeniously creates two recurrent neural network IOS-based mobile applications for the safety assessment of rock slopes. The first App evaluates the safety of slopes considering the earthquake effect, and the second App evaluates the pore water pressure effect on slope safety. Numerical methods were first used to evaluate the stability number of thousands of slope cases considering various geometric and rock mass properties, as well as external factors. The datasets are then employed in the prediction models. The Keras-based RNN models were converted into Core ML formats and then used to develop IOS mobile applications. The Apps can successfully assess the safety of rock slopes while maintaining good accuracy and convenience. Furthermore, the Apps may help reduce future risks and losses associated with landslides by providing quick access to data, which can aid early response action.