Predicting Deep-Seated Landslide Displacements in Mountains through the Integration of Convolutional Neural Networks and Age of Exploration-Inspired Optimizer

Abstract

Abstract. Deep-seated landslides, becoming increasingly frequent due to changing climate patterns, pose significant risks to human life and infrastructure. This research contributes to developing predictive early warning systems for deep-seated slope displacements, employing advanced computational models for environmental risk management. Our novel framework integrates machine learning, time series deep learning, and convolutional neural networks (CNN), enhanced by the Age of Exploration-Inspired Optimizer (AEIO) algorithm. Our approach demonstrates exceptional forecasting capabilities by utilizing eight years of comprehensive data—including displacement, groundwater levels, and meteorological information from the Lushan Mountain region in Taiwan. The AEIO-MobileNet model stands out for its precision in predicting imminent slope displacements with a mean absolute percentage error (MAPE) of 2.81 %. These advancements significantly enhance geohazard informatics by providing reliable and efficient landslide risk assessment and management tools. These safeguard road networks, construction projects, and infrastructure within vulnerable slope areas.