Journal of Intelligent Systems and Internet of Things JISIoT 2690-6791 2769-786X 10.54216/JISIoT https://www.americaspg.com/journals/show/3204 2019 2019 Department of Computing Technologies, SRM Institute of science and Technology, Kattankulathur, Chennai, India Domi Domi Department of Computing Technologies, SRM Institute of science and Technology, Kattankulathur, Chennai, India G. Usha Landslides establish a main geologic threat of strong concern in many parts of the world. The vigor of soil, rocks, or other rubbish moving down a slope can destroy whatever in its track. Landslides happen in an extensive variety of geological and structural settings, geomechanical contexts, and as a response to numerous triggering and loading procedures. They are frequently related to other main natural disasters like floods, earthquakes, and volcanic waves. Landslides occasionally attack without noticeable warning. While only some cases have been examined the earlier, modern monitoring models are certain to deliver a wealth of novel quantitative observations based on SAR (synthetic aperture radar) and GPS technology for mapping the surface velocity area. This study emphasizes the latent of incorporating advanced machine learning (ML) models with geophysical data to improve prediction of landslides and risk management strategies. This study develops a Predicting Landslides with frictional-based Deep Learning using Spider Wasp Optimizer (PLFFDL-SWO) Method. The major intention of the PLFFDL-SWO technique lies in the robust frictional force based on predicting landslides. In the presented PLFFDL-SWO model, Z-score normalization is performed to transform the raw data into compatible format. Then, the long short-term memory (LSTM) model is utilized for the prediction of landslides. LSTM is a recurrent neural network (RNN) type, for predicting landslides based on frictional force data. Traditional landslide prediction methods often struggle with temporal dynamics and nonlinear relationships inherent in geophysical data. Finally, the spider wasp optimizer (SWO) algorithm is exploited for the optimal hyper parameter adjustment of the LSTM model to improve prediction accuracy. The experimentation result investigation of the PLFFDL-SWO technique can be examined by employing a benchmark dataset. The simulation outcomes reported the supremacy of the PLFFDL-SWO technique under different measures   2024 2024 293 304 10.54216/JISIoT.140123 https://www.americaspg.com/articleinfo/18/show/3204