The Application of KNN-Optimized Hybrid Models in Landslide Displacement Prediction
Open Access
Abstract
Early warning systems depend heavily on the accuracy of landslide displacement forecasts. This study focuses on the Bazimen landslide located in the Three Gorges Reservoir region and proposes a hybrid prediction approach combining support vector regression (SVR) and long short-term memory (LSTM) networks. These models are optimized via the K-Nearest Neighbor (KNN) algorithm. Initially, cumulative displacement data were separated into trend and cyclic elements using a smoothing approach. SVR and LSTM were then used to predict the components, and KNN was introduced to optimize input factors and classify the results, improving accuracy. The final KNN-optimized SVR-LSTM model effectively integrates static and dynamic features, addressing limitations of traditional models. The results show that LSTM performs better than SVR, with an RMSE and MAPE of 24.73 mm and 1.87% at monitoring point ZG111, compared to 30.71 mm and 2.15% for SVR. The sequential hybrid model based on KNN-optimized SVR and LSTM achieved the best performance, with an RMSE and MAPE of 23.11 mm and 1.68%, respectively. This integrated model, which combines multiple algorithms, offers improved prediction of landslide displacement and practical value for disaster forecasting in the Three Gorges area.Keywords
Funding Information
- National Natural Science Foundation of China (52404113, CJ20240042, BNORSG-202408, ZMF22020036)
- the Changzhou Sci&Tech Program (52404113, CJ20240042, BNORSG-202408, ZMF22020036)
- the Open Fund of Badong National Observation and Research Station of Geohazards (52404113, CJ20240042, BNORSG-202408, ZMF22020036)
- the high-level Talent Introduction Project of Changzhou University (52404113, CJ20240042, BNORSG-202408, ZMF22020036)
This publication has 63 references indexed in Scilit:
- A new early warning criterion for landslides movement assessment: Deformation Standardized Anomaly IndexBulletin of Engineering Geology and the Environment, 2024
- Constructing a region-specific rheological parameter database for probabilistic run-out analyses of loess flowslidesLandslides, 2023
- Metaheuristic-based support vector regression for landslide displacement prediction: a comparative studyLandslides, 2022
- Landslide displacement prediction based on a novel hybrid model and convolutional neural network considering time-varying factorsBulletin of Engineering Geology and the Environment, 2021
- Prediction of landslide displacement with step-like curve using variational mode decomposition and periodic neural networkBulletin of Engineering Geology and the Environment, 2021
- A comparative study of random forests and multiple linear regression in the prediction of landslide velocityLandslides, 2020
- A hybrid computing model to predict rock strength index properties using support vector regressionEngineering with Computers, 2020
- A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility predictionLandslides, 2019
- Time series analysis and long short-term memory neural network to predict landslide displacementLandslides, 2019
- Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression modelLandslides, 2017