Deep convolutional neural networks with Bee Collecting Pollen Algorithm (BCPA)-based landslide data balancing and spatial prediction
Authors:
- 10 January 2024
- journal article
- research article
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 46 (1) , 597-617
Abstract
Predicting the landslide-prone area is critical for various applications, including emergency response, land planning, and disaster mitigation. There needs to be a thorough landslide inventory in current studies and appropriate sampling uncertainty issues. Landslide risk mapping has expanded significantly as machine learning techniques have developed. However, one of the primary issues in Landslide Prediction is data imbalance (DI). This is problematic since it is challenging or expensive to generate an accurate inventory map of landslides based on previous data. This study proposes a novel landslide prediction method using Generative Adversarial Networks (GAN) for generating the synthetic data, Synthetic Minority Oversampling Technique (SMOTE) for overcoming the data imbalance problem, and Bee Collecting Pollen Algorithm (BCPA) for feature extraction. Combining 184 landslides and ten criteria, including topographic wetness index (TWI), aspect, distance from the road, total curvature, sediment transport index (STI), height, slope, stream, lithology, and slope length, a geographical database was produced. The data was generated using GAN, a Deep Convolutional Neural Network (DCNN) technique to populate the dataset. The proposed DCNN-BCPA approach findings were merged with current machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), k-Nearest Neighbours (k-NN), Decision Trees (DT), Support Vector Machine (SVM), logistic regression (LR). The model’s accuracy, precision, recall, f-score, and RMSE were measured using the following metrics: 92.675%, 96.298%, 90.536%, 96.637%, and 45.623%. This study suggests that harmonizing landslide data may have a substantial impact on the predictive capabilities of machine learning models.Keywords
This publication has 27 references indexed in Scilit:
- Local-scale landslide susceptibility mapping using the B-GeoSVC modelLandslides, 2019
- Landslide Susceptibility Mapping Based on Weighted Gradient Boosting Decision Tree in Wanzhou Section of the Three Gorges Reservoir Area (China)ISPRS International Journal of Geo-Information, 2018
- Social and environmental impacts of landslidesInnovative Infrastructure Solutions, 2018
- Landslide Susceptibility Mapping in Tegucigalpa, Honduras, Using Data Mining Methods2018
- Global fatal landslide occurrence from 2004 to 2016Natural Hazards and Earth System Sciences, 2018
- Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methodsGeomorphology, 2018
- Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)Geomatics, Natural Hazards and Risk, 2017
- Optimized Neural Architecture for Automatic Landslide Detection from High‐Resolution Airborne Laser Scanning DataApplied Sciences, 2017
- Learning from class-imbalanced data: Review of methods and applicationsExpert Systems with Applications, 2017
- The influence of systematically incomplete shallow landslide inventories on statistical susceptibility models and suggestions for improvementsLandslides, 2017