Background: Landslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstruction of information from landslide-affecting factors. In this paper, a novel deep learning-based algorithm that combine classifiers of both deep learning and machine learning is proposed for landslide susceptibility assessment. A stacked autoencoder (StAE) and a sparse autoencoder (SpAE) both consist of an input layer for raw data, hidden layer for feature extraction, and output layer for classification and prediction. As a study case, Oda City and Gotsu City in Shimane Prefecture, southwestern Japan, were used for susceptibility assessment and prediction of landslides triggered by extreme rainfall. Results: The prediction performance was compared by analyzing real landslide and non-landslide data. The prediction performance of random forest (RF) was evaluated as better than that of a support vector machine (SVM) in traditional machine learning, so RF was combined with both StAE and SpAE. The results show that the prediction ratio of the combined classifiers was 93.2% for StAE combined with RF model and 92.5% for SpAE combined with RF model, which were higher than those of the SVM (87.4%), RF (89.7%), StAE (84.2%), and SpAE (88.2%). Conclusions: This study provides an example of combined classifiers giving a better predictive ratio than a single classifier. The asymmetric and unsupervised autoencoder combined with RF can exploit optimal non-linear features from landslide-affecting factors successfully, outperforms some conventional machine learning methods, and is promising for landslide susceptibility assessment.

Background: Thousands of landslides were triggered by the Hokkaido Eastern Iburi earthquake on 6 September 2018 in Iburi regions of Hokkaido, Northern Japan. Most of the landslides (5627 points) occurred intensively between the epicenter and the station that recorded the highest peak ground acceleration. Hundreds of aftershocks followed the major shocks. Moreover, in Iburi region, there is a high possibility of earthquakes occurring in the future. Effective prediction and susceptibility assessment methods are required for sustainable management and disaster mitigation in the study area. The aim of this study is to evaluate the performance of an autoencoder framework based on deep neural network for prediction and susceptibility assessment of regional landslides triggered by earthquakes. Results: By applying 12 sampling sizes and 12 landslide-influencing factors, 12 landslide susceptibility maps were produced using an autoencoder framework. The results of the model were evaluated using qualitative and quantitative assessment methods. The ratios of the sampling sizes on the non-landslide points randomly generated from the combination zone including plain and mountain (PM) and a mountainous only zone (M) affected different prediction abilities of the model’s performance. Conclusions: The 12 susceptibility maps, including the landslide susceptibility index, indicated the various spatial distributions of the landslide susceptibility values in both PM and the M. The highly accurate models explicitly distinguished the potential areas of landslide from stable areas without expanding the spatial extent of the potential landslide areas. The autoencoder is proved to be an effective and efficient method for extracting spatial patterns through unsupervised learning for the prediction and susceptibility assessment of landslide areas.

This study aims to enhance the accuracy and interpretability of flood susceptibility mapping (FSM) in Seoul, South Korea, by integrating automated machine learning (AutoML) with explainable artificial intelligence (XAI) techniques. Ten topographic and environmental conditioning factors were selected as model inputs. We first employed the Tree-based Pipeline Optimization Tool (TPOT), an evolutionary AutoML algorithm, to construct baseline ensemble models using Gradient Boosting (GB), Random Forest (RF), and XGBoost (XGB). These models were further fine-tuned using Bayesian optimization via Optuna. To interpret the model outcomes, SHAP (SHapley Additive exPlanations) was applied to analyze both the global and local contributions of each factor. The SHAP analysis revealed that lower elevation, slope, and stream distance, as well as higher stream density and built-up areas, were the most influential factors contributing to flood susceptibility. Moreover, interactions between these factors, such as built-up areas located on gentle slopes near streams, further intensified flood risk. The susceptibility maps were reclassified into five categories (very low to very high), and the GB model identified that approximately 15.047% of the study area falls under very-high-flood-risk zones. Among the models, the GB classifier achieved the highest performance, followed by XGB and RF. The proposed framework, which integrates TPOT, Optuna, and SHAP within an XAI pipeline, not only improves predictive capability but also offers transparent insights into feature behavior and model logic. These findings support more robust and interpretable flood risk assessments for effective disaster management in urban areas.

This study aims to improve the accuracy and interpretability of flood susceptibility mapping (FSM) by integrating automated machine learning (AutoML) with explainable artificial intelligence (XAI) frameworks. Using spatial data from Seoul, South Korea, ten topographic and environmental factors were selected as model inputs. Initially, the Tree-based Pipeline Optimization Tool (TPOT), an evolutionary AutoML algorithm, was employed to construct baseline models using Gradient Boosting (GB), Random Forest (RF), and XGBoost (XGB). Subsequently, Bayesian optimization with Optuna was applied for hyperparameter tuning, resulting in enhanced performance, with the GB model achieving the highest AUC of 0.966. To ensure interpretability, SHAP (SHapley Additive exPlanations) was used to analyze both global and local feature contributions. The SHAP summary and dependence plots identified elevation (DEM), slope, stream distance, stream density, and built-up areas (LULC_7.0) as primary drivers of flood risk. Force and waterfall plots provided instance-level insights into model behavior, validating prediction logic across various geospatial contexts. In addition, Optuna’s visualization tools, such as optimization history, parallel coordinate plots, and hyperparameter importance graphs, offered transparency into how parameter spaces affect performance. These findings highlight the critical role of hyperparameter tuning in FSM and demonstrate the synergy of combining TPOT, Optuna, and SHAP within an XAI framework. The proposed approach not only improves predictive performance but also ensures interpretability, supporting more transparent and data-driven flood risk management.