Global climate change has increased severe torrential hazards, particularly debris flows in mountainous regions. After floods and earthquakes, debris flows are the most devastating natural hazard in the world. The effects of debris flow on human life and built environments necessitate reconsidering current infrastructure planning, engineering, and risk management practices. Hence, the vulnerability of elements at risk is critical for effective risk reduction systems. Therefore, this article reviews the existing physical vulnerability approach of infrastructure, particularly building toward debris flow hazards in the last 20 years. Furthermore, uncertainties associated with the vulnerability assessment and their quantification techniques have also been discussed in detail. It was found that matrices, curves, and indicators have been extensively used for vulnerability assessment approaches in the last two decades. However, if aleatory and epistemic uncertainties are not quantified or conserved in the vulnerability assessment process, it makes the system inefficient and unreliable. Moreover, data requirements, strengths, and weaknesses of approaches presented herein are highlighted with case studies. Finally, a thorough discussion on future needs in the field of risk assessment methodologies is highlighted by considering uncertainties into account.

This paper describes the development and validation of landslides susceptibility models for mountainous regions using advanced data mining techniques. The investigation was carried out to ascertain the effectiveness of Naïve Bayes Multinomial (NBM) and Random Trees (RT) in landslide susceptibility mapping. The NBM is an advancement of the frequently used Naïve Bayes classifiers, while the RT was built to overcome the limitations of the traditional forest classifiers. A geospatial database for this investigation comprises 148 landslide locations influenced by ten (10) landslide conditioning factors. The factors (Slope Angle, Slopes Elevation, Slope Aspect, Plan curvature, Profile Curvature, Lithology, Soil type, Stream power index (SPI), Sediment transport index (STI), and Rainfall precipitation) were drawn using a Multi Collinearity Decision Making (MCDM) technique. A Frequency Ratio (FR) analysis was used to obtain the relative significance of the factors in the slides. Predictive models were also developed by quantifying these models using data mining techniques. A section of the entire geospatial data (70%) was used as training datasets, while the remaining part of the data (30%) was used to validate the trained datasets. SVM, RT, and NBM algorithms were used to produce predicted datasets from the training datasets. These predicted datasets were used to develop the Landslides Susceptibility Models. A comparative assessment between the two classifiers against the famous traditional learning algorithm, the Support vector machines (SVM), was conducted. Model performance evaluators such as the AUROC, RSME, F-measure, MAE, and ACC were employed to check the predictive capabilities and accuracies of the models. The indices indicated that the SVM model performed better than the other two algorithms in both training and validation datasets. Further analysis and comparison of the models reveal that the new data mining techniques are reliable for landslide susceptibility. Simultaneously, the traditional algorithm is also useful and remains relevant, especially with similar site conditions. This study has provided insights on better planning and development and provision of mitigation strategies and further analysis on landslides in the study area, particularly in cases of limited data availability. Graphical Abstract

Flooding is one of the most prevalent natural disasters affecting people worldwide. Flooding is a devastating natural disaster in Malaysia regarding the number of people affected, socioeconomic damage, severity, and scale of the impact. Urban flooding is currently a major concern due to the possible consequences and frequency with which it occurs in urban areas as urbanization and population increase. Due to the paved surfaces, paved roads, high population, and buildings that prevent water infiltration and movement to the nearby river, urban floods pose a significant threat to the sustainability of lives and properties in the city. The recent floods in Kuala Lumpur in December 2021 and January 2022 affected many buildings, infrastructure, and lives. As a result, this city needs to model the susceptibility of flood-prone areas for an early warning system against future flood hazards in Kuala Lumpur. This is because flooding can never be eradicated but can be minimized and managed. Therefore, this study integrates geospatial technology and a statistical model (logistic regression) to assess flood hazards in Kuala Lumpur. Ten flood conditioning factors such as altitude, slope, TWI, drainage density, distance to river, LULC, NDVI, NDWI, rainfall and MNDWI were used to predict the areas susceptible to flood. The prediction shows an overall accuracy of 0.84, precision of 0.91, recall of 0.72, and F1-score of 0.80. Distance to river, MNDWI, TWI, and LULC are the critical variables that showed high significance in the model prediction. Thus, stakeholders should prioritize urban planning and increase the drainage system to avoid flood effects.