Cluster landslides and associated damage in the Dima Hasao district of Assam, India due to heavy rainfall in May 2022

Roy, Priyom; Martha, Tapas R.; Kumar, K. Vinod; Chauhan, Prakash; Rao, V.V.S. Kesava

doi:10.1007/s10346-022-01977-6

Cited by 10 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method requires landslide-vulnerable areas based on past landslide events, geology, and slope. The qualitative methods include expert scoring and analytic hierarchy methods based on numerous controlling landslide parameters (Kayastha et al, 2013;Yu et al, 2022;Meena et al, 2022;Roy et al, 2023). The quantitative method is divided based on data and physical driven parameters.…”

Section: Introductionmentioning

confidence: 99%

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Yin

Wang

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. In recent years, several catastrophic landslide events have been observed throughout the globe, significantly affecting the loss of lives, infrastructure, everyday life and livelihood. To minimize the impact of landslides and issue early warnings, landslide susceptibility maps (LSM) are essential. Aim to improve the accuracy of LSM, this study applied a random selection of non-landslide samples and low accuracy of individual classifiers using machine learning (ML) techniques, coupled with ensemble learning and ML, for LSM. China's Zigui-Badong section of the Three Gorges Reservoir area (TGRA) was considered a case study. Twelve influencing factors were selected as inputs for modelling, and the relationship between each causal factor and landslide spatial development was quantitatively analyzed. A total of 179 landslides were identified in the present study. About 70 % of the landslide pixels were randomly considered for training, and the remaining 30 % were used for validation. The Logistic Regression model (LR) was applied to produce an initial susceptibility map, and the non-landslide samples were selected within the classified low-susceptibility area. Subsequently, two ML classifiers – the Classification and Regression Tree (CART), and the Multi-Layer Perceptron (MLP), and four coupling models – the CART-Bagging, CART-Boosting, MLP-Bagging, and MLP-Boosting, were utilized for LSM. Finally, the receiver operating characteristics (ROC) curve and statistical analysis were applied for accuracy assessment. The results show that elevation and distance to rivers were the main causal factors of landslide development in the study area. The modeling accuracy of LR-MLP was calculated approx. 0.901, which is higher than the LR-CART (0.889). The LR-MLP-Boosting performed the best with an accuracy of 0.986 followed by the LR-CART-Bagging (0.973), LR-CART-Boosting (0.981), and LR-MLP-Bagging (0.978). The accuracy has been improved compared with the NO-CART, NO-MLP, NO-CART-Bagging, NO-CART-Boosting, NO-MLP-Bagging, and NO-MLP-Boosting models. Four ensemble models outperformed their corresponding classifiers, while Boosting outperforms Bagging. Overall, the combination of ensemble learning and ML effectively improved the accuracy of LSM. The LR model can effectively constrain the selection range of non-landslide samples and enhance the quality of sample selection. Our results show promise to map susceptible landslides locations which will help to monitor for an early warning of the landside.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Yin

Wang

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In Thailand, over the past decade, heavy rains have become more frequent, resulting in devastating landslides. These destructive events involve the forceful descent of rocks, soil, and debris from higher elevations, causing severe damage to house, buildings, and public infrastructure, such as roads and bridges [10][11][12]. As a result, local communities endure immense suffering and bear the brunt of the aftermath [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

“…These destructive events involve the forceful descent of rocks, soil, and debris from higher elevations, causing severe damage to house, buildings, and public infrastructure, such as roads and bridges [10][11][12]. As a result, local communities endure immense suffering and bear the brunt of the aftermath [10][11][12]. Each landslide leads to human casualties, destroys homes and structures under the weight of debris, and devastates agricultural crops.…”

Section: Introductionmentioning

confidence: 99%

Development and Application of a Real-Time GIS Digital Platform for Landslide Risk Analysis

Puttinaovarat,

Kongcharoen,

Pruitikanee

et al. 2023

IJSDP

View full text Add to dashboard Cite

In the current global context of climate change, the frequency and intensity of disasters, including landslides, are on the rise. During the initial three quarters of 2023, a notable incidence of fatalities resulting from landslides was observed across several nations, with specific instances including India reporting 26 casualties, South Korea documenting 43 fatalities, and Burma recording 31 lives lost, among others. Moreover, there has been significant damage to critical infrastructure, encompassing various forms of infrastructure, such as transportation networks and buildings. To address this challenge, researchers have turned to Geographic Information Systems (GIS) for studying and analyzing landslide risks. However, they face a limitation: the analysis results mainly consist of static maps, lacking a real-time digital platform for efficient data management and dynamic display of landslide information. This limitation hampers effective monitoring and surveillance efforts. To overcome this limitation, the present study introduces an innovative approach that integrates GIS with the development of a digital platform, effectively addressing the existing challenges. This integrated solution not only enables accurate landslide risk analysis with an impressive accuracy rate of 83.50% but also provides users with the ability to access information about specific landslide sites within a defined radius, regardless of their geographical location. Unlike previous studies, this research demonstrates the potential to address past methodological limitations by utilizing a real-time data platform. Accuracy varies based on geographic context, and landslide occurrences are influenced by diverse factors in different terrains. The digital platform elucidated in this study holds applicability for utilization by disaster prevention and relief organizations, as well as government agencies.

show abstract

“…Rainfall-triggered landslides have been a focus of scientific inquiry for decades, for instance, [14] compiled a list of more than 450 references dealing with this topic. The availability of landslide inventories following heavy rainfall and storms is rapidly increasing, covering different geographic and climatic settings (e.g., [15][16][17][18][19][20][21][22][23][24]). A relatively high number of inventories are available for Italy, such as the seminal works by [25] on the Friuli seismic sequence and [26] on rapid snowmelt in Umbria.…”

Section: Introductionmentioning

confidence: 99%

Rapid Mapping of Landslides Induced by Heavy Rainfall in the Emilia-Romagna (Italy) Region in May 2023

Ferrario,

Livio

2023

Remote Sensing

View full text Add to dashboard Cite

Heavy rainfall is a major factor for landslide triggering. Here, we present an inventory of 47,523 landslides triggered by two precipitation episodes that occurred in May 2023 in the Emilia-Romagna and conterminous regions (Italy). The landslides are manually mapped from a visual interpretation of satellite images and are mainly triggered by the second rainfall episode (16–17 May 2023); the inventory is entirely original, and the mapping is supplemented with field surveys at a few selected locations. The main goal of this paper is to present the dataset and to investigate the landslide distribution with respect to triggering (precipitation) and predisposing (land use, lithology, slope and distance from roads) factors using a statistical approach. The landslides occurred more frequently on steeper slopes and for the land use categories of “bare rocks and badlands” and woodlands. A weaker positive correlation is found for the lithological classes: silty and flysch-like units are more prone to host slope movements. The inventory presented here provides a comprehensive picture of the slope movements triggered in the study area and represents one of the most numerous rainfall-induced landslide inventories on a global scale. We claim that the inventory can support the validation of automatic products and that our results on triggering and predisposing factors can be used for modeling landslide susceptibility and more broadly for hazard purposes.

show abstract

Cluster landslides and associated damage in the Dima Hasao district of Assam, India due to heavy rainfall in May 2022

Cited by 10 publications

References 26 publications

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Development and Application of a Real-Time GIS Digital Platform for Landslide Risk Analysis

Rapid Mapping of Landslides Induced by Heavy Rainfall in the Emilia-Romagna (Italy) Region in May 2023

Contact Info

Product

Resources

About