Avalanche forecasting using neural network

Dekanova, Martina; Duchoň, František; Dekan, Martin; Kyzek, Filip; Biskupič, Marek

doi:10.1109/elektro.2018.8398359

Cited by 8 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to high complexity of snow avalanche processes, understanding the manner of governing parameters is not yet fully manifested (Singh and Ganju, 2008). However, the terrain information, such as slope, affects snow stability, the characteristics of snow cover, and avalanche danger (Bakermans and Jamieson, 2006;Dekanová et al, 2018). Sen-sitivity analysis indicated that elevation was mostly an unimportant variable (Fig.…”

Section: Sensitivity Analysismentioning

confidence: 99%

See 1 more Smart Citation

Snow avalanche hazard prediction using machine learning methods

Choubin

Borji

Mosavi

et al. 2019

Journal of Hydrology

120

View full text Add to dashboard Cite

Snow avalanches are among the most destructive natural hazards threatening human life, ecosystems, built structures, and landscapes in mountainous regions. The complexity of snow avalanche modelling has been discussed in many studies, but its modelling is not well-documented. Snow avalanche modeling in this study was done using three main categories of data, including avalanche occurrence locations, meteorological factors, and terrain characteristics. Two machine learning models, namely support vector machine (SVM) and multivariate discriminant analysis (MDA), were employed. A ratio of 70 to 30 of data was considered for calibrating and validating the models. Results indicated that both models had an excellent performance in snow avalanche modeling (area under curve, AUC > 90), although hits and misses analysis demonstrated the superior performance of MDA. Sensitivity analysis indicated that the topographic position index, slope, precipitation, and topographic wetness index were the most effective variables for modeling. A snow avalanche map indicated that the high snow avalanche hazard zone was mostly near the streams and was matched with hillsides around the water pathways. Findings of study can be helpful for land use planning, to control snow avalanche paths, and to prevent the probable hazards induced by it, and it can be a good reference for future studies on modeling snow avalanche hazards.

show abstract

Section: Sensitivity Analysismentioning

confidence: 99%

“…Singh and Ganju (2008) in-dicated the potential of ANN in detecting avalanche days in Indian Himalayas. Dekanová et al (2018) proposed different architectures of ANNs and evaluated model performance and obtained promising re-sults. However, modeling snow avalanches, especially their spatial prediction needs to be more widely addressed.…”

Section: Introductionmentioning

confidence: 99%

Snow avalanche hazard prediction using machine learning methods

Choubin

Borji

Mosavi

et al. 2019

Journal of Hydrology

120

View full text Add to dashboard Cite

show abstract

“…The experiments using a shorter hour interval of the day produced results comparable to those obtained for the whole interval, maybe even a little better. The method was inspired from the work [3]. They also applied Feed Forward Neural Networks on a more elaborate input vector and applied on a much more extensive set of data.…”

Section: Discussionmentioning

confidence: 99%

“…There are some factors and critical conditions that can trigger an avalanche. Those factors are presented in Table 1 [3][4][5][6]. Another important factor would be the avalanche history of the investigated site.…”

Section: Introductionmentioning

confidence: 99%

IoT data analysis for avalanche forecast

SEGARCEANU,

VATASOIU,

HIJON

et al. 2023

RJTS-AM

View full text Add to dashboard Cite

In mountainous regions worldwide, avalanches pose a significant hazard to infrastructure and human life. Avalanche identification and prediction have relied on labor-intensive and error-prone human observation and analysis. Artificial intelligence (AI) tools have become a promising means of improving the precision and speed of avalanche detection and prediction in recent years. To address this problem, we are developing an early warning system that utilizes Machine Learning techniques. This article examines the most recent research in AI techniques for avalanche detection and prediction, along with the details of our solution implementation. The system gathers and analyses data from various sensors, including meteorological and auditory sensors, to determine the potential risk of an avalanche. An analysis made on the data collected from the sensors placed in the selected region is also presented. Recent investigations have shown that AI algorithms can identify and forecast avalanches. The article discusses the potential benefits and challenges of implementing an early warning system for avalanches, highlighting the importance of continued research in this area. The research was carried out over 2 years within the MEWS project and is based on the fruitful collaboration between all partners involved in the project. The IoT stations used in the research were located in Norway. The current paper presents an analysis of the data collected in the project and a method for avalanche prediction using Feed Forward Neural Networks.

show abstract

“…Our results indicate that topographic factors (TPI, slope, LS, VD, convexity, aspect and plan curvature) along with climatic factors (temperature), geological factors (lithology) and hydrological factors (SPI, DD, distance to river and TWI) are responsible for snow avalanche occurring in the study area. Hydrologically, terrain factors such as TPI and slope angle (> 30 degrees) are the main factors that a?ects snowpack stability [48], [57], [99]; therefore, these factors can control or accelerate the avalanche occurrences [55], [100]. Few studies have been conducted on snow avalanche susceptibility mapping because of its high complexity [101].…”

Section: B the Most Important Factors For Snow Avalanche Occurrencementioning

confidence: 99%

Towards an Ensemble Machine Learning Model of Random Subspace Based Functional Tree Classifier for Snow Avalanche Susceptibility Mapping

et al. 2020

View full text Add to dashboard Cite

Snow avalanche as a natural disaster severely affects socio-economic and geomorphic processes through damaging ecosystems, vegetation, landscape, infrastructures, transportation networks, and human life. Modeling the snow avalanche has been seen as an essential approach for understanding the mountainous landscape dynamics to assess hazard susceptibility leading to effective mitigation and resilience. Therefore, the main aim of this study is to introduce and implement an ensemble machine learning model of random subspace (RS) based on a classifier, functional tree (FT), named RSFT model for snow avalanche susceptibility mapping at Karaj Watershed, Iran. According to the best knowledge of literature, the proposed model, RSFT, has not earlier been introduced and implemented for snow avalanche modeling and mapping over the world. Four benchmark models, including logistic regression (LR), logistic model tree (LMT), alternating decision tree (ADT), and functional trees (FT) models were used to check the goodnessof-fit and prediction accuracy of the proposed model. To achieve this objective, the most important factors among many climatic, topographic, lithologic, and hydrologic factors, which affect the snow accumulation and snow avalanche occurrence, were determined by the information gain ratio (IGR) technique. The goodness-of-fit and prediction accuracy of the models were evaluated by some statistical-based indexes including, sensitivity, specificity, accuracy, kappa, and area under the ROC curve, Friedman and Wilcoxon sign rank tests. Results indicated that the ensemble proposed model (RSFT), had the highest performance (Sensitivity = 94.1%, Specificity = 92.4%, Accuracy = 93.3%, and Kappa = 0.782) rather than the other soft-computing benchmark models. The snow avalanche susceptibility maps indicated that the high and very high susceptibility avalanche areas are located in the north and northeast parts of the study area, which have a higher elevation with more precipitation and lower temperatures. INDEX TERMSSnow avalanche, susceptibility mapping, ensemble approach, feature selection. AMIRHOSEIN MOSAVI graduated from Kingston University London, U.K. He received the Ph.D. degree in applied informatics. He is currently a Data Scientist in climate change, sustainability, and hazard prediction. He is a Senior Research Fellow with Oxford Brookes University. He is also an Alexander von Humboldt Research Fellow in big data, the IoT, and machine learning. He was a recipient of the Green-Talent Award, the UNESCO Young Scientist Award, the ERCIM Alain Bensoussan Fellowship Award, the Campus France Fellowship Award, the Campus Hungary Fellowship Award, and the Endeavour-Australia Leadership.

show abstract

Avalanche forecasting using neural network

Cited by 8 publications

References 2 publications

Snow avalanche hazard prediction using machine learning methods

Snow avalanche hazard prediction using machine learning methods

IoT data analysis for avalanche forecast

Towards an Ensemble Machine Learning Model of Random Subspace Based Functional Tree Classifier for Snow Avalanche Susceptibility Mapping

Contact Info

Product

Resources

About