Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning
A procedure aimed at forecasting the velocity trend of a landslide for a period of some hours to one or two days is proposed here together with its MATLAB implementation. The method is based on continuous wavelet transform (CWT) and convolutional neural network (CNN) applied to rainfall and velocity...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Geosciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3263/12/5/205 |
_version_ | 1797499600042459136 |
---|---|
author | Giordano Teza Simonetta Cola Lorenzo Brezzi Antonio Galgaro |
author_facet | Giordano Teza Simonetta Cola Lorenzo Brezzi Antonio Galgaro |
author_sort | Giordano Teza |
collection | DOAJ |
description | A procedure aimed at forecasting the velocity trend of a landslide for a period of some hours to one or two days is proposed here together with its MATLAB implementation. The method is based on continuous wavelet transform (CWT) and convolutional neural network (CNN) applied to rainfall and velocity time series provided by a real-time monitoring system. It is aimed at recognizing the conditions that induce a strong increase, or even a significant decrease, in the average velocity of the unstable slope. For each evaluation time, the rainfall and velocity scalograms related to the previous days (e.g., two weeks) are computed by means of CWT. A CNN recognizes the velocity trend defined in the training stage corresponds to these scalograms. In this way, forecasts about the start, persistence, and end of a critical event can be provided to the decision makers. An application of the toolbox to a landslide (Perarolo di Cadore landslide, Eastern Alps, Italy) is also briefly described to show how the parameters can be chosen in a real case and the corresponding performance. |
first_indexed | 2024-03-10T03:49:43Z |
format | Article |
id | doaj.art-ddd659e1654a42a69cf63438b3bc3892 |
institution | Directory Open Access Journal |
issn | 2076-3263 |
language | English |
last_indexed | 2024-03-10T03:49:43Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Geosciences |
spelling | doaj.art-ddd659e1654a42a69cf63438b3bc38922023-11-23T11:12:14ZengMDPI AGGeosciences2076-32632022-05-0112520510.3390/geosciences12050205Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep LearningGiordano Teza0Simonetta Cola1Lorenzo Brezzi2Antonio Galgaro3Department of Physics and Astronomy, Alma Mater Studiorum University of Bologna, Viale Berti Pichat 6/2, 40127 Bologna, ItalyDepartment of Civil, Environmental and Architectural Engineering, University of Padua, Via Marzolo, 9, 35121 Padova, ItalyDepartment of Civil, Environmental and Architectural Engineering, University of Padua, Via Marzolo, 9, 35121 Padova, ItalyDepartment of Geosciences, University of Padua, Via Gradenigo, 6, 35131 Padova, ItalyA procedure aimed at forecasting the velocity trend of a landslide for a period of some hours to one or two days is proposed here together with its MATLAB implementation. The method is based on continuous wavelet transform (CWT) and convolutional neural network (CNN) applied to rainfall and velocity time series provided by a real-time monitoring system. It is aimed at recognizing the conditions that induce a strong increase, or even a significant decrease, in the average velocity of the unstable slope. For each evaluation time, the rainfall and velocity scalograms related to the previous days (e.g., two weeks) are computed by means of CWT. A CNN recognizes the velocity trend defined in the training stage corresponds to these scalograms. In this way, forecasts about the start, persistence, and end of a critical event can be provided to the decision makers. An application of the toolbox to a landslide (Perarolo di Cadore landslide, Eastern Alps, Italy) is also briefly described to show how the parameters can be chosen in a real case and the corresponding performance.https://www.mdpi.com/2076-3263/12/5/205continuous wavelet transformscalogramdeep learningconvolutional neural networkrainfall time serieslandslide velocity |
spellingShingle | Giordano Teza Simonetta Cola Lorenzo Brezzi Antonio Galgaro Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning Geosciences continuous wavelet transform scalogram deep learning convolutional neural network rainfall time series landslide velocity |
title | Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning |
title_full | Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning |
title_fullStr | Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning |
title_full_unstemmed | Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning |
title_short | Wadenow: A Matlab Toolbox for Early Forecasting of the Velocity Trend of a Rainfall-Triggered Landslide by Means of Continuous Wavelet Transform and Deep Learning |
title_sort | wadenow a matlab toolbox for early forecasting of the velocity trend of a rainfall triggered landslide by means of continuous wavelet transform and deep learning |
topic | continuous wavelet transform scalogram deep learning convolutional neural network rainfall time series landslide velocity |
url | https://www.mdpi.com/2076-3263/12/5/205 |
work_keys_str_mv | AT giordanoteza wadenowamatlabtoolboxforearlyforecastingofthevelocitytrendofarainfalltriggeredlandslidebymeansofcontinuouswavelettransformanddeeplearning AT simonettacola wadenowamatlabtoolboxforearlyforecastingofthevelocitytrendofarainfalltriggeredlandslidebymeansofcontinuouswavelettransformanddeeplearning AT lorenzobrezzi wadenowamatlabtoolboxforearlyforecastingofthevelocitytrendofarainfalltriggeredlandslidebymeansofcontinuouswavelettransformanddeeplearning AT antoniogalgaro wadenowamatlabtoolboxforearlyforecastingofthevelocitytrendofarainfalltriggeredlandslidebymeansofcontinuouswavelettransformanddeeplearning |