Applying machine learning methods to avalanche forecasting
Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dim...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2008
|
Subjects: | |
Online Access: | https://doi.org/10.5167/uzh-25644 https://serval.unil.ch/notice/serval:BIB_BDF164BCA522 |
id |
fttriple:oai:gotriple.eu:10670/1.65u3cd |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:10670/1.65u3cd 2023-05-15T13:29:17+02:00 Applying machine learning methods to avalanche forecasting Pozdnoukhov, A. Purves, R.S. Kanevski, M. 2008-01-01 https://doi.org/10.5167/uzh-25644 https://serval.unil.ch/notice/serval:BIB_BDF164BCA522 en eng doi:10.5167/uzh-25644 urn:issn:0260-3055 10670/1.65u3cd https://serval.unil.ch/notice/serval:BIB_BDF164BCA522 undefined Serveur académique Lausannois Annals of Glaciology, vol. 49, pp. 107-113 demo geo Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2008 fttriple https://doi.org/10.5167/uzh-25644 2023-01-22T17:45:37Z Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work. Article in Journal/Newspaper Annals of Glaciology Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English |
topic |
demo geo |
spellingShingle |
demo geo Pozdnoukhov, A. Purves, R.S. Kanevski, M. Applying machine learning methods to avalanche forecasting |
topic_facet |
demo geo |
description |
Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work. |
format |
Article in Journal/Newspaper |
author |
Pozdnoukhov, A. Purves, R.S. Kanevski, M. |
author_facet |
Pozdnoukhov, A. Purves, R.S. Kanevski, M. |
author_sort |
Pozdnoukhov, A. |
title |
Applying machine learning methods to avalanche forecasting |
title_short |
Applying machine learning methods to avalanche forecasting |
title_full |
Applying machine learning methods to avalanche forecasting |
title_fullStr |
Applying machine learning methods to avalanche forecasting |
title_full_unstemmed |
Applying machine learning methods to avalanche forecasting |
title_sort |
applying machine learning methods to avalanche forecasting |
publishDate |
2008 |
url |
https://doi.org/10.5167/uzh-25644 https://serval.unil.ch/notice/serval:BIB_BDF164BCA522 |
genre |
Annals of Glaciology |
genre_facet |
Annals of Glaciology |
op_source |
Serveur académique Lausannois Annals of Glaciology, vol. 49, pp. 107-113 |
op_relation |
doi:10.5167/uzh-25644 urn:issn:0260-3055 10670/1.65u3cd https://serval.unil.ch/notice/serval:BIB_BDF164BCA522 |
op_rights |
undefined |
op_doi |
https://doi.org/10.5167/uzh-25644 |
_version_ |
1765999647861506048 |