Avalanche forecasting — an expert system approach
Abstract Avalanche forecasting for a given region is still a difficult task involving great responsibility. Any tools assisting the expert in the decision-making process are welcome. However, an efficient and successful tool should meet the needs of the forecaster. With this in mind, two models, wer...
Published in: | Journal of Glaciology |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press (CUP)
1996
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1017/s0022143000004172 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0022143000004172 |
id |
crcambridgeupr:10.1017/s0022143000004172 |
---|---|
record_format |
openpolar |
spelling |
crcambridgeupr:10.1017/s0022143000004172 2024-04-28T08:26:47+00:00 Avalanche forecasting — an expert system approach Schweizer, Jürg Föhn, Paul M. B. 1996 http://dx.doi.org/10.1017/s0022143000004172 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0022143000004172 en eng Cambridge University Press (CUP) Journal of Glaciology volume 42, issue 141, page 318-332 ISSN 0022-1430 1727-5652 Earth-Surface Processes journal-article 1996 crcambridgeupr https://doi.org/10.1017/s0022143000004172 2024-04-09T06:56:19Z Abstract Avalanche forecasting for a given region is still a difficult task involving great responsibility. Any tools assisting the expert in the decision-making process are welcome. However, an efficient and successful tool should meet the needs of the forecaster. With this in mind, two models, were developed using a commercially available software: CYBERTEK-COGENSYS TM , a judgment processor for inductive decision-making–a principally data-based expert system. Using weather, snow and snow-cover data as input parameters, the models evaluate for a region the degree of avalanche hazard, the aspect and altitude of the most dangerous slopes. The output result is based on the snow-cover stability. The new models were developed and have been tested in the Davos region (Swiss Alps) for several years. To rate the models, their output is compared to the a posteriori verified hazard. the first model is purely data-based. Compared to other statistical models, the differences are: more input information about the snow cover from snow profiles and Rutschblock tests, the specific method to search for similar situations, the concise output result and the knowledge base that includes the verified degree of avalanche hazard. The performance is about 60%. The second, more-refined model, is both data- and rule-based. It tries to model the decision-making process of a pragmatic expert and has a performance of about 70%, which is comparable to the accuracy of the public warning. Article in Journal/Newspaper Journal of Glaciology Cambridge University Press Journal of Glaciology 42 141 318 332 |
institution |
Open Polar |
collection |
Cambridge University Press |
op_collection_id |
crcambridgeupr |
language |
English |
topic |
Earth-Surface Processes |
spellingShingle |
Earth-Surface Processes Schweizer, Jürg Föhn, Paul M. B. Avalanche forecasting — an expert system approach |
topic_facet |
Earth-Surface Processes |
description |
Abstract Avalanche forecasting for a given region is still a difficult task involving great responsibility. Any tools assisting the expert in the decision-making process are welcome. However, an efficient and successful tool should meet the needs of the forecaster. With this in mind, two models, were developed using a commercially available software: CYBERTEK-COGENSYS TM , a judgment processor for inductive decision-making–a principally data-based expert system. Using weather, snow and snow-cover data as input parameters, the models evaluate for a region the degree of avalanche hazard, the aspect and altitude of the most dangerous slopes. The output result is based on the snow-cover stability. The new models were developed and have been tested in the Davos region (Swiss Alps) for several years. To rate the models, their output is compared to the a posteriori verified hazard. the first model is purely data-based. Compared to other statistical models, the differences are: more input information about the snow cover from snow profiles and Rutschblock tests, the specific method to search for similar situations, the concise output result and the knowledge base that includes the verified degree of avalanche hazard. The performance is about 60%. The second, more-refined model, is both data- and rule-based. It tries to model the decision-making process of a pragmatic expert and has a performance of about 70%, which is comparable to the accuracy of the public warning. |
format |
Article in Journal/Newspaper |
author |
Schweizer, Jürg Föhn, Paul M. B. |
author_facet |
Schweizer, Jürg Föhn, Paul M. B. |
author_sort |
Schweizer, Jürg |
title |
Avalanche forecasting — an expert system approach |
title_short |
Avalanche forecasting — an expert system approach |
title_full |
Avalanche forecasting — an expert system approach |
title_fullStr |
Avalanche forecasting — an expert system approach |
title_full_unstemmed |
Avalanche forecasting — an expert system approach |
title_sort |
avalanche forecasting — an expert system approach |
publisher |
Cambridge University Press (CUP) |
publishDate |
1996 |
url |
http://dx.doi.org/10.1017/s0022143000004172 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0022143000004172 |
genre |
Journal of Glaciology |
genre_facet |
Journal of Glaciology |
op_source |
Journal of Glaciology volume 42, issue 141, page 318-332 ISSN 0022-1430 1727-5652 |
op_doi |
https://doi.org/10.1017/s0022143000004172 |
container_title |
Journal of Glaciology |
container_volume |
42 |
container_issue |
141 |
container_start_page |
318 |
op_container_end_page |
332 |
_version_ |
1797586032519020544 |