Applying machine learning methods to avalanche forecasting

Authors: Pozdnoukhov, A.; Purves, R.S.; Kanevski, M.

Source: Annals of Glaciology, Volume 49, Number 1, October 2008 , pp. 107-113(7)

Publisher: International Glaciological Society

Key:

- Free Content

- New Content

- Subscribed Content

- Free Trial Content

Abstract:

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 (SVMs) to a dataset from Lochaber, Scotland, UK, to assess their applicability in avalanche forecasting. 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 that were comparable with NN for categorical and probabilistic forecasts. Experiments utilizing the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.

Document Type: Research article

DOI: 10.3189/172756408787814870

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$32.46 plus tax Refund Policy