Experimental Forecast of Area Burned for Interior Alaska

The purpose of this experimental forecast is to provide managers with a forecast of the area burned in Interior Alaska for the upcoming fire season. The forecast falls into one of the three categories:

Median Forecast for the 2010 season is 1,570,000 acres (High) as of the end of May.

1,068,705 acres have burned as of August 19th
http://fire.ak.blm.gov/content/sitreport/current.pdf
  • There is a 5% chance that less than 500,000 acres will burn.
  • There is a 40% chance that between 500,000 and 1,500,000 acres will burn.
  • There is a 55% chance that more than 1,500,000 acres will burn.

The next 2010 forecast will be available in early July.

What this product does ...

What this product does not do ...

How is this product constructed?

Atmospheric circulation patterns influence seasonal temperature and precipitation across large regions of Alaska. This experimental product uses to information to produce a forecast of area burned in Interior Alaska (i.e. South of the Brooks Range and North of the Alaska Range). By using the historical area burned data, historical teleconnection indices, and monthly temperature and precipitation indices for Interior Alaska, we constructed statistical models that forecast the area burned for the upcoming season based on the early season atmospheric circulation patterns. The temperature and precipitation data are assembled following the methods of Duffy et al. (2005) and are available from the National Weather Service Forecast Office. For more information about the modeling procedure click on the Methodology tab.

The general approach can be simply stated as "sequentially fit a predictive model for annual area burned in Alaska after the data for each month (March-July) become available". As with any modeling process there are a number of different decisions that must be made regarding model complexity, selection of explanatory variables, spatio-temporal resolution of interest, and others. A brief outline of the specifics of the approach is presented below, with an example for the data available at the end of June 2008.

One of the key results of Duffy et al. (2005) was the identification of the approximate spatial and temporal resolution that displays the strongest linkage between climate and fire. This work keeps the focus on linkages at an annual timescale across interior Alaska for the time period of 1950-2008. Explanatory variables used in this analysis are monthly teleconnection indices and monthly temperature/precipitation. Predictions are made monthly from March through July. The collection of potential explanatory variables includes monthly values for the following: the arctic oscillation; the east Pacific/North Pacific teleconnection; the Polar teleconnection; the West Pacific teleconnection; and average temperature and total precipitation. The teleconnection data are available from two NOAA sites [here and here]. The temperature and precipitation data are assembled following the methods of Duffy et al. (2005) and are available from the Western Region Climate Center .

Details regarding the specifics of the software used to implement this approach can be found at The R Project. A detailed description of the generalized boosting model approach is beyond the scope of this document. Conceptually, the goal of the GBM approach is to find the 'combination' of explanatory variables that best characterizes the annual area burned. In a regression model this is done by using the data to find the best parameters in a linear model. In the GBM approach, regression trees are constructed through binary recursive partitioning.