Modeling and forecasting MODIS-based Fire Potential Index on a pixel basis using time series models

详细信息    查看全文

• 作者：Margarita Huesca ; Javier Litago ; Silvia Merino-de-Miguel ; Victor Cicuendez-L贸pez-Oca帽a ; Alicia Palacios-Orueta
• 关键词：ACF ; autocorrelation function ; Adj-R2 ; adjusted coefficient of determination ; AR ; autoregressive ; ARIMA ; autoregressive integrated moving average ; B&J ; Box and Jenkins ; EMR ; estimated model from representative series (significant lags  ; +  ; estimated coefficients) ; EM ; estimated model (significant lags  ; +  ; estimated coefficients) ; GM ; generic model (significant lags) ; L&ndash ; B Q ; Ljung&ndash ; Box Q ; MODIS ; moderate resolution imaging spectroradiometer ; PACF ; partial autocorrelation
• 刊名：International Journal of Applied Earth Observation and Geoinformation
• 出版年：February, 2014
• 年：2014
• 卷：26
• 期：Complete
• 页码：363-376
• 全文大小：4675 K

文摘

The aim of this research was to model and forecast MODIS-based Fire Potential Index (FPI), implemented with Normalized Difference Water Index (NDWI), as a proxy of forest fire risk, in Navarre (Spain) on a pixel basis using time series models with a forecasting horizon of one year.

We forecast FPI_NDWI for 2009 based on time series from 2001 to 2008. In the modeling process, the Box and Jenkins methodology was applied in two consecutive stages. First, several generic models based on average FPI_NDWI time series from different 鈥渇uel type-ecoregion鈥?combinations were developed. In a second stage, the generic models were implemented at the pixel level for the entire study region. The usefulness of the proposed autoregressive (AR) model, using the original data and introducing significant seasonal AR parameters, was demonstrated.

Results show that 93.18% of the estimated models (EMs) are highly accurate and present good forecasting ability, precisely reproducing the original FPI_NDWI dynamics. Best results were found in the Mediterranean areas dominated by grasslands; slightly lower accuracies were found in the temperate and alpine regions, and especially in the transition areas between them and the Mediterranean region.