Predictive Modeling of Wildfire Occurrence and Damage in a Tropical Savanna Ecosystem of West Africa

Abstract

Wildfires are a major environmental, economic, and social threat. In Central Côte d’Ivoire, they are among the biggest environmental and forestry problems during the dry season. National authorities do not have tools and methods to predict spatial and temporal fire proneness over large areas. This study, based on the use of satellite historical data, aims to develop an appropriate model to forecast wildfire occurrence and burnt areas in each ecoregion of the N’Zi River Watershed. We used an autoregressive integrated moving average (ARIMA) model to simulate and forecast the number of wildfires and burnt area time series in each ecoregion. Nineteen years of monthly datasets were trained and tested. The model performance assessment combined Ljung–Box statistics, residuals, and autocorrelation analysis coupled with cross-validation using three forecast errors—namely, root mean square error, mean absolute error, and mean absolute scaled error—and observed–simulated data analysis. The results showed that the ARIMA models yielded accurate forecasts of the test dataset in all ecoregions and highlighted the effectiveness of the ARIMA models to forecast the total number of wildfires and total burnt area estimation in the future. The forecasts of possible wildfire occurrence and extent of damages in the next four years will help decision-makers and wildfire managers to take actions to reduce the exposure and the vulnerability of ecosystems and local populations to current and future pyro-climatic hazards.

Comparing Machine Learning and Time Series Approaches in Predictive Modeling of Urban Fire Incidents: A Case Study of Austin, Texas

“…In addition to machine learning models, researchers also applied various time series statistical models to fire incident prediction, and Autoregressive integrated moving average (ARIMA) models are a commonly used technique in this field [13,30]. ARIMA models were created in the 1970s and use mathematical laws to realize predictions from time series variables [31].…”

Deep Learning Provides Substantial Improvements to County‐Level Fire Weather Forecasting Over the Western United States

“…With a vast amount of data accumulated over decades, statistical approaches have also been widely used for efficient forecasting of various climate variables (Graff et al., 2020; Kouassi et al., 2020; Preisler & Westerling, 2007). Statistical methods are versatile in detecting internal features and anomalous patterns regardless of the data domain.…”

Exploring spatio‐temporal trends and environmental drivers of wildfire occurrence and impacts in Côte d'Ivoire, West Africa

“…Compared with mid‐season and early‐season fires, late‐season fires caused intense damages to flora both for herbaceous and tree cover in forest and savannah ecosystems, while exterminating micro‐ and macro‐fauna (N'Dri et al, 2012; N'Dri, Soro, et al, 2018). Besides, recent studies have quantified wildfire occurrence and their damage to vegetation (Kouassi et al, 2018, 2020). Despite their relevance, these efforts have remained highly localised at a fine scale.…”

“…Several studies have been carried out to understand the behaviour of wildfires within the country's savannah ecosystems (N'Dri, Fongbe, et al, 2018;N'Dri & Konan, 2018) and to assess fire intensity and regime on vegetation (Aubréville, 2013;Koffi et al, 2019;Kouadio et al, 2013;Louppe et al, 1995;Louppe & Oliver, 2004;N'Dri et al, 2012) . Besides, recent studies have quantified wildfire occurrence and their damage to vegetation (Kouassi et al, 2018(Kouassi et al, , 2020. Despite their relevance, these efforts have remained highly localised at a fine scale.…”