Comparing machine learning algorithms to predict vegetation fire detections in Pakistan

• Published in: Fire ecology 2024-12, Vol.20 (1), p.57, Article 57
• Main Authors: Shahzad, Fahad, Mehmood, Kaleem, Hussain, Khadim, Haidar, Ijlal, Anees, Shoaib Ahmad, Muhammad, Sultan, Ali, Jamshid, Adnan, Muhammad, Wang, Zhichao, Feng, Zhongke
• Format: Article
• Language: English
• Subjects: Accuracy; Agricultural land; Algorithms; Biomedical and Life Sciences; Climatic conditions; Data processing; Ecology; Environmental impact; Forest & brush fires; Forest fires; Forestry; Geographical distribution; Learning algorithms; Life Sciences; Machine learning; MODIS; Original Research; Performance measurement; Prediction models; Regression models; Remote Sensing for Wildfire Management Potential and Impacts; Risk assessment; Support vector machines; Vegetation
• ISSN: 1933-9747; 1933-9747
• DOI: 10.1186/s42408-024-00289-5

Vegetation fires have major impacts on the ecosystem and present a significant threat to human life. Vegetation fires consists of forest fires, cropland fires, and other vegetation fires in this study. Currently, there is a limited amount of research on the long-term prediction of vegetation fires in Pakistan. The exact effect of every factor on the frequency of vegetation fires remains unclear when using standard analysis. This research utilized the high proficiency of machine learning algorithms to combine data from several sources, including the MODIS Global Fire Atlas dataset, topographic, climatic conditions, and different vegetation types acquired between 2001 and 2022. We tested many algorithms and ultimately chose four models for formal data processing. Their selection was based on their performance metrics, such as accuracy, computational efficiency, and preliminary test results. The model’s logistic regression, a random forest, a support vector machine, and an eXtreme Gradient Boosting were used to identify and select the nine key factors of forest and cropland fires and, in the case of other vegetation, seven key factors that cause a fire in Pakistan. The findings indicated that the vegetation fire prediction models achieved prediction accuracies ranging from 78.7 to 87.5% for forest fires, 70.4 to 84.0% for cropland fires, and 66.6 to 83.1% for other vegetation. Additionally, the area under the curve (AUC) values ranged from 83.6 to 93.4% in forest fires, 72.6 to 90.6% in cropland fires, and 74.2 to 90.7% in other vegetation. The random forest model had the highest accuracy rate of 87.5% in forest fires, 84.0% in cropland fires, and 83.1% in other vegetation and also the highest AUC value of 93.4% in forest fires, 90.6% in cropland fires, and 90.7% in other vegetation, proving to be the most optimal performance model. The models provided predictive insights into specific conditions and regional susceptibilities to fire occurrences, adding significant value beyond the initial MODIS detection data. The maps generated to analyze Pakistan’s vegetation fire risk showed the geographical distribution of areas with high, moderate, and low vegetation fire risks, highlighting predictive risk assessments rather than historical fire detections.