ABSTRACT
Carbon emissions produced by forest fires contribute to the global emission increase. The amount of carbon emission may indicate the severity of the fires. In a dry climate condition, forest fires become an unexpected serious problem. This paper investigates the effect of climate variables on forest fires in Sumatra from 1998 to 2018. We employ two methods, Random Forest (RF) and Artificial Neural Network (ANN) to predict the carbon emission in 2019-2021. The total emission over the domain and the fire distribution map are compared in both models. As a result, the RF model is more accurate in predicting the location and intensity in 2019 but overestimates in 2020-2021. This indicates that the RF model gives a slightly better prediction when the carbon emission is high. This result is consistent with the evaluation metrics showing that ANN mostly gives smaller errors. Also, we found that the climate variables are still relevant to describe the carbon emissions through both models with importance scores of more than .
- M. Bisquert, E. Caselles, J. M. Sánchez, and V. Caselles. 2012. Application of artificial neural networks and logistic regression to the prediction of forest fire danger in Galicia using MODIS data. International Journal of Wildland Fire 21 (2012), 1025–1029.Google ScholarCross Ref
- L. Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5–32.Google ScholarDigital Library
- C. C. Chen, H. W. Lin, J. Y. Yu, and M. H Lo. 2016. The 2015 Borneo fires: What have we learned from the 1997 and 2006 El Niños?Environmental Research Letters 11, 10 (2016), 104003.Google Scholar
- R. Comert, U. Avdan, T. Gorum, and H. A. Nefeslioglu. 2019. Mapping of shallow landslides with object-based image analysis from unmanned aerial vehicle data. Engineering Geology 260(2019), 105264.Google ScholarCross Ref
- Kementerian Lingkungan Hidup dan Kehutanan. [n. d.]. SiPongi Forest and Land Fires Monitoring System. Available online https://sipongi.menlhk.go.id/.Google Scholar
- Field et al. 2016. Indonesian fire activity and smoke pollution in 2015 show persistent nonlinear sensitivity to El Niño-induced drought. Proceedings of the National Academy of Sciences 113, 33(2016), 9204–9209.Google ScholarCross Ref
- Giglio et al. 2013. Analysis of daily, monthly, and annual burned areas using the fourth-generation global fire emissions database (GFED4). J. Geophys. Res. Biogeosciences 118, 1 (2013), 317–328.Google ScholarCross Ref
- Hersbach et al.2020. The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society 146, 730(2020), 1999–2049.Google ScholarCross Ref
- Pedregosa et. al. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825–2830.Google ScholarDigital Library
- Pham et. al. 2020. Performance evaluation of machine learning methods for forest fire modeling and prediction. Symmetry 12, 6 (2020), 1022.Google ScholarCross Ref
- Prasetyo et al. 2022. Assessing Sumatran Peat Vulnerability to Fire under Various Condition of ENSO Phases Using Machine Learning Approaches. Forests 13, 6 (2022).Google Scholar
- E. Frankenberg, D. McKee, and D. Thomas. 2005. Health consequences of forest fires in Indonesia. Demography 42, 1 (2005), 109–129.Google ScholarCross Ref
- L. Gigović, H. R. Pourghasemi, S. Drobnjak, and S. Bai. 2019. Testing a new ensemble model based on SVM and random forest in forest fire susceptibility assessment and its mapping in Serbia’s Tara National Park. Forests 10, 5 (2019), 408.Google ScholarCross Ref
- I. C. Hidayati, N Nalaratih, A Shabrina, I. N. Wahyuni, and A. L. Latifah. 2020. Correlation of Climate Variability and Burned Area in Borneo using Clustering Methods. Forest and Society 4(2020). https://doi.org/FS.V4I2.9687Google ScholarCross Ref
- P. Jain, S. CP Coogan, S. G. Subramanian, M. Crowley, S. Taylor, and M. D. Flannigan. 2020. A review of machine learning applications in wildfire science and management. Environmental Reviews 28, 4 (2020), 478–505.Google ScholarCross Ref
- S. Kanga and S. K. Singh. 2017. Forest Fire Simulation Modeling using Remote Sensing & GIS.International Journal of Advanced Research in Computer Science 8, 5(2017).Google Scholar
- P. L Kinney. 2018. Interactions of climate change, air pollution, and human health. Current environmental health reports 5, 1 (2018), 179–186.Google Scholar
- A. L. Latifah, A. Shabrina, I. N. Wahyuni, and R. Sadikin. 2019. Evaluation of Random Forest model for forest fire prediction based on climatology over Borneo. In 2019 International Conference on Computer, Control, Informatics and its Applications (IC3INA). IEEE, 4–8.Google Scholar
- G. Louppe. 2014. Understanding random forests: From theory to practice. arXiv preprint arXiv:1407.7502(2014).Google Scholar
- W. Ma, Z. Feng, Z. Cheng, S. Chen, and F. Wang. 2020. Identifying forest fire driving factors and related impacts in china using random forest algorithm. Forests 11, 5 (2020), 507.Google ScholarCross Ref
- J. Miettinen, C. Shi, and S. C. Liew. 2017. Fire distribution in Peninsular Malaysia, Sumatra and Borneo in 2015 with special emphasis on peatland fires. Environmental management 60, 4 (2017), 747–757.Google Scholar
- M. Mohajane, R. Costache, F. Karimi, Q. B. Pham, A. Essahlaoui, H. Nguyen, G. Laneve, and F. Oudija. 2021. Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area. Ecological Indicators 129 (2021), 107869.Google ScholarCross Ref
- K Narendran. 2001. Forest fires. Resonance 6, 11 (2001), 34–41.Google ScholarCross Ref
- NPL. 1996. A Guide to the Measurement of Humidity. The Institute of Measurement and Control. 53–54 pages.Google Scholar
- S. Nurdiati, A. Sopaheluwakan, M. T. Julianto, P. Septiawan, and F. Rohimahastuti. 2021. Modelling and analysis impact of El Nino and IOD to land and forest fire using polynomial and generalized logistic function: Cases study in South Sumatra and Kalimantan, Indonesia. Modeling Earth Systems and Environment(2021), 1–16.Google Scholar
- S. Nurdiati, A. Sopaheluwakan, and P. Septiawan. 2021. Spatial and temporal analysis of El Niño impact on land and forest fire in Kalimantan and Sumatra. Agromet 35, 1 (2021), 1–10.Google ScholarCross Ref
- S. E. Page, F. Siegert, J. O. Rieley, H. V Boehm, A. Jaya, and S. Limin. 2002. The amount of carbon released from peat and forest fires in Indonesia during 1997. Nature 420, 6911 (2002), 61–65.Google Scholar
- S. J. Rigatti. 2017. Random forest. Journal of Insurance Medicine 47, 1 (2017), 31–39.Google ScholarCross Ref
- A. H. Sadat Razavi, M. Shafiepour Motlagh, A. Noorpoor, and A. H. Ehsani. 2020. Modeling of wildfire occurrence by using climate data and effect of temperature increments. Natural Hazards and Earth System Sciences Discussions 2020 (2020), 1–19. https://doi.org/10.5194/nhess-2020-353Google Scholar
- O. Satir, S. Berberoglu, and C. Donmez. 2016. Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem. Geomatics, Natural Hazards and Risk 7, 5 (2016), 1645–1658.Google ScholarCross Ref
- I. N. Wahyuni, A. Shabrina, and A. L. Latifah. 2021. Investigating Multivariable Factors of the Southern Borneo Forest and Land Fire based on Random Forest Model. In The 2021 International Conference on Computer, Control, Informatics and Its Applications. 71–75.Google ScholarDigital Library
Index Terms
- Modelling the climate factors affecting forest fire in Sumatra using Random Forest and Artificial Neural Network
Recommendations
Investigating Multivariable Factors of the Southern Borneo Forest and Land Fire based on Random Forest Model
IC3INA '21: Proceedings of the 2021 International Conference on Computer, Control, Informatics and Its ApplicationsForest and land fires have been problematic annually in Indonesia, particularly in Southern Borneo. Previous studies showed that artificial intelligence contributes to measuring various factors affecting fire. However, there has not been a thorough ...
Crop classification of upland fields using Random forest of time-series Landsat 7 ETM+ data
Application of Random forest approach for crop classification.The use of EVI obtained from time-series Landsat 7 ETM+ imagery as predictor variables.Effects of number of predictor variables, decision trees and training data on classification ...
Forest fire monitoring and burnt area mapping using satellite data: a study over the forest region of Kerala State, India
The present study describes the night-time active forest fire detection capabilities of Defense Meteorological Satellite Program-Operational Linescan System (DMSP-OLS) satellite data over the forest region of Kerala State, India in 2004. Kerala State ...
Comments