Climate Change Including Forest Fire Prediction using Machine Learning and Deep Learning

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2024 | Volume : 15 | Issue : 03 | Page :
    By

    Garima Srivastava,

  1. Assistant Professor, Computer Science & Engineering, Amity University Lucknow Campus, Malhaur (Near Railway Station), Gomti Nagar Extension, Lucknow, Uttar Pradesh, India

Abstract

Climate change alludes to long haul shifts in temperatures and atmospheric conditions. These movements might be regular, for example, through varieties in the sun-oriented cycle. In any case, since the 1800s, human exercises have been the fundamental driver of climate change, basically because of consuming fossil fuels like coal, oil and gas. Many individuals think climate change mostly implies hotter temperatures. Be that as it may, the temperature climb is just the start of the story. Since the Earth is a framework, where everything is associated, changes in a single region can impact changes in all others. The results of climate change currently incorporate, among others, extreme dry spells, water shortage, serious fires, rising ocean levels, flooding, dissolving polar ice, disastrous tempests, and declining biodiversity. This paper assesses the exhibition of a few Machines Learning algos (Linear Regression, Support Vector Regression (SVR), Logistic regression, decision tree regression, random forest) in issues of rainfall, temperature, and forest fire forecast, from recently estimated values. For the forest fire prediction model, we used linear regression, random forest and decision tree regression. For the rainfall prediction model, we used logistic regression, decision tree and random forest classifier and for the temperature prediction model we used linear regression, polynomial regression, decision tree regression and random forest. The most promising results were achieved through the use of decision trees with the MSE of 882.62, MAE OF 11.8 and R2_score of -0.56 in predicting the occurrence of a forest fire. Random forest had the maximum precision score of 87% and recall score of 95% for the prediction of rainfall. Decision tree regression gave the maximum accuracy of 84.33% for prediction of temperature.

Keywords: Climate change, forest fire prediction, linear regression, SVR, decision tree, random forest, logistic regression

[This article belongs to Journal of Computer Technology & Applications ]

How to cite this article:
Garima Srivastava. Climate Change Including Forest Fire Prediction using Machine Learning and Deep Learning. Journal of Computer Technology & Applications. 2024; 15(03):-.
How to cite this URL:
Garima Srivastava. Climate Change Including Forest Fire Prediction using Machine Learning and Deep Learning. Journal of Computer Technology & Applications. 2024; 15(03):-. Available from: https://journals.stmjournals.com/jocta/article=2024/view=186410


References

  1. Aronszajn N. Introduction to the theory of Hilbert spaces. Stillwater (OK): Research Foundation; 1950.
  2. Brillinger DR, Preisler HK, Benoit JW. Risk assessment: a forest fire example. Lecture Notes Monogr Ser. 2003;1:177–96.
  3. Cheng T, Wang J. Applications of spatio-temporal data mining and knowledge for forest fire. In: Remote Sensing: From Pixels to Processes. 2006. p. 148–53.
  4. Alexandridis A, Vakalis D, Siettos CI, Bafas GV. A cellular automata model for forest fire spread prediction: The case of the wildfire that swept through Spetses Island in 1990. Appl Math Comput. 2008;204(1):191–201.
  5. Cortez P, Morais A. A data mining approach to predict forest fires using meteorological data [Internet]. Available from: https://repositorium.sdum.uminho.pt/bitstream/1822/8039/1/fires.pdf
  6. Dunn A, Milne G. Modelling wildfire dynamics via interacting automata. In: Cellular Automata: 6th International Conference on Cellular Automata for Research and Industry, ACRI 2004, Amsterdam, The Netherlands, October 25–28, 2004. Proc. 2004. p. 395–404.
  7. Han JG, Ryu KH, Chi KH, Yeon YK. Statistics based predictive geo-spatial data mining: Forest fire hazardous area mapping application. In: Web Technologies and Applications: 5th Asia-Pacific Web Conference, APWeb 2003, Xian, China, April 23–25, 2003. Proc. 2003. p. 370–81.
  8. Iliadis LS. A decision support system applying an integrated fuzzy model for long-term forest fire risk estimation. Environ Model Softw. 2005;20(5):613–21.
  9. Jaiswal RK, Mukherjee S, Raju KD, Saxena R. Forest fire risk zone mapping from satellite imagery and GIS. Int J Appl Earth Obs Geoinf. 2002;4(1):1–10.
  10. Kecman V. Learning and soft computing: support vector machines, neural networks, and fuzzy logic models. Cambridge (MA): MIT Press; 2001.
  11. Li ZH, Kaufman YJ, Ichoku C, Fraser R, Trishchenko A, Giglio L, et al. A review of AVHRR-based active fire detection algorithms: Principles, limitations, and recommendations. Glob Reg Veg Fire Monit Space Plan Coord Int Effort. 2001:199–225.
  12. Mitri GH, Gitas IZ. A semi-automated object-oriented model for burned area mapping in the Mediterranean region using Landsat-TM imagery. Int J Wildl Fire. 2004;13(3):367–76.
  13. Muzy A, Marcelli T, Aiello A, Santoni PA, Santucci JF, Balbi JH. An object-oriented environment applied to a semi-physical model of fire spread across a fuel bed. In: Actes de la conférence ESS 2001 conference. 2001. p. 641–3.
  14. Ntaimo L, Khargharia B. Two-dimensional fire spread decomposition in cellular DEVS models. Simul Ser. 2006;38(1):103.
  15. Rothermel RC. A mathematical model for predicting fire spread in wildland fuels. Intermountain Forest & Range Experiment Station, Forest Service, US Department of Agriculture; 1972.
  16. Vapnik V. Statistical learning theory. New York: John Wiley & Sons; 1998.
  17. Wiering M, Mignogna F. Learning to control forest fires with ESP. In: Proceedings of the Sixth European Workshop on Reinforcement Learning. 2003. p. 22–3.
  18. Alonso-Betanzos A, Fontenla- Romero O, Guijarro-Berdiñas B, Hernández-Pereira E, Andrade MI, Jiménez E, et al. An intelligent system for forest fire risk prediction and firefighting management in Galicia. Expert Syst Appl. 2003;25(4):545–54.
Regular Issue Subscription Original Research
Volume 15
Issue 03
Received 16/09/2024
Accepted 01/10/2024
Published 30/11/2024
207


My IP

PlumX Metrics