Abstract
The frequency of climate-induced disasters (CID) has exhibited a fivefold increase in the last five decades. In terms of CID global impact, around 1.7 billion people were affected in the last decade, and in 2020 alone, 30 million people were displaced due to CID. Furthermore, over the past two decades, 1 million deaths were reported and over $1.7 trillion in damage was attributed to CID. As such, the World Economic Forum, in its 2022 report, has identified climate action failure and extreme weather as the two most severe global risks to be considered over the next decade. Given the uncertainty and complexity associated with predicting CID frequencies and related impacts, the use of descriptive-, predictive- and prescriptive data analytics is key. To demonstrate the power of data analytics in predicting CID impacts, this work focuses on developing a data-driven machine learning model that predicts tornado-induced injuries based on a diverse set of input features ranging from hazard-, social-, geographic-, and climate-related features together with attributes related to community vulnerability, risk and resilience. These input features are then used to train and test various machine learning-based prediction models utilizing diverse techniques including decision trees, ensemble methods, and artificial neural networks. These models are subsequently evaluated to select the most significant features and the best performing model. In addition, several variable importance techniques are used to evaluate the dominance of all features and develop a model considering the most influential features. The results show that the best performing model had a testing accuracy of 83%. In addition, the results highlighted the apparent relationship between hazard-related attributes and tornadoes’ injury predictions. The developed approach is a step forward in harnessing the power of machine learning for improving our adaptation, preparedness, and planning towards global CID resilience.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
Not applicable.
Code availability
Not applicable.
References
Ajaj QM, Shareef MA, Hassan ND, Hasan SF, Noori AM (2018) GIS based spatial modeling to mapping and estimation relative risk of different diseases using inverse distance weighting (IDW) interpolation algorithm and evidential belief function (EBF) (Case study: Minor Part of Kirkuk City, Iraq). Int J Eng Technol 7(4):185–191
Anggoro DA, Supriyanti W (2019) Improving accuracy by applying Z-score normalization in linear regression and polynomial regression model for real estate data. Int J Emerg Trends Eng Res 7(11):549–555
Andrew Hurst (2021) Tornadoes caused $2.5 million in damage per storm across U.S. in Past Decade. https://www.valuepenguin.com/damage-caused-by-tornadoes. Accessed 28 Apr 2022
Boehmke B, Greenwell B (2020) Model-based clustering. In: Chambers JM, Horthorn T, Lang DT, Wickham H (eds) Hands-on machine learning with R. CRC Press, Taylor and Francis Group, Boca Raton, pp 429–441
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Breiman L (2001) Random forests. Mach Learn 45:5–32
Choi C, Kim J, Kim J, Kim D, Bae Y, Kim HS (2018) Development of heavy rain damage prediction model using machine learning based on big data. Adv Meteorol 2018
Chu J, Lee T, Ullah A, Wang R (2020) Boosting. In: Fuleky P (ed) Macroeconomic forecasting in the era of big data. Springer, Cham, pp 431–463
Climate and Weather (2020) Weather—Tornadoes | Climate and Weather. https://www.climateandweather.net/world-weather/tornadoes/. Accessed 28 Apr 2022
Cook TR (2020) Neural networks. In: Fuleky P (ed) Macroeconomic forecasting in the era of big data. Springer, Cham, pp 161–189
Cusick D (2021) Climate-Fueled Disasters Killed 475,000 People over 20 Years - Scientific American. https://www.scientificamerican.com/article/climate-fueled-disasters-killed-475-000-people-over-20-years/. Accessed 28 Apr 2022
Diaz J, Joseph MB (2019) Predicting property damage from tornadoes with zero-inflated neural networks. Weather Clim Extrem 25(July 2018):100216
Federal Emergency Management Agency (2021) National Risk Index for Natural Hazards | FEMA. Accessed 01 Jan 2022 https://www.fema.gov/flood-maps/products-tools/national-risk-index
Finnis N (2020) Tornado facts: which countries have the most and the deadliest tornadoes? https://www.netweather.tv/weather-forecasts/news/10277-tornado-facts-which-countries-have-the-most-and-the-deadliest-tornadoes. Accessed 28 Apr 2022
Fraley C, Raftery AE (1998) How many clusters? Which clustering method? Answers via model-based cluster analysis. Comput J 41(8):578–588
Fraley C, Raftery AE (2002) Model-based clustering, discriminant analysis, and density estimation. J Am Stat Assoc 97(458):611–631
France 24 (2022) Weather disaster deaths hit 10-year high in mainland US. https://www.france24.com/en/live-news/20220110-weather-disaster-deaths-hit-10-year-high-in-mainland-us. Accessed 28 Apr 2022
Ganguly K, Nahar N, Hossain M (2019) A machine learning-based prediction and analysis of flood affected households: a case study of floods in Bangladesh. Int J Disaster Risk Reduct 34:283–294
Guha-sapir D, Hoyois P, Below R (2015) Annual disaster statistical review 2014: the numbers and trends. Cent Res Epidemiol Disasters, pp 1–54
Haggag M, Siam AS, El-Dakhakhni W, Coulibaly P, Hassini E (2021a) A deep learning model for predicting climate-induced disasters. Nat Hazards 107(1):1009–1034
Haggag M, Yosri A, El-dakhakhni W, Hassini E (2022) Interpretable data-driven model for Climate-Induced Disaster damage prediction: the first step in community resilience planning. Int J Disaster Risk Reduct 73(November 2021):102884
Hanewinkel M, Zhou W, Schill C (2004) A neural network approach to identify forest stands susceptible to wind damage. For Ecol Manag 196(2–3):227–243
Hausfather Z (2019) Tornadoes and climate change: what does the science say?. https://www.carbonbrief.org/tornadoes-and-climate-change-what-does-the-science-say-2. Accessed 30 Apr 2022
Hossin M, Sulaiman M (2015) A review on evaluation metrics for data classification evaluations. Int J Data Min Knowl Manag Process 5(2):01–11
I. P. on Climate Change, “Climate Change (2022)—Mitigation of Climate Change—Summary for Policymakers (SPM). Cambridge University Press, no. 1, pp 1–30
Jaafari A, Zenner E, Panahi M, Shahabi H (2019) Hybrid artificial intelligence models based on a neuro-fuzzy system and metaheuristic optimization algorithms for spatial prediction of wildfire probability. Agric for Meteorol 266–267:198–207
Jondeau E, Mhalla L (2021) Climate-related disasters and the death toll ∗. Toll Swiss Financ Inst Res Pap September, pp 21–637
Kahira A, Gomez B, Badia Sala R (2018) A machine learning workflow for hurricane prediction. In: Book of abstracts. Barcelona Supercomputing Center, pp 72–73
Kahn ME et al (2005) The death toll from natural disasters: the role of income, geography, and institutions. Rev Econ Stat 87(3):271–284
Khalaf M et al. (2018) A data science methodology based on machine learning algorithms for flood severity prediction. In: 2018 IEEE Congress on Evolutionary Computation, pp 1–8
Lam KC, Bryant RG, Wainright J (2015) Application of spatial interpolation method for estimating the spatial variability of rainfall in Semiarid New Mexico, USA. Mediterr J Soc Sci 6(4S3):108–116
Laslett GM, Laslett AB, Pahl PJ, Hutchinson MF (1987) Comparison of several spatial prediction methods for soil ph. J Soil Sci 38(2):325–341
Lopez R, Thomas V, Troncoso P (2020) Impacts of carbon dioxide emissions on global intense hydrometeorological disasters. Clim Disaster Dev J 4(1):30–50
Meng Y, Cave M, Zhang C (2019) Comparison of methods for addressing the point-to-area data transformation to make data suitable for environmental, health and socio-economic studies. Sci Total Environ 689:797–807
Meredith-Miller B (2021) Costs from tornado outbreak could reach $3. https://www.propertycasualty360.com/2021/12/16/costs-from-fridays-tornado-outbreak-could-reach-3-7-billion/. Accessed 28 Apr 2022
Musashi JP, Pramoedyo H, Fitriani R (2018) Comparison of inverse distance weighted and natural neighbor interpolation method at air temperature data in Malang Region. Cauchy 5(2):48
National Weather Services (2022) Storm Events Database | National Centers for Environmental Information. Accessed 10 Oct 2019 https://www.ncdc.noaa.gov/stormevents/%5Cnfiles/5576/stormevents.html
New approaches to help businesses tackle climate change | University of Cambridge (2020) https://www.cam.ac.uk/research/news/new-approaches-to-help-businesses-tackle-climate-change. Accessed 22 Mar 2021
NOAA Climate Data Online (CDO)
“Natural Disasters Could Cost 20 Percent More By 2040 Due to Climate Change - Yale E360 (2020) https://e360.yale.edu/digest/natural-disasters-could-cost-20-percent-more-by-2040-due-to-climate-change. Accessed 02 Jan 2021
Oxfam International (2021) 5 natural disasters that beg for climate action. https://www.oxfam.org/en/5-natural-disasters-beg-climate-action. Accessed 27 Apr 2022
Perez L (2022) FIU receives $12.8M NSF grant to design an extreme wind, surge and wave testing facility. https://news.fiu.edu/2022/fiu-receives-12.8-million-nsf-grant-to-design-an-extreme-wind,-surge-and-wave-testing-facility. Accessed 20 Jun 2022
Philanthropy Center for Disasters (2022) December 2021 Tornado outbreak - center for disaster philanthropy. https://disasterphilanthropy.org/disasters/december-2021-tornado-outbreak/. Accessed 28 Apr 2022
Pilkington SF, Mahmoud HN (2020) “Interpreting the socio-technical interactions within a wind damage-artificial neural network model for community resilience. R Soc Open Sci 7(11):200922
Pule M (2021) Total economic impacts of historic tornado outbreak about $18 billion | AccuWeather. https://www.accuweather.com/en/severe-weather/total-economic-impacts-of-historic-tornado-outbreak-about-18-billion/1062259. Accessed 28 Apr 2022
Raheel S (2018) Feature selection techniques in machine learning with python. Towards Data Science. Accessed 23 Mar 2021 https://towardsdatascience.com/feature-selection-techniques-in-machine-learning-with-python-f24e7da3f36e
Rahman MS et al (2022) Climate disasters and subjective well-being among urban and rural residents in Indonesia. Sustainability 14(3383):1–14
Raschka S (2021) What is the difference between filter, wrapper, and embedded methods for feature selection. Accessed 01 Jan 2021 https://sebastianraschka.com/faq/docs/feature_sele_categories.html
Rastogi A, Sridhar S, Gupta R (2020) Comparison of different spatial interpolation techniques to thematic mapping of socio-economic causes of crime against women. In: 2020 Systems and Information Engineering Design Symposium (SIEDS 2020)
Rice D (2022) Weather disasters broke records and killed over 600 Americans in 2021. https://www.usatoday.com/story/news/nation/2022/01/10/weather-2021-death-toll/9157670002/
Ridgeway G (2004) The gbm package. R Found Stat Comput 3(5)
Rodrigues M, De la Riva J (2014) An insight into machine-learning algorithms to model human-caused wildfire occurrence. Environ Model Softw 57:192–201
Rokach L, Maimon O (2005) Decision trees. In: Rokach L, Maimon O (eds) Data mining and knowledge discovery handbook. Springer, Boston, pp 165–192
Roser M (2013) Future population growth—our world in data. https://ourworldindata.org/future-population-growth#citation. Accessed 30 Apr 2022
Sallis PJ, Claster W, Herna S (2011) A machine-learning algorithm for wind gust prediction. Comput Geosci 37:1337–1344
Schloeder CA, Zimmerman NE, Jacobs MJ (2001) Comparison of methods for interpolating soil properties using limited data. Soil Sci Soc Am J 65(2):470–479
Setianto A, Triandini T (2015) Comparison of Kriging and inverse distance weighted (Idw) interpolation methods in lineament extraction and analysis. J Appl Geol 5(1):21–29
Sheffey A (2022) Climate disasters killed 688 people, cost $145 Billion in 2021: report. https://www.businessinsider.com/climate-disaster-death-toll-688-people-cost-145-billion-2021-2022-1. Accessed 27 Apr 2022
Tallón-Ballesteros A, Riquelme JC (2014) Deleting or keeping outliers for classifier training? In: 6th World Congress on nature and biologically inspired computing, pp 281–286
Thomas V (2017) Climate change and natural disasters: transforming economies and policies for a sustainable future. Routledge, London
Thomas V, López R (2015) Global increase in climate-related disasters. Asian Dev Bank Econ Work Pap Ser November 2(466):1–44
Thomas V, Albert JRG, Hepburn C (2014) Contributors to the frequency of intense climate disasters in Asia-Pacific countries. Clim Change 126(3–4):381–398
Totaro G (2022) Tornado statistics for 2022 | Bankrate. https://www.bankrate.com/insurance/homeowners-insurance/tornado-statistics/. Accessed 28 Apr 2022
Toya H, Skidmore M (2007) Economic development and the impacts of natural disasters. Econ Lett 94(1):20–25
United Nations University (UNU-EHS) Interconnected Disaster Risks (2022)
U.S Geological Survey (2011) Land Cover Data Download. Accessed 10 Oct 2020 https://www.usgs.gov/core-science-systems/science-analytics-and-synthesis/gap/science/land-cover-data-download?qt-science_center_objects=0#qt-science_center_objects
Word Economic Forum (2022) The global risks report 2022 17th Edition
World Food Programme (2022) 14 facts linking climate change, disasters & hunger. [Online]. https://www.wfpusa.org/articles/14-facts-climate-disasters-hunger/. Accessed 27 Apr 2022
World Health Organization (2018) Climate change and health. [Online]. https://www.who.int/news-room/fact-sheets/detail/climate-change-and-health. Accessed 06 Jun 2019
World Meteorological Organization (2021) Weather-related disasters increase over past 50 years, causing more damage but fewer deaths | World. https://public.wmo.int/en/media/press-release/weather-related-disasters-increase-over-past-50-years-causing-more-damage-fewer. Accessed 27 Apr 2022
Y-H Wu, M-C Hung (2016) Comparison of spatial interpolation techniques using visualization and quantitative assessment. In: Applications of spatial statistics
Yang Y, Webb GI, Wu X (2010) Discretization methods. In: Rokach L, Maimon O (eds) Data mining and knowledge discovery handbook. Springer, Boston, pp 101–116
Acknowledgements
We acknowledge the financial support of the Natural Sciences and Engineering Research Council of Canada (NSERC). The authors would also like to acknowledge the fruitful discussions with the research teams of the INViSiONLab and the INTERFACE Institute, both at McMaster University.
Funding
The authors are grateful to the financial support of the Natural Sciences and Engineering Research Council (NSERC) of Canada.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author(s) declare no competing interests.
Consent to participate
Not applicable.
Consent for publication
The authors confirm that the consent for publication is granted.
Ethics approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Haggag, M., Rezk, E. & El-Dakhakhni, W. Machine learning prediction of climate-induced disaster injuries. Nat Hazards 116, 3645–3667 (2023). https://doi.org/10.1007/s11069-023-05829-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-023-05829-x