A PCA-GA-ELM Method and Its Application in Earthquake Casualty Prediction

Abstract

Major earthquake events worldwide have posed substantial threats to human security and socioeconomic stability. Accurate prediction of earthquake casualty is important for effective disaster preparedness and emergency response. However, conventional prediction methods are often constrained by multicollinearity among high-dimensional influencing factors, suboptimal computational efficiency, and inadequate consideration of critical environmental variables. Notably, the impact of meteorological conditions on post-seismic mortality remains underexplored in existing methods, despite its potential to significantly affect survival rates during secondary earthquake disaster phases. To overcome these limitations, a novel hybrid method, PCA-GA-ELM, is proposed, integrating Principal Component Analysis (PCA), Genetic Algorithm (GA), and Extreme Learning Machine (ELM). The method innovatively incorporates temperature as a key prediction variable alongside six conventional seismic and socioeconomic factors. PCA facilitates dimensionality reduction and eliminates feature redundancy, while GA enhances the prediction robustness of ELM. Rigorous validation using global seismic datasets demonstrates the superior performance of the proposed method, achieving a significant improvement in prediction accuracy compared with benchmark methods. Furthermore, owing to its promising adaptability for casualty prediction, the generalizable PCA-GA-ELM framework can also be extended to other geophysical hazards, including tsunamis and landslides, where multifactorial interactions determine outcomes. This research contributes by establishing a quantitative relationship between temperature and earthquake casualty, while its practical implementation offers substantial improvements in emergency resource allocation and mitigation strategy formulation for disaster management authorities. Nevertheless, several limitations remain and warrant further improvement: 1) the study relies on historical static data and has not yet established a dynamic mechanism integrated with real-time monitoring systems; and 2) geological environmental factors are not included in the prediction system.

Keywords

Earthquake casualty prediction / extreme learning machine / principal component analysis

References

[1] Aghamohammadi H, Mesgari M S, Mansourian A, Molaei D. Seismic human loss estimation for an earthquake disaster using neural network. International Journal of Environmental Science and Technology, 2013, 10(5): 931-939

[2] Ali H, Hariharan M, Yaacob S, Adom A H. Facial emotion recognition using empirical mode decomposition. Expert Systems with Applications, 2014, 42(3): 1261-1277

[3] Al Bataineh A, Jalali S M J, Mousavirad S J, Yazdani A, Islam S M S, Khosravi A. An efficient hybrid extreme learning machine and evolutionary framework with applications for medical diagnosis. Expert Systems, 2024, 41(4): 1-27

[4] Armaghani D J, Hasanipanah M, Mahdiyar A, Abd Majid M, Amnieh H B, Tahir MMD. Airblast prediction through a hybrid genetic algorithm-ANN model. Neural Computing & Applications, 2018, 29(9): 619-629

[5] Armaghani D J, Yang P X, He X Z, Pradhan B, Zhou J, Sheng D C. Toward precise long-term rockburst forecasting: A fusion of SVM and cutting-edge metaheuristic algorithms. Natural Resources Research, 2024, 33(5): 2037-2062

[6] Bastami M, Soghrat M R. An empirical method to estimate fatalities caused by earthquakes: the case of the Ahar-Varzaghan earthquakes (Iran). Natural Hazards, 2017, 86(1): 125-149

[7] Chen Q F, Mi H L, Huang J. A simplified approach to earthquake risk in mainland China. Pure and Applied Geophysics, 2005, 162(6–7): 1255-1269

[8] Chen K, Laghrouche S, Djerdir A. Proton exchange membrane fuel cell prognostics using genetic algorithm and extreme learning machine. Fuel Cells, 2020, 20(3): 263-271

[9] Chen W Y, Zhang L M. An automated machine learning approach for earthquake casualty rate and economic loss prediction. Reliability Engineering & System Safety, 2022, 225: 1-15

[10] Cui S Z, Yin Y Q, Wang D J, Li Z W, Wang Y Z. A stacking-based ensemble learning method for earthquake casualty prediction. Applied Soft Computing Journal, 2021, 101: 1-16

[11] Demir S, Sahin E K. Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost. Acta Geotechnica, 2023, 18(6): 3403-3419

[12] Du H, Song D Q, Chen Z, Shu H P, Guo Z Z. Prediction model oriented for landslide displacement with step-like curve by applying ensemble empirical mode decomposition and the PSO-ELM method. Journal of Cleaner Production, 2020, 270: 1-17

[13] Fang Z M, Huang J H, Huang Z Y, Chen L Z, Cong B H, Yu L Y. An earthquake casualty prediction method considering burial and rescue. Safety Science, 2020, 126: 1-8

[14] Gao P, Wang N, Lu Y, Liu J M, Wang G N, Hou R. Research on millet origin identification model based on improved parrot optimizer optimized regularized extreme learning machine. Journal of Food Composition and Analysis, 2025, 141: 107354

[15] Ghorbani B, Arulrajah A, Narsilio G, Horpibulsuk S, Bo M W. Development of genetic-based models for predicting the resilient modulus of cohesive pavement subgrade soils. Solis and Foundations, 2020, 60(2): 398-412

[16] Gul M, Guneri A F. An artificial neural network-based earthquake casualty estimation model for Istanbul city. Natural Hazards, 2016, 84(3): 2163-2178

[17] Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Networks, 2006, 17(4): 879-892

[18] Huang X, Zhou Z L, Wang S Y. The prediction model of earthquake casuailty based on robust wavelet v-SVM. Natural Hazards, 2015, 77(2): 717-732

[19] Huang X, Jin H D. An earthquake casualty prediction model based on modified partial Gaussian curve. Natural Hazards, 2018, 94(3): 999-1021

[20] Huang X, Song J Y, Jin H D. The casualty prediction of earthquake disaster based on Extreme Learning Machine method. Natural Hazards, 2020, 102(3): 873-886

[21] Huang X, Luo M J, Jin H D. Application of improved ELM algorithm in the prediction of earthquake casualties. Plos One, 2020, 15(6): 1-13

[22] Jia H X, Lin J Q, Liu J L. An earthquake fatalities assessment method based on feature importance with deep learning and random forest models. Sustainability, 2019, 11(10): 1-21

[23] Holland J. Genetic algorithms. Scientific American, 1992, 267(1): 66-73

[24] Krishnan G S, Kamath S. A novel GA-ELM model for patient-specific mortality prediction over large-scale lab event data. Applied Soft Computing, 2019, 80: 525-533

[25] Li B Y, Gong A D, Zeng T T, Bao W X, Xu C, Huang Z Q. A zoning earthquake casualty prediction model based on machine learning. Remote Sensing, 2022, 14(1): 1-27

[26] Li B, Lian Y Q. A forecasting approach for wholesale market agricultural product prices based on combined residual correction. Applied Science-Basel, 2025, 15(10): 5575

[27] Liang Y C, Juarez JRC. A self-adaptive virus optimization algorithm for continuous optimization problems. Soft Computing, 2020, 24(17): 13147-13166

[28] Liu L Q, Moayedi H, Rashid A S A, Rahman S S A, Nguyen H. Optimizing an ANN model with genetic algorithm (GA) predicting load-settlement behaviours of eco-friendly raft-pile foundation (ERP) system. Engineering with Computers, 2020, 36(1): 421-433

[29] Liu H F, Wang J. Integrating independent component analysis and principal component analysis with neural network to predict chinese stock market. Mathematical Problems in Engineering, 2011, 2011: 1-16

[30] Luo M H, Peng S Y, Gao Y B, Liu J, Huang B M. Earthquake fatality prediction based on hybrid feature importance assessment: A case study in Yunnan Province China. Natural Hazards, 2023, 116(3): 3353-3376

[31] Nagarajan D, Sujatha R, Kuppuswami G, Kavikumar J. Real-time forecasting of the COVID 19 using fuzzy grey Markov: A different approach in decision-making. Computational & Applied Mathematics, 2022, 41(6): 1-26

[32] Peng S M, Chen S D, Liu Y, Yu Q Q, Kan J R, Li R. State of power prediction joint fisher optimal segmentation and PO-BP neural network for a parallel battery pack considering cell inconsistency. Applied Energy, 2025, 381: 125130

[33] Sabbah T, Selamat A, Selamat M H, Al-Anzi F S, Viedma E H, Krejcar O, Fujita H. Modified frequency-based term weighting schemes for text classification. Applied Soft Computing, 2017, 58: 193-206

[34] Shi B B, Chen J J, Chen H Y, Lin W J, Yang J, Chen Y, Wu C W, Huang Z Q. Prediction of recurrent spontaneous abortion using evolutionary machine learning with joint self-adaptive sime mould algorithm. Computers in Biology and Medicine, 2022, 148: 105885

[35] Soltanpour S, Wu Q M J. Weighted extreme sparse classifier and local derivative pattern for 3D face recognition. IEEE Transactions on Image Processing, 2019, 28(6): 3020-3033

[36] Tang X Y, Wang L, Cheng J R, Chen J, Shen V S. Forecasting model based on information-granulated GA-SVR and ARIMA for producer price index. CMC-Computers Materials & Continua, 2019, 58(2): 463-491

[37] Tang W K, Shi S Q, Lu Z T, Lin M Y, Cheng H. EDECO: An enhanced educational competition optimizer for numerical optimization problems. Biomimetics, 2025, 10(3): 176

[38] Turkan S, Özel G. Modeling destructive earthquake casualties based on a comparative study for Turkey. Natural Hazards, 2014, 72(2): 1093-1110

[39] Wang H X, Niu J X, Wu J F. ANN model for the estimation of life casualties in earthquake engineering. Systems Engineering Procedia, 2011, 1: 55-60

[40] Wang Z X. Correlation analysis of sequences with interval grey numbers based on the kernel and greyness degree. Kybernetes, 2013, 42(1–2): 309-317

[41] Wang Q H, Wang W, He Y, Li M. Prediction of physical and mechanical properties of heat-treated wood based on the improved beluga whale optimisation back propagation (IBWO-BP) neural network. Forests, 2024, 15(4): 687

[42] Weng F T, Chen Y H, Wang Z, Hou M Z, Luo J S, Tian Z C. Gold price forecasting research based on an improved online extreme learning machine algorithm. Journal of Ambient Intelligence and Humanized Computing, 2020, 11(10): 4101-4111

[43] Xia C X, Nie G Z, Fan X W, Zhou J X, Li X Y, Pang X K. Research on the rapid assessment of earthquake casualties based on the anti-lethal levels of buildings. Geomatics Natural Hazards & Risk, 2020, 11(1): 377-398

[44] Xia C X, Nie G Z, Fan X W, Li H Y, Zhou J X, Zeng X. A new model for the quantitative assessment of earthquake casualties based on the correction of antilethal level. Natural Hazards, 2022, 110(2): 1199-1226

[45] Xia C X, Nie G Z, Li H Y, Fan X W, Qi W X. A composite database of casualty-inducing earthquakes in mainland China. Natural Hazards, 2023, 116(3): 3321-3351

[46] Xu C H, Amar M N, Chriga M A, Ouaer H, Zhang X L, Hasanipanah M. Evolving support vector regression using grey wolf optimization: Forecasting the geomechanical properties of rock. Engineering with Computers, 2022, 38(2): 1819-1833

[47] Yariyan P, Zabihi H, Wolf I D, Karami M, Amiriyan S. Earthquake risk assessment using an integrated fuzzy analytic hierarchy process with artificial neural networks based on GIS: A case study of Sanandaj in Iran. International Journal of Disaster Risk Reduction, 2020, 50: 1-62

[48] Yin Z Q. A study for predicting earthquake disaster loss. Earthquake Eng Eng Vib, 1991, 11(4): 87-96

[49] Zhang X Y, Yang X Y, Yang J. Teaching evaluation algorithm based on grey relational analysis. Complexity, 2021, 2021: 1-9

[50] Zhao M, Jiang W J, Yan G H, Zhang X L, Ma R J. Instant prediction of earthquake casualties for early rescue planning: A joint Poisson mixed modeling approach. International Journal of Disaster Risk Reduction, 2021, 58: 1-11

[51] Zhou D H, Feng H, Cheng L Q, Li W. Earthquake casualty assessment based on the BP neural network of the optimized genetic algorithm. Journal of Safety and Environment, 2017, 17(6): 1-6

[52] Zhu Y G, Diao F Q, Fu Y C, Liu C L, Xiong X. Slip rate of the seismogenic fault of the 2021 Maduo earthquake in western China inferred from GPS observations. Science China – Earth Sciences, 2021, 64(8): 1363-1370

[53] Zubaidi S L, Hashim K, Ethaib S, Bdairi N A, Bugharbee H A, Gharghan S K. A novel methodology to predict monthly municipal water demand based on weather variables scenario. Journal of King Saud University – Engineering Sciences, 2022, 34(3): 163-169

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.