CFP last date
21 September 2026
Call for Paper
October Edition
IJCA solicits high quality original research papers for the upcoming October edition of the journal. The last date of research paper submission is 21 September 2026

Submit your paper
Know more
The week's pick
Responsive image
Contextual Sentiment Analysis of Airbnb Customer Reviews in Albania: An Investigation of BERT-based Classification

Blerina Zanaj Serxhio Kurti Elma Zanaj
Random Articles
Reseach Article

Neural-XGB Fusion: A Hybrid Approach for Disaster Prediction and Management using Machine Learning

by Devendra Singh Kushwaha, Divya Kishor Sapkale, Kumudini Kishor Khairnar, Sonakshi Sopan Kanse, Mansi Nilkanth Bhole
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 144
Year of Publication: 2026
Authors: Devendra Singh Kushwaha, Divya Kishor Sapkale, Kumudini Kishor Khairnar, Sonakshi Sopan Kanse, Mansi Nilkanth Bhole
10.5120/ijcaaefd60e28e07

Devendra Singh Kushwaha, Divya Kishor Sapkale, Kumudini Kishor Khairnar, Sonakshi Sopan Kanse, Mansi Nilkanth Bhole . Neural-XGB Fusion: A Hybrid Approach for Disaster Prediction and Management using Machine Learning. International Journal of Computer Applications. 187, 144 ( Sep 2026), 27-35. DOI=10.5120/ijcaaefd60e28e07

@article{ 10.5120/ijcaaefd60e28e07,
author = { Devendra Singh Kushwaha, Divya Kishor Sapkale, Kumudini Kishor Khairnar, Sonakshi Sopan Kanse, Mansi Nilkanth Bhole },
title = { Neural-XGB Fusion: A Hybrid Approach for Disaster Prediction and Management using Machine Learning },
journal = { International Journal of Computer Applications },
issue_date = { Sep 2026 },
volume = { 187 },
number = { 144 },
month = { Sep },
year = { 2026 },
issn = { 0975-8887 },
pages = { 27-35 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number144/neural-xgb-fusion-a-hybrid-approach-for-disaster-prediction-and-management-using-machine-learning/ },
doi = { 10.5120/ijcaaefd60e28e07 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-09-19T02:57:40.850009+05:30
%A Devendra Singh Kushwaha
%A Divya Kishor Sapkale
%A Kumudini Kishor Khairnar
%A Sonakshi Sopan Kanse
%A Mansi Nilkanth Bhole
%T Neural-XGB Fusion: A Hybrid Approach for Disaster Prediction and Management using Machine Learning
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 144
%P 27-35
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Natural disasters such as floods, earthquakes, cyclones, landslides, droughts and wildfires are becoming increasingly frequent and catastrophic due to climate change, rapid urban agglomeration, and severe environmental degradation. These events impose devastating impacts on human life, public infrastructure, and socioeconomic stability. Traditional forecasting approaches primarily rely on numerical physical models and historical rainfall heuristics, which struggle to capture complex, multi-scale, and non-linear interactions across heterogeneous geospatial and hydrometeorological domains. To address these critical shortcomings, this paper presents Neural-XGB Fusion, an integrated hybrid machine learning architecture combining the deep non-linear latent representation learning capabilities of Deep Neural Networks (DNN) with the superior gradient-boosted decision boundary partitioning of eXtreme Gradient Boosting (XGBoost) for flood prediction and disaster management. The framework ingests multi-source data including multi-temporal rainfall, ambient temperature, humidity, river water discharge, historical inundation footprints, digital elevation slope, and crowdsourced distress telemetry. Extensive experimental benchmarking on a curated multi-basin dataset of 24,750 observation points reveals that Neural-XGB Fusion achieves state-of-the-art predictive performance with an overall classification accuracy of 97.45%, precision of 97.10%, recall of 96.85%, F1-score of 96.97%, and an Area Under the ROC Curve (ROC-AUC) of 0.991, substantially outperforming Random Forest (86.42%), SVM (83.15%), standalone MLP (89.20%), standalone XGBoost (93.65%), and CNN-LSTM (92.10%). Furthermore, an integrated Explainable AI (XAI) engine utilizing SHAP provides both global feature attributions and localized situational explanations. The system is containerized via FastAPI and Docker and benchmarked under cloud deployment on Microsoft Azure, demonstrating ultra-low sub-5ms inference latency and high throughput. This unified platform effectively equips disaster management authorities with early warning intelligence, scenario simulations, and optimized resource allocation.

References
  1. M. Asim Saleem, W. Benjapolakul, W. Srisiri, S. Chaitusaney, and P. Kaewplung, "A Hybrid Prediction Model Integrating Artificial Intelligence and Geospatial Analysis for Disaster Management," IEEE Access, vol. 13, pp. 43716–43727, 2025, doi: 10.1109/ACCESS.2025.3545449.
  2. S. H. Mahir et al., "Advanced Hydro-Informatic Modeling Through Feedforward Neural Network, Federated Learning, and Explainable AI for Enhancing Flood Prediction," IEEE Open Journal of the Computer Society, vol. 6, pp. 726–738, 2025, doi: 10.1109/OJCS.2025.3556424.
  3. V. Chamola, V. Hassija, S. Gupta, A. Goyal, M. Guizani, and B. Sikdar, "Disaster and Pandemic Management Using Machine Learning: A Survey," IEEE Internet of Things Journal, vol. 8, no. 21, pp. 16047–16071, Nov. 2021, doi: 10.1109/JIOT.2020.3044966.
  4. S. Puttinaovarat and P. Horkaew, "Flood Forecasting System Based on Integrated Big and Crowdsource Data by Using Machine Learning Techniques," IEEE Access, vol. 8, pp. 5885–5894, 2020, doi: 10.1109/ACCESS.2019.2963819.
  5. N. Fatima et al., "Integrating Machine Learning Models with Probability Distribution Methods for Extreme Flood Risk Assessment," IEEE Access, vol. 13, pp. 160922–160938, 2025, doi: 10.1109/ACCESS.2025.3598121.
  6. P. Yang, X. Xu, M. Shao, and Y. Liu, "Intelligent Prediction of Flood Disaster Risk Levels Based on Knowledge Graph and Graph Neural Networks," IEEE Access, vol. 13, pp. 8416–8424, 2025, doi: 10.1109/ACCESS.2025.3525757.
  7. M. Asim Saleem, A. Javeed, W. Benjapolakul, W. Srisiri, S. Chaitusaney, and P. Kaewplung, "Neural-XGBoost: A Hybrid Approach for Disaster Prediction and Management Using Machine Learning," IEEE Access, vol. 13, pp. 86768–86780, 2025, doi: 10.1109/ACCESS.2025.3569499.
  8. S. Ahmadzai et al., "Machine Learning Regression Models for Rainfall Prediction Using Satellite-Derived Meteorological Data and Ground Observations," Remote Sensing, vol. 17, no. 2, Art. no. 312, 2025, doi: 10.3390/rs17020312.
  9. C. Subashini and S. Sellamuthu, "Recent Trends in the Quality Module of Sustainable Water Management Models — A Systematic Review," IEEE Access, vol. 13, pp. 81236–81251, 2025, doi: 10.1109/ACCESS.2025.3560783.
  10. N. A. Nunez, M. Vargas-Bejarano, and C. Sanchez, "The More You Know, the Less You Trust: Knowledge Paradox in AI-Driven Disaster Management," IEEE Access, vol. 14, pp. 82344–82355, 2026, doi: 10.1109/ACCESS.2026.3694008.
  11. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD '16), San Francisco, CA, USA, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.
  12. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
  13. F. Chollet, Deep Learning with Python, 2nd ed. Shelter Island, NY, USA: Manning Publications, 2021.
  14. Scikit-learn Developers, "Scikit-learn: Machine Learning in Python," [Online]. Available: https://scikit-learn.org.
  15. TensorFlow Developers, "TensorFlow Documentation and API Reference," [Online]. Available: https://www.tensorflow.org.
  16. Kaggle, "Flood Prediction and Meteorological Hydrological Datasets," [Online]. Available: https://www.kaggle.com/datasets.
  17. Open Government Data (OGD) Platform India, "Water Resources and Hydrological Telemetry Portal," [Online]. Available: https://www.data.gov.in/.
  18. A. Pourzangbar, P. Oberle, A. Kron, and M. J. Franca, "Analysis of the Utilization of Machine Learning to Map Flood Susceptibility," Journal of Flood Risk Management, vol. 18, no. 2, Art. no. e70042, 2025, doi: 10.1111/jfr3.70042.
  19. L. B. L. Santos et al., "Machine learning-based hydrological models for flash floods: A systematic literature review," Smart Construction and Sustainable Cities, vol. 3, Art. no. 21, 2025, doi: 10.1007/s44268-025-00071-9.
  20. Z. Zhang, D. Wang, Y. Mei, J. Zhu, and X. Xiao, "Developing an explainable deep learning module based on the LSTM framework for flood prediction," Frontiers in Water, vol. 7, Art. no. 1562842, 2025, doi: 10.3389/frwa.2025.1562842.
  21. H. Huang et al., "Improving the explainability of CNN-LSTM-based flood prediction with integrating SHAP technique," Ecological Informatics, vol. 84, Art. no. 102904, 2024, doi: 10.1016/j.ecoinf.2024.102904.
  22. X. Fu et al., "An XGBoost-SHAP framework for identifying key drivers of urban flooding and developing targeted mitigation strategies," Ecological Indicators, vol. 175, Art. no. 113579, 2025, doi: 10.1016/j.ecolind.2025.113579.
  23. S. Vemula, F. Gatti, and P. Jehel, "Graph Transformer-Based Flood Susceptibility Mapping: Application to the French Riviera and Railway Infrastructure under Climate Change," arXiv: 2504.03727, 2025.
  24. T. Islam, E. B. Zeleke, M. Afroz, and A. M. Melesse, "A Systematic Review of Urban Flood Susceptibility Mapping: Remote Sensing, Machine Learning, and Other Modeling Approaches," Remote Sensing, vol. 17, no. 3, Art. no. 524, 2025, doi: 10.3390/rs17030524.
  25. G. Bertoli, K. Schroeter, R. Arcucci, and E. Caporali, "A Hybrid Machine Learning Framework for Improved Short-Term Peak-Flow Forecasting," arXiv:2601.09336, 2026.
  26. P. Kawadkar, D. K. Rathore, D. S. Kushwaha, B. Rebecca, G. P. J. Karunya, and P. M. Yohan, "Performance analysis of image compression techniques for MRI image using machine learning techniques," AIP Conf. Proc., vol. 3214, no. 1, Art. no. 020038, Nov. 2024, doi: 10.1063/5.0239127.
  27. G. R. Kadam, N. U. Jadhav, M. A. Wassay, Y. R. Mohabe, K. B. Loharkar, and D. S. Kushwaha, "Facial Recognition-Based Classroom Attendance System with Real-Time Group Photo Processing Using Machine Learning Approach," in Proc. Int. Conf. Comput. Sci. Commun. Eng. (ICCSCE 2025), Atlantis Press, pp. 1166–1177, 2025, doi: 10.2991/978-94-6463-858-5_97.
Index Terms

Computer Science
Information Sciences

Keywords

Disaster Prediction Deep Neural Networks XGBoost Hybrid AI Fusion Flood Forecasting Explainable AI SHAP Interpretation Cloud Deployment Decision Support System

Powered by PhDFocusTM