2023· International Journal of Emerging Trends in Multidisciplinary Research· 0 citations
TL;DR
A full predictive framework of disasters based on the integrated data system as a conglomeration of satellite imagery, Internet of Things (IoT) sensor data, meteorological data, geospatial databases, social media feeds and historic disaster data is presented.
Abstract
Both natural and man-made calamities have major impacts to life, infrastructures, and economic stability across the globe. The rising rate and severity of catastrophes like earthquakes, floods, cyclones, landslides, wildfires and pandemics require the creation of sophisticated forecasting methods. Conventional ways of managing disasters tend to use isolated data sources and manual interpretation thereby providing restrictions on predictive accuracy and response frequency. The paper is a full predictive framework of disasters based on the integrated data system as a conglomeration of satellite imagery, Internet of Things (IoT) sensor data, meteorological data, geospatial databases, social media feeds and historic disaster data. The proposed model optimizes the situational awareness and early warning capabilities by using machine and deep learning. The research presents a multi-layered data acquisition, data preprocessing, and data trending, feature extraction, and predictive modeling. Sir-complicated algorithms that include the use of random forest, support vector machines, Convolutional Neural Networks, and Long Short-term Memory networks are used to process spatio-temporal patterns. The real-world datasets were used to test the system and show better prediction accuracy and lower response time. Findings from experimental outcomes show that holistic data-driven systems work far much better than traditional single source methodologies. The results point out the significance of data integration and smart analytics in disaster risk management. The study will help develop resilient smart disaster management systems and form a basis on the future advancements in real-time forecasting and emergency response planning.
The findings demonstrate that AI-driven disaster prediction systems significantly improve early warning capabilities, situational awareness, resource allocation, infrastructure protection, and emergency response, ultimately reducing disaster impacts and saving lives.
Alan Bundy, Karen Spärck Jones· International Journal of Mod...· 0 citations
An approach based on multi-layered which involves combining real-time data collection, AI-enhanced predictive analytics, and automated decision-making to improve disaster preparedness and response is suggested to improve disaster preparedness and response.
Pooja Agarwal· International Journal of Mod...· 0 citations
Flood is one of the most destructive natural disasters in Tamil Nadu and needs proper forecasting systems to give early warning and mitigate the disaster. The present study, the Smart Flood Forecasting System is an AI and Machine Learning-powered system that incorporates four key datasets (Flood Inventory, Rainfall, Flood Impact, and IndoFlood events) with real-time weather data and automated voice notifications using Twilio. It used two complementary models: a Proposed Optimized Random Forest model, which was trained using curated datasets only, achieved 97.9% accuracy, 97.7% precision, 96.4% recall, and 97.1% F1-score using hyperparameter optimization and feature selection; and a Real Dataset framework, which used Logistic Regression, KNearest Neighbors (KNN), and The Flood Impact data added insights of the districts to the predictive features in terms of fatalities, injuries and the mean flood duration, enhancing the correlations between human displacement and the severity of floods. The high-risk cases identified during the risk assessment were more than 9,000 with a 60% probability threshold and automated voice alerts were successfully triggered in case of extreme flood scenarios. The system has integrated curated datasets, optimized algorithms, real-time weather integration, and instant communication mechanism, which makes it appear systematic, efficient, and scalable in disaster management to provide timely alerts and actionable insights to flood-prone areas in Tamil Nadu.
Anushya D, A. M· 2026 6th International Confe...· 0 citations
This research presents a Coastal Flood Prediction System based on Machine Learning techniques to improve the accuracy and efficiency of flood forecasting and provides a scalable framework for future flood prediction systems.
K. T. Kumar, D. Bhargavi· International Journal for Re...· 0 citations
Rivers are dynamic geomorphological systems that frequently alter their courses due to erosion, sediment deposition, channel migration, and flooding. Although such changes are normal, a sudden and major change like the diversion of the Kosi River in Bihar in 2008 can cause disastrous flooding, displacement and heavy land loss. The conventional methods are a poor fit because manual interpretation of satellites and hydrological modelling is time-consuming and has limited spatial-temporal resolution and lacks predictability. This study utilizes multi-source databases to present an AI-based Geo-Informatics framework for river course change prediction and disaster risk mitigation. Other than satellite imagery the data also includes hydrology, rain and soil data. The suggested hybrid architecture aims to jointly model the spatial river morphology and the evolution of the spatial pattern over time through the use of machine learning models (e.g. Random Forest, Gradient Boosting) and deep learning components (CNN, U-Net, LSTM/ConvLSTM). The framework has the ability to create predictive geospatial risk maps, forecasts of river migration over time, and interactive visualization products that support disaster preparedness and sustainable usage of water resources. Overall, the results demonstrate the potential of AI-driven Geo-Informatics to transform river monitoring from reactive assessment to proactive prediction, contributing to resilience building in accordance with the UN Sendai Framework (2015-2030) and the Sustainable Development Goals on climate action and water management.
Jay Modhiya, Wasim Khan, Z. A. Ansari et al.· Scientific Reports· 0 citations
Accurate disaster prediction plays a critical role in disaster management and mitigation by reducing the loss of life and
property. Traditional machine learning approaches often struggle to handle complex disaster patterns, class imbalance in
datasets, and challenges in multi-class disaster classification, which reduces prediction reliability. To address these issues, a
hybrid disaster prediction framework based on Neural Networks and XGBoost is proposed for the multi-class classification of
natural disasters. In the proposed framework, neural networks are employed for high-level feature extraction from real-world
disaster data, while XGBoost (Extreme Gradient Boosting) performs efficient classification using gradient-boosted decision
trees. The dataset, sourced from the EM-DAT International Disaster Database, comprises 4,543 samples with 31 features
encompassing wildfires, floods, and earthquakes. The Synthetic Minority Oversampling Technique (SMOTE) is applied
exclusively to the training data to address class imbalance and improve the model's generalization capability. Experimental
results demonstrate improved performance, with the proposed Neural-XGBoost (N-XGB) model achieving 94.72% accuracy,
98.57% ROC-AUC, 90.49% F1-score, and 89.65% precision, outperforming traditional machine learning models. The proposed
system provides a reliable and efficient disaster prediction approach that supports better disaster preparedness and decisionmaking.
Ms. V. Bharathi· International Journal for Re...· 0 citations