Jul 2026· International Journal for Research in Applied Science and Engineering Technology· 0 citations
TL;DR
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.
Abstract
Coastal flooding is one of the most severe natural hazards, causing significant damage to human life, infrastructure,
and ecosystems in coastal regions. Accurate and timely flood prediction is essential for effective disaster preparedness and
mitigation. This research presents a Coastal Flood Prediction System based on Machine Learning techniques to improve the
accuracy and efficiency of flood forecasting. The proposed system utilizes environmental parameters such as rainfall, humidity,
sea level, and wind speed to predict the likelihood of flood occurrence. Data preprocessing techniques are applied to clean and
prepare the dataset, followed by the implementation of machine learning algorithms, including Logistic Regression, Decision
Tree, and Random Forest. Among these, the Random Forest algorithm demonstrates superior performance in terms of
prediction accuracy and reliability. The developed system is integrated into a user-friendly web application using Python and
Flask, enabling users to obtain real-time flood predictions. Experimental results indicate that the proposed model effectively
identifies flood-prone conditions and supports early warning decision-making. The study highlights the potential of machine
learning in disaster management and provides a scalable framework for future flood prediction systems. The proposed approach
can contribute to reducing the impact of floods by enabling proactive planning and timely response measures
Flood occurrence in tropical regions is intensifying due to climate variability and land-use change, increasing the need for reliable flood response time estimation. Accurate prediction of flood lag time (TL)—the interval between the centroid of excess rainfall and peak runoff—is critical for flood early warning and water resource planning. However, TL estimation remains challenging in data-scarce regions because of complex interactions among watershed morphology, rainfall characteristics, and runoff generation processes. This study evaluates four machine learning (ML) algorithms—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—for predicting TL across twenty gauged watersheds in the Blue Nile Basin of Ethiopia. Fourteen physiographic and hydro-climatic watershed characteristics were used as predictors. Among the tested models, XGBoost achieved the highest training performance (R2 = 0.98, NSE = 0.96), while RF showed better generalization in the test dataset (R2 = 0.77, NSE = 0.70, KGE = 0.71). SVM produced the lowest prediction errors (MAE = 0.95; RMSE = 2.25) but had lower explanatory power (R2 = 0.49). To enhance interpretability and practical applicability, ML-based feature importance was used to develop a parsimonious empirical model: TL = 0.8 + 0.011A − 0.023RI, where A is watershed area and RI is rainfall intensity. This model explained 51% of TL variability and retained much of the predictive skill of more complex ML models. The proposed hybrid ML–empirical framework provides a transparent and operational approach for flood response time estimation in tropical highland watersheds. Its broader applicability remains subject to additional watershed-level validation and regional calibration.
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
Flash floods are among the most destructive natural hazards, often causing substantial loss of life and severe damage to infrastructure and property. Predicting flood-prone areas remains challenging because flood generation is controlled by complex interactions among topographic, hydrological, climatic, and environmental factors. In this study, six machine learning algorithms—Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree Classifier (DTC), AdaBoost, and Artificial Neural Network (ANN)—were developed to predict flash-flood inundation locations using satellite-derived flood inventories from two major rainfall events in Wadi El-Darb and Wadi El-Allaqi, Egypt. Model performance was evaluated using accuracy, precision, recall, and F1-score. During model development, Random Forest and Decision Tree Classifier achieved the highest prediction accuracy (94%), followed by AdaBoost and ANN (92%), while Logistic Regression (89%) and SVM (88%) also produced satisfactory results. To evaluate model generalization, the trained models were independently validated using a rainfall event in Wadi Hodein (Egypt) and a major flash-flood event that occurred in Oman during April 2024. The external validation showed that AdaBoost achieved the highest predictive performance in both validation basins, with accuracies of 87% for Wadi Hodein and 83% for Oman, providing encouraging initial evidence of applicability across hydrologically similar arid watersheds, While AdaBoost and Logistic Regression maintained satisfactory performance during external validation, other algorithms exhibited noticeable reductions in recall and F1-score, particularly in the Oman case study, indicating variability in model generalization across independent watersheds These findings suggest that the proposed framework may support flood susceptibility assessment in ungauged arid environments with comparable hydrological characteristics, although further validation across a wider range of climatic and geological settings is needed. Overall, the results highlight the value of integrating satellite remote sensing with machine learning to support flood hazard assessment, disaster preparedness, early warning systems, and flood risk management in data-scarce regions.
M. Mashal, D. Amin, M. Hagras et al.· Geomatics· 0 citations
Cities flooding is a major hydrological risk in rapidly urbanizing regions, intensified by climate change, extreme rainfall, and inadequate drainage systems. Traditional hydrological models require extensive calibration and high-resolution data, which are often unavailable for many cities. To address this issue, this study proposes a flood prediction framework that integrates Geographic Information Systems (GIS) with Machine Learning (ML). Multi-source geospatial data such as digital elevation models (DEM), land use–land cover (LULC), soil properties, drainage density, rainfall intensity, and historical flood records are used to derive flood conditioning factors in a GIS environment. These factors are then applied as inputs for supervised ML algorithms including Artificial Neural Networks (ANN), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting. Model performance is evaluated using RMSE, MAE, R², and ROC–AUC metrics. Results indicate that hybrid GIS-ML models outperform traditional approaches by effectively capturing non-linear relationships between hydrometeorological and urban factors. The framework provides a reliable decision-support tool for urban planners and disaster management authorities to identify flood-prone areas, improve drainage planning, and enhance early warning systems.
Ahmed Hassan, Fatima Noor· International Journal of Mod...· 0 citations
Rainfall prediction is one of the most significant research areas in meteorology because of its direct influence on
agriculture, water resource management, disaster preparedness, and environmental sustainability. Accurate rainfall forecasting
assists governments, farmers, and disaster management agencies in making informed decisions regarding crop planning,
irrigation scheduling, flood prevention, and drought management. Conventional statistical forecasting methods often fail to
capture the complex nonlinear relationships existing among climatic variables, leading to inaccurate predictions. Machine
Learning (ML) techniques have emerged as efficient alternatives by automatically learning hidden patterns from historical
weather datasets. This paper presents a machine learning-based rainfall prediction system using Multiple Linear Regression
(MLR), Random Forest Regressor, and K-Nearest Neighbor (KNN) Regression algorithms. The proposed model utilizes
historical meteorological parameters such as temperature, humidity, atmospheric pressure, wind speed, and previous rainfall
records to predict future rainfall with improved accuracy. Initially, the collected dataset undergoes preprocessing techniques
including missing value handling, normalization, feature selection, and data transformation. The processed dataset is divided
into training and testing subsets for model development and validation. The performance of each regression algorithm is
evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R² Score, and
prediction accuracy. Experimental results demonstrate that the Random Forest Regressor achieves superior prediction
performance compared with Multiple Linear Regression and KNN Regression by effectively handling nonlinear relationships
and reducing prediction errors. The proposed system provides an efficient and reliable rainfall forecasting solution that can
support agricultural planning and environmental monitoring.
P. Latha, D. Gangadhar· International Journal for Re...· 0 citations
Urban flooding is a major issue to sustainable urban development and disaster risk mitigation. A sustainable AI-based early warning system is suggested to improve the predictive effectiveness and reactiveness and is based on a hybrid deep learning architecture to provide real-time flood hazard estimates. It combines Long Short-Term Memory (LSTM) networks to perform temporal analysis of rainfall data and Convolutional Neural Networks (CNN) to extract spatial features of images in small patches of remote sensing. The hybrid model is effective in describing the multi-modal characteristics of the flood-related data, and the classification performance is improved. Synthetic rainfall sequences and satellite-like images have been evaluated experimentally with an overall accuracy of 94, an F1-score of 0.94 and area under the ROC curve (AUC) of 0.97. Such findings suggest that the generalization and reliability of flood versus non-flood situations are strong. The solution is appropriately designed to be implemented in real time on edge or cloud computing platforms to implement scalable, intelligent and interpretable flood monitoring systems. This framework provides a practical base of future sustainable and proactive urban flood risk management.
Sathiyamoorthy M· 2026 7th International Confe...· 0 citations