A recall-optimized LSTM–XGBoost ensemble model for river flood forecasting using multivariate time-series data—case study in Sri Lanka
4 affiliations
- 1Department of Electrical and Telecommunication Engineering, South Eastern University of Sri Lanka , ,
- 2Business Continuity Management & Integrated Emergency Management Program, Faculty of Resilience, Rabdan Academy , ,
- 3Department of Computer and Communication Systems Engineering, University Putra Malaysia , ,
- 4Department of Civil Engineering, South Eastern University of Sri Lanka , ,
Abstract
Riverine (fluvial) flooding remains a significant climate-related disaster in many countries. Extreme rainfall events caused by climate change cause significant damage and disruption to communities living near riverbanks or neighboring land areas, particularly when risk-sensitive development is ignored. This necessitates an effective mechanism to predict river flooding events and provide timely early warnings to the most vulnerable populations in high-risk flood-prone areas. The dynamics of flood risks require a localized, automated, and scalable solution that can be centrally monitored. This study presents a river flood forecasting system integrating artificial intelligence (AI) and Internet of Things (IoT). This system was deployed in one of the flood-prone river basins in Sri Lanka to assess the operational feasibility of real-time hydrological monitoring and flood-risk classification. The proposed system employed two machine learning models, Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost), for flood-risk prediction and IoT sensors (rainfall and ultrasonic sensors) for real-time hydrological data collection. The machine learning models were developed using rainfall, discharge rate, and river water level data to predict flood-risk states. A rule-based ensemble strategy was implemented by combining the outputs of LSTM and XGBoost to prioritize positive-class detection and reduce missed positive-labeled observations. Model performance was evaluated primarily using recall for the positive flood cases, while the overall accuracy was reported as the complementary metric alongside positive-class recall, providing an overall assessment of classification performance. Among the evaluated input window configurations using the same chronological holdout, the rule-based ensemble model with a 1-day input window showed the most favorable observed balance of performance metrics, achieving 100% positive-class recall, with 98.73% accuracy, 50.00% positive-class precision, and 66.67% positive-class F1-score. The 100.00% recall was based on correctly classifying all four positive-labeled observations in the held-out test set (4/4; 95% exact binomial CI: 39.8%−100.0%) and these observations occurred consecutively from November 25 to 28, 2024, and represent one continuous positive-labeled flood episode. The proposed safety-oriented AI-IoT framework demonstrates the operational feasibility of integrating real-time sensing with AI-based flood forecasting; however, longer-term field deployment, including actual flood events, is required to evaluate flood-event prediction performance under real-world flood conditions.
Related
- Monitoring and forecasting groundwater storage dynamics in arid Wadi systems using GRACE/GRACE-FO satellite observations and XGBoost machine learning: Wadi El-Assiuti, Egypt (2003–2030)
- Multivariate phase-space interpretation of ensemble forecasts: A comparison of physical and AI models
- Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
- Sonny-ENS: demystifying machine-learning ensemble weather forecasting
- Conditional-Risk Optimization and KKT Geometry of a Regime- and Horizon-Adaptive Probabilistic Ensemble for Local Weather Forecasting
BibTeX
@article{sankalpa2026recalloptimized,
title = {{A recall-optimized LSTM–XGBoost ensemble model for river flood forecasting using multivariate time-series data—case study in Sri Lanka}},
author = {T. H. S. Sankalpa and G. H. C. Sandaruwan and A. M. Aslam Saja and N. T. M. Sajith and M. F. M. Ishqy},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1903150},
url = {https://europepmc.org/article/PMC/PMC13719459},
note = {CC BY},
}
RIS
TY - JOUR
TI - A recall-optimized LSTM–XGBoost ensemble model for river flood forecasting using multivariate time-series data—case study in Sri Lanka
AU - T. H. S. Sankalpa
AU - G. H. C. Sandaruwan
AU - A. M. Aslam Saja
AU - N. T. M. Sajith
AU - M. F. M. Ishqy
PY - 2026
DA - 2026/10/16
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1903150
UR - https://europepmc.org/article/PMC/PMC13719459
AB - Riverine (fluvial) flooding remains a significant climate-related disaster in many countries. Extreme rainfall events caused by climate change cause significant damage and disruption to communities living near riverbanks or neighboring land areas, particularly when risk-sensitive development is ignored. This necessitates an effective mechanism to predict river flooding events and provide timely early warnings to the most vulnerable populations in high-risk flood-prone areas. The dynamics of flood risks require a localized, automated, and scalable solution that can be centrally monitored. This study presents a river flood forecasting system integrating artificial intelligence (AI) and Internet of Things (IoT). This system was deployed in one of the flood-prone river basins in Sri Lanka to assess the operational feasibility of real-time hydrological monitoring and flood-risk classification. The proposed system employed two machine learning models, Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost), for flood-risk prediction and IoT sensors (rainfall and ultrasonic sensors) for real-time hydrological data collection. The machine learning models were developed using rainfall, discharge rate, and river water level data to predict flood-risk states. A rule-based ensemble strategy was implemented by combining the outputs of LSTM and XGBoost to prioritize positive-class detection and reduce missed positive-labeled observations. Model performance was evaluated primarily using recall for the positive flood cases, while the overall accuracy was reported as the complementary metric alongside positive-class recall, providing an overall assessment of classification performance. Among the evaluated input window configurations using the same chronological holdout, the rule-based ensemble model with a 1-day input window showed the most favorable observed balance of performance metrics, achieving 100% positive-class recall, with 98.73% accuracy, 50.00% positive-class precision, and 66.67% positive-class F1-score. The 100.00% recall was based on correctly classifying all four positive-labeled observations in the held-out test set (4/4; 95% exact binomial CI: 39.8%−100.0%) and these observations occurred consecutively from November 25 to 28, 2024, and represent one continuous positive-labeled flood episode. The proposed safety-oriented AI-IoT framework demonstrates the operational feasibility of integrating real-time sensing with AI-based flood forecasting; however, longer-term field deployment, including actual flood events, is required to evaluate flood-event prediction performance under real-world flood conditions.
SN - 2624-8212
ER -