Improving flood hazard susceptibility assessment by integrating hydrodynamic modeling with remote sensing and ensemble machine learning

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 11, 2025

Abstract Floods are natural disasters with significant economic and infrastructural impacts. Assessing flood susceptibility in mountainous urban regions is particularly challenging due to the complicated interaction which structures terrain affect behavior. This study employs two ensemble machine learning algorithms, Extreme Gradient Boosting (XGBoost) Random Forest (RF), develop maps for Hunza-Nagar region, has been experiencing frequent flooding past three decades. An unsteady flow simulation carried out HEC-RAS utilizing a 100-year return period hydrograph as an input boundary condition, output of provided spatial inundation extents necessary developing inventory. Ten explanatory factors, including climatic, geological, geomorphological features namely elevation, slope, curvature, topographic wetness index (TWI), normalized difference vegetation (NDVI), land use cover (LULC), rainfall, lithology, distance roads rivers considered mapping. For inventory, random sampling technique adopted create repository non-flood points, incorporating ten geo-environmental conditioning factors. The models’ accuracy assessed using area under curve (AUC) receiver operating characteristics (ROC). prediction rate AUC values 0.912 RF 0.893 XGBoost, also demonstrating superior performance accuracy, precision, recall, F1-score, kappa evaluation metrics. Consequently, model selected represent map area. resulting will assist national disaster management infrastructure development authorities identifying high susceptible zones carrying early mitigation actions future floods.

Language: Английский

---

Enhancing flood susceptibility mapping in Meghna River basin by introducing ensemble Naive Bayes with stacking algorithms

Geomatics Natural Hazards and Risk, Journal Year: 2025, Volume and Issue: 16(1)

Published: Feb. 13, 2025

Language: Английский

---

Planning scale flood risk assessment and prediction in ultra-high density urban environments: The case of Hong Kong

Ecological Indicators, Journal Year: 2024, Volume and Issue: 162, P. 112000 - 112000

Published: April 13, 2024

Climate change has significantly increased the risks associated with urban flooding. However, most research on flood risk assessment focuses large-scale climate changes and impacts, leaving a gap in high spatial resolution of inter-urban areas. This makes it difficult to guide regional planning for government. Therefore, this study aims explore floods ultra-high-density cities under at scale, using Hong Kong as case study. We comprehensively assessed index (FRI) built environment 211 tertiary units (TPUs) from three dimensions vulnerability, exposure, hazard 2006 2021. also employed prediction model forecast spatial–temporal patterns FRI next 5, 10, 15 years evaluated uneven distribution risks. The results show that TPUs yearly, which poses higher threats agglomerative areas transportation functional facilities. Additionally, future will further impact coastal western Kong, resulting more negative impacts high-building should prioritize integrating management mitigation measures.

Language: Английский

---

Flood susceptibility mapping leveraging open-source remote-sensing data and machine learning approaches in Nam Ngum River Basin (NNRB), Lao PDR

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 28, 2024

Frequent floods caused by monsoons and rainstorms have significantly affected the resilience of human natural ecosystems in Nam Ngum River Basin, Lao PDR. A cost-efficient framework integrating advanced remote sensing machine learning techniques is proposed to address this issue enhancing flood susceptibility understanding informed decision-making. This study utilizes geo-datasets algorithms (Random Forest, Support Vector Machine, Artificial Neural Networks, Long Short-Term Memory) generate comprehensive maps. The results highlight Random Forest's superior performance, achieving highest train test Area Under Curve Receiver Operating Characteristic (AUROC) (1.00 0.993), accuracy (0.957), F1-score (0.962), kappa value (0.914), with lowest mean squared error (0.207) Root Mean Squared Error (0.043). Vulnerability particularly pronounced low-elevation low-slope southern downstream areas (Central part PDR). reveal that 36%–53% basin's total area highly susceptible flooding, emphasizing dire need for coordinated floodplain management strategies. research uses freely accessible data, addresses data scarcity studies, provides valuable insights disaster risk sustainable planning

Language: Английский

---

Assessing future changes in flood susceptibility under projections from the sixth coupled model intercomparison project: case study of Algiers City (Algeria)

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 2, 2024

Language: Английский

---

A novel flood conditioning factor based on topography for flood susceptibility modeling

Geoscience Frontiers, Journal Year: 2024, Volume and Issue: 16(1), P. 101960 - 101960

Published: Nov. 1, 2024

Language: Английский

---

Advancing flood susceptibility prediction: A comparative assessment and scalability analysis of machine learning algorithms via artificial intelligence in high‐risk regions of Pakistan

Journal of Flood Risk Management, Journal Year: 2024, Volume and Issue: 18(1)

Published: Nov. 24, 2024

Abstract Flood susceptibility mapping (FSM) is crucial for effective flood risk management, particularly in flood‐prone regions like Pakistan. This study addresses the need accurate and scalable FSM by systematically evaluating performance of 14 machine learning (ML) models high‐risk areas The novelty lies comprehensive comparison these use explainable artificial intelligence (XAI) techniques. We employed XAI to identify significant conditioning factors at both model training prediction stages. were assessed accuracy scalability, with specific focus on computational efficiency. Our findings indicate that LGBM XGBoost are top performers terms accuracy, also excelling achieving a time ~18 s compared LGBM's 22 random forest's 31 s. evaluation framework presented applicable other highlights superior accuracy‐focused applications, while optimal scenarios constraints. this can assist different scaling up analysis larger geographical region which could better decision‐making informed policy production management.

Language: Английский

---

Advanced Efficient Feature Selection Integrating Augmented Extreme Learning Machine and Particle Swarm Optimization for Predicting Nitrogen Use Efficiency and Yield in Corn

Agronomy, Journal Year: 2025, Volume and Issue: 15(1), P. 244 - 244

Published: Jan. 20, 2025

Efficient nitrogen management is crucial for improving corn productivity while minimizing environmental impacts. This study evaluates the response of to fertilization using three key metrics: yield; harvest index (NHI); and agronomic use efficiency (ANUE). experiment was conducted over years (2021–2023) across 84 sites in Quebec, Canada, with five treatments applied post-emergence (0, 50, 100, 150, 200 kg N/ha) initial at seeding (30 60 kg/ha). In addition, various soil health indicators, including physical, chemical, biochemical properties, were monitored understand their interaction efficiency. Machine learning techniques, such as augmented extreme machine (AELM) particle swarm optimization (PSO), employed optimize recommendations by identifying most relevant features predicting yield (NUE). The results highlight that integrating indicators enzyme activities (β-glucosidase [BG] N-acetyl-β-D-glucosaminidase [NAG]) proteins into models improves prediction accuracy, leading enhanced sustainability. These findings suggest advanced data-driven approaches can significantly contribute more precise sustainable strategies.

Language: Английский

---

Landslide susceptibility assessment based on remote sensing interpretation and DBN-MLP model: a case study of Yiyuan County, China

Stochastic Environmental Research and Risk Assessment, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 19, 2025

Language: Английский

---

A Systematic Review of Urban Flood Susceptibility Mapping: Remote Sensing, Machine Learning, and Other Modeling Approaches

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 524 - 524

Published: Feb. 3, 2025

Climate change has led to an increase in global temperature and frequent intense precipitation, resulting a rise severe urban flooding worldwide. This growing threat is exacerbated by rapid urbanization, impervious surface expansion, overwhelmed drainage systems, particularly regions. As becomes more catastrophic causes significant environmental property damage, there urgent need understand address flood susceptibility mitigate future damage. review aims evaluate remote sensing datasets key parameters influencing provide comprehensive overview of the causative factors utilized mapping. also highlights evolution traditional, data-driven, big data, GISs (geographic information systems), machine learning approaches discusses advantages limitations different mapping approaches. By evaluating challenges associated with current practices, this paper offers insights into directions for improving management strategies. Understanding identifying foundation developing effective resilient practices will be beneficial mitigating

Language: Английский

---