Advanced hybrid CNN-Bi-LSTM model augmented with GA and FFO for enhanced cyclone intensity forecasting

Alexandria Engineering Journal, Год журнала: 2024, Номер 92, С. 346 - 357

Опубликована: Март 9, 2024

Predicting cyclone intensity is an important aspect of weather forecasting since it influences disaster preparation and response. This framework addresses the pressing need for precise prediction by presenting a unique predictive model based on hybrid CNN Bi-LSTM architecture optimized using Genetic Algorithm (GA) enhanced Fruit Fly Optimizer (FFO). Existing methods have primarily relied traditional machine learning models meteorological data, demonstrating limitations in capturing complex spatial-temporal patterns inherent evolution. These drawbacks include insufficient feature extraction abilities, underutilization convolutional neural networks (CNN), poor tuning. method incorporates that tuned (FFO), resulting higher accuracy. The experimental results are implemented Python software, they reveal this outperforms current average 21% when compared to existing such as VGG-16 achieved accuracy 78% Ty 5-CNN (95.23%). suggested CNN-Bi-LSTM predicts strength with excellent 99.4%. approach offers possible avenue increasing prediction, hence improving preparedness risk mitigation efforts sensitive locations.

Язык: Английский

---

Leveraging geo-computational innovations for sustainable disaster management to enhance flood resilience

Discover Geoscience, Год журнала: 2024, Номер 2(1)

Опубликована: Июль 16, 2024

Abstract The increasing frequency of flood disasters around the globe highlights need for creative approaches to improve disaster preparedness. This thorough analysis and assessment explore topic enhancing resilience by utilising cutting-edge geo-computational techniques. By combining a variety techniques, such as remote sensing, geographic information systems (GIS), LiDAR, unmanned aerial vehicles (UAVs), technologies like machine learning geospatial big data analytics, study provides complex framework monitoring, risk assessment, mitigation. using sensing technology, occurrences can be tracked in real time inundations may precisely mapped, which makes proactive response plans possible. GIS facilitates effective evacuation planning streamlining spatial decision-making procedures providing critical insights into risky locations. High-resolution elevation is provided LiDAR essential precise modelling simulation. Unmanned Aerial Vehicles (UAVs) quickly deployed assist with situational awareness damage during disaster. Furthermore, predictive skills are enhanced combination opening door creation adaptive reaction early warning systems. investigation how tools significantly community lessen negative effects disasters. After review literature case studies, this clarifies these might preparation great extent.

Язык: Английский

---

Smart monitoring solution for dengue infection control: A digital twin-inspired approach

Computer Methods and Programs in Biomedicine, Год журнала: 2024, Номер 257, С. 108459 - 108459

Опубликована: Окт. 10, 2024

Язык: Английский

---

Enhancing flood monitoring and prevention using machine learning and IoT integration

Natural Hazards, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 4, 2024

Язык: Английский

---

Review of flood monitoring and prevention approaches: a data analytic perspective

Natural Hazards, Год журнала: 2024, Номер unknown

Опубликована: Дек. 2, 2024

Язык: Английский

---