Discrete Migratory Bird Optimizer with Deep Learning Driven Cyclone Intensity Prediction on Remote Sensing Images DOI Open Access

S. Jayasree,

K. R. Ananthapadmanaban

Engineering Technology & Applied Science Research, Год журнала: 2025, Номер 15(2), С. 21605 - 21610

Опубликована: Апрель 3, 2025

Tropical Cyclones (TCs) are extreme climatic conditions that can crucially disrupt human life. Heavy rainfall and resilient winds follow these systems result in severe consequences for property hamper social economic growth respective areas. Thus, accurate assessments of TC intensity is paramount practical applications theoretical research predicting preventing disasters. Satellite Cloud Images (SCIs) a primary preferable effective data source the study TCs. Efficient estimation often challenging despite remarkable success different SCI-based studies. Recently, Machine Learning (ML) Deep (DL) methods have shown significant potential gained fast development against big data, especially with images. Considerable progress has been made applying Convolutional Neural Networks (CNNs) to predict evaluate This focuses on developing Discrete Migratory Bird Optimizer Dirven Cyclone Intensity Prediction (DMBODL-CIP) technique remote sensing images estimate levels To accomplish this, DMBODL-CIP initially undergoes preprocessing two phases: Bilateral Filtering (BF) Adaptive Histogram Equalization (AHE)-based noise removal contrast enhancement. The utilizes deep CNN-based SqueezeNet model feature extraction process. Then, Belief Network (DBN) used intensity. Finally, DMBO employed optimal hyperparameter selection DBN model, which assists improving overall prediction results. proposed approach was evaluated cyclone image dataset comparison showed an RMSE 6.02 kt outperforming existing techniques.

Язык: Английский

Deep learning for automatic post-disaster debris identification for precise damage assessments using UAV footage DOI

Gyan Prakash,

Sindhuja Kasthala,

Akshay Loya

и другие.

Applied Geomatics, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Язык: Английский

Процитировано

0
The Twins City of Wellington - Palu and Lessons Learned After the Six Years Sulawesi Earthquake for Build Back Better DOI Creative Commons

Ketut Sulendra,

Gidion Turu’allo, Atur P. N. Siregar

и другие.

International Journal of Latest Technology in Engineering Management & Applied Science, Год журнала: 2025, Номер 14(1), С. 269 - 276

Опубликована: Фев. 18, 2025

Abstract: Wellington And Palu Cities Are Passed By A Normal Type Fault, The Population Is Around 400 Thousand People, Including Medium City Water Front Predicate On Bay Area So It Vulnerable To Tsunami Disasters Due Tectonic Earthquakes. Has Been Categorized As Resilience But Not. Based This, Needs Learn Lot About Disaster Management From Wellington, Building Infrastructure That Resistant Earthquake Disasters. This Article Compares Geological Conditions, Risks Hazard, Capacity Of Two Cities. Observing Many Similarities Between Cities, There Certainly Lessons Can Be Used In Managing Their Secondary Impacts Risk Reduction Efforts Achieved Optimally. Condition 6 Years After 28 September 2018, Recovery Process Quite Significant. Reconstruction Similarity Conditions 2011-2012 Sequel Christchurch Rehabilitation Hospital Buildings, Schools, Bridges Viaducts, Airports Other Have Partially Completed. An Important Note Obstacle Availability Fast Accurate Data Damage, Relocation Locations, Covid-19 Relatively Long Duration Progress.

Язык: Английский

Процитировано

0
Discrete Migratory Bird Optimizer with Deep Learning Driven Cyclone Intensity Prediction on Remote Sensing Images DOI Open Access

S. Jayasree,

K. R. Ananthapadmanaban

Engineering Technology & Applied Science Research, Год журнала: 2025, Номер 15(2), С. 21605 - 21610

Опубликована: Апрель 3, 2025

Tropical Cyclones (TCs) are extreme climatic conditions that can crucially disrupt human life. Heavy rainfall and resilient winds follow these systems result in severe consequences for property hamper social economic growth respective areas. Thus, accurate assessments of TC intensity is paramount practical applications theoretical research predicting preventing disasters. Satellite Cloud Images (SCIs) a primary preferable effective data source the study TCs. Efficient estimation often challenging despite remarkable success different SCI-based studies. Recently, Machine Learning (ML) Deep (DL) methods have shown significant potential gained fast development against big data, especially with images. Considerable progress has been made applying Convolutional Neural Networks (CNNs) to predict evaluate This focuses on developing Discrete Migratory Bird Optimizer Dirven Cyclone Intensity Prediction (DMBODL-CIP) technique remote sensing images estimate levels To accomplish this, DMBODL-CIP initially undergoes preprocessing two phases: Bilateral Filtering (BF) Adaptive Histogram Equalization (AHE)-based noise removal contrast enhancement. The utilizes deep CNN-based SqueezeNet model feature extraction process. Then, Belief Network (DBN) used intensity. Finally, DMBO employed optimal hyperparameter selection DBN model, which assists improving overall prediction results. proposed approach was evaluated cyclone image dataset comparison showed an RMSE 6.02 kt outperforming existing techniques.

Язык: Английский

Процитировано

0