Scholarlink

<p>Most prevalent and destructive natural disasters represent all weather-related incidents and impact more individuals, especially during floods. These regions assess the susceptibility to flooding, which is crucial for effective disaster risk mitigation. However, current methods for estimating flood damage, including depth-damage functions, frequently fall short regarding regional relevance and precision. To tackle these challenges, an innovative approach known as Knowledge Graph Convolutional Radial Basis DeepLab v3+ (KGCRDLv3) has been developed in conjunction with the Arctic Fox Optimization Algorithm (AFOA) to improve the precision and efficiency of flood zone identification. This method integrates the LIME is utilized in the KGCRDLv3-AFOA methodology, in order to afford interpretable and local explanations of flood zone predictions, which provide the most significant spectral and graphical features in satellite images and knowledge graphs to help make the model more transparent and trustworthy. The incorporation of knowledge graphs within KGCRDLv3 enhances both spatial and contextual comprehension. At the same time, the radial basis convolutional layers are proficient in recognizing complex patterns and addressing fine details in satellite imagery. Additionally, a Long-Range Wide Area Network (LoRaWAN) communication network interface enables the transfer of collected data to cloud servers through the internet of things-enabled devices like Raspberry or Arduino. This method ensures low power consumption and improves scalability in data communications. The proposed approach achieves an accuracy of 99.7%, precision of 98.8%, recall of 98.5%, specificity of 99.2%, detection rate of 98.3%, area under curve of 0.98 and prediction time of 10.52&#xa0;s. Overall, the suggested approach enhances flood area detection by improving spatial-contextual understanding and pattern recognition.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An IoT Enabled Knowledge Graph Convolutional Radial Basis Deeplabv3+ Model for Flood Disaster Detection

  • 期刊论文

  • 发表日期：

    2025年8月4日

查看全文
  • Shashank Shashikant Tolye,
  • Vinayak Ashok Bharadi,
  • Kaushal Kamaleshwar Prasad

摘要

Most prevalent and destructive natural disasters represent all weather-related incidents and impact more individuals, especially during floods. These regions assess the susceptibility to flooding, which is crucial for effective disaster risk mitigation. However, current methods for estimating flood damage, including depth-damage functions, frequently fall short regarding regional relevance and precision. To tackle these challenges, an innovative approach known as Knowledge Graph Convolutional Radial Basis DeepLab v3+ (KGCRDLv3) has been developed in conjunction with the Arctic Fox Optimization Algorithm (AFOA) to improve the precision and efficiency of flood zone identification. This method integrates the LIME is utilized in the KGCRDLv3-AFOA methodology, in order to afford interpretable and local explanations of flood zone predictions, which provide the most significant spectral and graphical features in satellite images and knowledge graphs to help make the model more transparent and trustworthy. The incorporation of knowledge graphs within KGCRDLv3 enhances both spatial and contextual comprehension. At the same time, the radial basis convolutional layers are proficient in recognizing complex patterns and addressing fine details in satellite imagery. Additionally, a Long-Range Wide Area Network (LoRaWAN) communication network interface enables the transfer of collected data to cloud servers through the internet of things-enabled devices like Raspberry or Arduino. This method ensures low power consumption and improves scalability in data communications. The proposed approach achieves an accuracy of 99.7%, precision of 98.8%, recall of 98.5%, specificity of 99.2%, detection rate of 98.3%, area under curve of 0.98 and prediction time of 10.52 s. Overall, the suggested approach enhances flood area detection by improving spatial-contextual understanding and pattern recognition.