Flood Disaster Estimation Using Images and Machine Learning

Clicks: 5
ID: 313216
2023
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Popular

Ranked #68 of 705 articles by views in Journal of Computing & Biomedical Informatics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 705 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Pakistan is exposed to heavy floods every year, which can cause significant damage to property, infrastructure and loss of life. To minimize the loss, an estimation of the post flood disaster using images of inundated areas and Machine learning is a better solution for improving the efficiency and accuracy of disaster response efforts in the country. The research aims to enhance flood disaster management by utilizing real-time data to measure flood water levels in inundated areas.Estimating floodwater levels is challenging due to different levels and moderate visibility of objects. Building precise flood level maps is crucial for assisting emergency plan activities in the case of a flood. It's crucial to gather data from the disaster region in order to create these maps. In this circumstance, National disaster management authorithy (NDMA) platforms might be helpful information source. In this article, we provide a technique for measuring floodwater using images from (NDMA) sites. If there is no previous experience or understanding of the area where the image was taken, determining how much the items in the image are immersed in water might be one method of estimating the flood level. Several things contribute to the difficulty of this endeavor, including: The size of the items in the photograph may not be understood with certainty;  Different areas of the photographic scene's flood-water may appear at varying heights, and objects may only be just partially apparent since they may be submerged in the water. We provide an approach to address these issues that first identifies classes of items whose sizes are roughly known before using this feature to calculate the water level. We first create a dataset of flood-water images to test the viability of this method, and then we train a deep learning model on it. Finally, we demonstrate how our trained model can accurately estimate flood levels while also recognizing objects. Flood Disaster Estimation using images and machine learning has the potential to make a policy based decision on flood disaster estimation in the country. With the use of this proposed solution one can save the lives and property on bigger scale.
Reference Key
imported_1777059838_69ebc7fe6f756 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Farida Memon
Journal Journal of Computing & Biomedical Informatics
Year 2023
DOI
DOI not found
URL
https://jcbi.org/index.php/Main/article/view/233
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.