XEventNet: Extreme Weather Event Prediction using Convolutional Neural Networks and In Situ Visualization

Simple item page
dc.contributor.authorWani, Muzafar Ahmaden_US
dc.contributor.authorMalakar, Preetien_US
dc.contributor.editorReina, Guidoen_US
dc.contributor.editorRizzi, Silvioen_US
dc.contributor.editorGueunet, Charlesen_US
dc.date.accessioned2025-05-26T07:15:13Z
dc.date.available2025-05-26T07:15:13Z
dc.date.issued2025
dc.description.abstractExtreme weather phenomena such as cyclones, torrential rainfall, snow storms, flash floods and landslides pose serious threat to living beings and property all over the world. An accurate and early prediction system for these extreme events may minimize the loss of life and property. However, this requires an online prediction system integrated with the weather simulation model for faster prediction such that low I/O bandwidth does not hinder performance. We present an in situ framework, XEventNet, that integrates weather simulation, deep learning-based prediction, and visualization. XEventNet predicts extreme events at real-time while the simulation is running using a Convolutional Neural Network (CNN). XEventNet is trained and tested on 400 events (extreme and non-extreme). Data is streamed online from XEventNet simulation processes to prediction processes for parallel inference. XEventNet uses the prediction values with high confidence to selectively transfer sub-domains of the large parent simulation domain. We use ADIOS2 for parallel data transfers via memory between groups of processes. This helps in timely prediction and visualization of critical weather events despite large volume of simulation data. We performed weather simulations at 9 km resolutions, thereby producing gigabytes of data per time step. XEventNet is able to classify four extreme events at real-time and visualize the same. We achieved an average prediction accuracy of 90.25% for all extreme events using a single CNN model. We ran weather simulations on up to 512 processes and parallel predictions on up to 64 processes, thereby streaming gigabytes of data in parallel within seconds. This was possible due to efficient data transfer and process mapping. Furthermore, our selective data transfer for visualization resulted in more than 70% reduction in data size, thereby improving the end-to-end simulation-prediction-visualization times.en_US
dc.description.sectionheadersPapers
dc.description.seriesinformationEurographics Symposium on Parallel Graphics and Visualization
dc.identifier.doi10.2312/pgv.20251154
dc.identifier.isbn978-3-03868-274-5
dc.identifier.issn1727-348X
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/pgv.20251154
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pgv20251154
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectVisualization application domain Scientific Visualization CCS Concepts: Human-centered computing->Visualization; Computing methodologies->Parallel computing methodologies
dc.subjectVisualization application domain Scientific Visualization CCS Concepts
dc.subjectHuman centered computing
dc.subjectVisualization
dc.subjectComputing methodologies
dc.subjectParallel computing methodologies
dc.titleXEventNet: Extreme Weather Event Prediction using Convolutional Neural Networks and In Situ Visualizationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pgv20251154.pdf
Size:
2.28 MB
Format:
Adobe Portable Document Format
Download
Collections
EGPGV25: Eurographics Symposium on Parallel Graphics and Visualization