Overview / Usage

Developing systems for predicting solar flares is of critical importance for mitigating the potential adverse effects of these intense bursts of radiation on power grids, GPS systems, and the safety of individuals in space. Intel OneAPI, with its powerful tools and libraries for high-performance computing, can play a pivotal role in building solar flares prediction systems.

Solar flares are intense bursts of radiation which can disrupt the power grids of a continent, shut down the GPS system or irradiate people exposed in space. It would allow us to precisely aim our observation instruments at upcoming events, and eventually enable countermeasures against such worst-case scenarios.

Methodology / Approach

• The prediction of solar flares proves to be a challenging problem, some even compare it to weather forecasting. And regarding Machine Learning, I find this dataset to be particularly challenging because of the complexity of a single sample (up to 40 images), the relatively small size of samples (8'000 for training), and the fact that it is a regression problem. Intel OneAPI makes it to run faster than other notebooks.
• The Intel® OneAPI toolkit, Intel® OneDAL enables models to be trained. Deliver high-performance computing tools to build, analyze, optimize, and scale AI, machine learning, and deep learning applications.
• Logistic Regression, Tensorflow, Scikit learn, Keras Preprocessing, Pandas, scipy.io, nibabel, csv, numpy, seaborn, matplotlib.
• PIL, keras.preprocessing, tensorflow.keras.preprocessing.image
• Scikit learn

Technologies Used

• The Intel® OneAPI toolkit, Intel® OneDAL enables models to be trained. Deliver high-performance computing tools to build, analyze, optimize, and scale AI, machine learning, and deep learning applications.
• Intel OneAPI is a powerful software development toolkit and programming model from Intel designed to simplify and accelerate application development across a wide range of Intel hardware, including CPUs, GPUs, FPGAs, and other accelerators. It's particularly useful for creating high-performance applications.
• Intel Distribution for Python: This is a Python distribution optimized for Intel hardware, which includes popular data science libraries like NumPy, SciPy, scikit-learn, and more. It enables Python developers to take advantage of Intel's hardware acceleration for machine learning and data analysis.
• Intel DevCloud: Intel provides access to a cloud-based environment (DevCloud) where developers can experiment with and test their code on various Intel architectures without needing access to physical hardware.

Repository

https://github.com/SHIVAANISREE/SolarFlares

Other links

• SDOBenchmark Solar Flares