Particle Position Prediction in RSD - Data Science Pipeline

Project Overview

This repository contains our work Me & Sana Ailla on a data science project for predicting the positions of particles (e.g., electrons) as they pass through a Resistive Silicon Detector (RSD). The project aims to build a robust predictive model to accurately determine the $(x, y)$ coordinates of particle events based on signal measurements from the detector's pads.

Problem Statement

This project addresses a significant challenge in particle physics: accurately predicting the positions of particles, like electrons, as they pass through a Resistive Silicon Detector (RSD). The task involves analyzing signals captured by the RSD's pads, which provide crucial data points for determining particle trajectories. The complexity of this problem lies in the intricate nature of the signals and the precision required to accurately map particle positions. Developing a predictive model capable of handling this complexity is not only essential for advancing our understanding of particle behaviors but also has broader implications in the field of physics research and detector technology.

Dataset

The dataset for this project comprises 514,000 events, each representing a unique particle interaction with the RSD. Key features in this dataset include signal magnitude, area, and delay, which are essential for understanding the behavior of particles as they pass through the detector. These features serve as the basis for predicting the $(x, y)$ coordinates of particle events. The dataset's large size and comprehensive feature set present an opportunity to develop and train sophisticated models capable of high precision in particle position prediction. \

For each signal measured by each of the 12 pads, some features are extracted and comprise the dataset. In particular:

• pmax[0], pmax[1], ... pmax[17]: the magnitude of the positive peak of the signal, in mV
• negpmax[0], negpmax[1], ... negpmax[17]: the magnitude of the negative peak of the signal, in mV
• tmax[0], tmax[1], ... tmax[17]: the delay (in ns) from a reference time when the positive peak of the signal occurs
• area[0], area[1], ... area[17]: the area under the signal
• rms[0], rms[1], ... rms[17]: the root mean square (RMS) value of the signal.

Repository Structure

Provide an overview of the repository's structure. Example:

├── data                   # Directory containing the dataset
├── notebooks              # Jupyter notebooks with exploratory data analysis and models
├── src                    # Source code for the project
├── results                # Results and visualizations generated from the models
├── LICENSE
└── README.md

(Adjust the above structure based on your repository's actual content.)

Installation and Usage

Instructions on how to set up the environment, install necessary dependencies, and run the code.

```bash
# Example of installation steps
git clone [repository URL]
cd [repository's folder]
pip install -r requirements.txt
# etc.
```

Models and Techniques

Describe the models and techniques used in the project. Discuss why these were chosen and how they contribute to solving the problem.

Results and Evaluation

Summarize the results achieved, including key statistics and findings. Discuss the evaluation metric used and the performance of your models.

Visualization

(Optional) Include any visualizations that illustrate key aspects of the data or the results of your analysis.

Contributing

Guidelines for how others can contribute to this project. Example:

Contributions to this project are welcome! To contribute, please fork the repository, make your changes, and submit a pull request.

License

State the license under which this project is available. Common licenses for open-source projects include MIT, GPL, etc.

Contact

Your contact information for questions or collaboration inquiries.

Acknowledgements

(Optional) Acknowledge any individuals, organizations, or datasets that were crucial to the completion of this project.