Production Forecasting - Volve Field

This project focuses on forecasting oil and gas production using historical data from the Equinor Volve Field (an open-source dataset). It utilizes data exploration, time-series analysis, and machine learning techniques to predict future production rates, which is critical for reservoir management and economic planning in the petroleum industry.

📊 Project Overview

Accurate production forecasting helps engineers estimate the Ultimate Recoverable Resources (URR) and optimize well performance. This repository contains a comprehensive workflow from raw data cleaning to predictive modeling.

Key Features

• Data Cleaning: Handling missing values and outliers in the Volve production dataset.
• Exploratory Data Analysis (EDA): Visualizing production trends (Oil, Gas, Water) and pressure data.
• Time-Series Forecasting: Implementing models to predict future production based on historical trends.
• Decline Curve Analysis (DCA): (Optional/Likely) Traditional reservoir engineering methods for production decline.

📁 Repository Structure

• Volve production data.xlsx: The primary dataset containing daily production logs, wellbore information, and pressure data from the Volve field.
• data_exploration.ipynb: A Jupyter Notebook containing the end-to-end analysis, including data visualization, feature engineering, and model implementation.
• .DS_Store: System file (can be ignored).

🚀 Getting Started

Prerequisites

You will need Python 3.x and the following libraries:

pip install pandas numpy matplotlib seaborn scikit-learn openpyxl

Installation

1. Clone the repository:

git clone https://github.com/anmolshukla13/Production-Forecasting.git

2. Navigate to the project directory:

cd Production-Forecasting

3. Run the Jupyter Notebook:

jupyter notebook data_exploration.ipynb

📈 Dataset

The dataset used is the Volve Field Data, released by Equinor. It includes:

• Daily Production: Volume of oil, gas, and water produced.
• Injection Data: Water injection volumes used for pressure maintenance.
• Pressure/Temperature: Bottom-hole and wellhead measurements.

🛠️ Methodology

1. Preprocessing: Converting timestamps, handling null values, and filtering data for specific wells (e.g., 15/9-F-14).
2. Visualization: Plotting production curves to identify "Plateau," "Decline," and "Shut-in" periods.
3. Modeling: Training regression or time-series models (like LSTM or Prophet, depending on notebook content) to forecast the next 12–24 months of production.

🤝 Contributing

Contributions are welcome! If you'd like to improve the forecasting models or add new analysis techniques:

1. Fork the Project.
2. Create your Feature Branch (git checkout -b feature/NewForecastingModel).
3. Commit your Changes (git commit -m 'Add some feature').
4. Push to the Branch (git push origin feature/NewForecastingModel).
5. Open a Pull Request.

📜 License

Distributed under the MIT License. See LICENSE for more information (if applicable).

---

Author: Anmol Shukla