chandrashekhard17/forest-fires-prediction-algerian-dataset
Domain:
environment and energyRecord type:
project
Creator:
cha
Host:
# Algerian Forest Fires Prediction
This project aims to predict fire occurrences in the forests of Algeria based on the data collected from different regions. The project involves an end-to-end machine learning pipeline using exploratory data analysis (EDA), feature engineering, regression models, and model deployment. The main objective is to estimate the occurrence of fires during specific months.
## Table of Contents
- Project Overview
- Dataset Information
- Exploratory Data Analysis (EDA)
- Feature Engineering
- Modeling
- Pickle Files
- Results
- Screenshots
- Technologies Used
- Installation
- Contributors
- Usage
## Project Overview
Forest fires are a serious concern in Algeria, especially during the summer months. This project aims to predict fire occurrences based on various environmental factors like temperature, wind speed, humidity, etc. The data was analyzed, processed, and used to train regression models for fire estimation. Ridge regression provided the best results, and the model was saved as a pickle file for future use.
## Dataset Information
The dataset contains environmental data collected from multiple regions in Algeria over several months. The main features in the dataset include:
- Temperature
- Humidity
- Wind Speed
- Rainfall
- FFMC (Fine Fuel Moisture Code)
- DMC (Duff Moisture Code)
- DC (Drought Code)
- ISI (Initial Spread Index)
**Target**: Fire Estimation (Burned Area)
## Exploratory Data Analysis (EDA)
EDA was performed to understand the dataset, visualize the distribution of the features, and identify correlations between them. Key insights include:
- Seasonal trends in temperature, humidity, and wind speed.
- Correlation between the Fine Fuel Moisture Code and fire occurrence.
- Outlier detection and handling.
## Feature Engineering
Feature engineering was crucial to improving the model's performance. The following steps were taken:
- Handling missing values.
- Encoding categorical features.
- Normalizing/Standardizing fea …