Flood Prediction

[thevijayshankersharma]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Flood Prediction Using Machine Learning
:red_circle: Aim : To develop machine learning models for accurate flood prediction by analyzing historical data, weather patterns, topographical information, and real-time sensor inputs. This will improve flood warnings, emergency response, and planning strategies.
:red_circle: Dataset : Historical flood data, weather data, topographical data, and real-time sensor inputs. (Specific dataset sources can be mentioned once identified.)
:red_circle: Approach : Implement 3-4 different machine learning algorithms to develop flood prediction models.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Vijay Shanker Sharma
• GitHub Profile Link : https://github.com/thevijayshankersharma
• Email ID : vijayshankersharma658@gmail.com
• Participant ID (if applicable):
• Approach for this Project : Implementation, Code and Results will be provided
• What is your participant role? GSSOC'24

  ---

  Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

What are the models you are planning to implement here for this problem statement? @thevijayshankersharma

[thevijayshankersharma]

@abhisheks008 These

K-Nearest Neighbors (KNN) Logistic Regression Support Vector Classification Decision Tree Classifier Random Forest Classifier

[abhisheks008]

Hi @thevijayshankersharma this project repository mainly focuses on deep learning methods instead of machine learning methods. You need to update your approach and get back again.

[SHREERAJ11]

• Full name: Sobhan Shreeraj Sa
• GitHub Profile Link: https://github.com/SHREERAJ11
• Email ID: sobhansa03@gmail.com
• Participant ID (if applicable): NA
• Approach for this Project: Build model leveraging CNN.

Since no dataset provided, I want to use the dataset inspired from this published paper. FloodNet Challenge EARTHVISION2021 This contains satellite imagery datasets that include images before and after a disaster, along with annotations describing the damage levels. Main approach is to preprocess data and develop CNN model for image classifying and predicting damage. Also include evaluation results.

[abhisheks008]

Hi @SHREERAJ11 hope you are doing well. Are you participating in the GSSoC Extd event? What are the specific CNN architectures you are planning to implement for this problem statement?

The dataset is good. Thanks for sharing it.

[SHREERAJ11]

Hello! @abhisheks008 I'm doing well, thanks. No, I'm not participating in the extd event. I just wanted to contribute to this issue.

For this problem, I want to use ResNet. Based on the size, I think ResNet34 would be okay. I will also try ResNet50 if not constrained by my resources, also experiment with mobilenet architecture for comparison.

[abhisheks008]

Apart from ResNet what are the other models you are planning to implement here? As you know, you need to implement 3-4 models for each problem statement.

[SHREERAJ11]

I will be implementing ResNet, MobileNet, EfficientNet, and VGG19 models.

[abhisheks008]

Assigning this issue to you @SHREERAJ11

[Niraj1608]

@abhisheks008 assign me this