momererkoc/cloud_classifier

Ensemble Learning Cloud Classifier

Note: This project was developed as a assignment for the Youth AI Initiative. It demonstrates the application of advanced Deep Learning techniques (Transfer Learning and Stacking Ensembles) to solve meteorological classification problems.

Overview

This project implements a robust Ensemble Learning model to classify images of clouds into 7 distinct meteorological categories. By leveraging the power of Transfer Learning, we combine three state-of-the-art Convolutional Neural Networks (ResNet50, VGG16, and InceptionV3) to extract features, which are then fed into a Meta-Learner (Neural Network) to make the final prediction.

This "Stacked Generalization" approach achieves higher accuracy and stability compared to using individual models alone, effectively handling the visual complexity and ambiguity often found in cloud formations.

Objectives

• To classify cloud types from images with high accuracy.

• To mitigate the issue of limited training data using Data Augmentation and Transfer Learning.

• To address class imbalance using Weighted Loss Functions.

• To demonstrate the effectiveness of stacking multiple weak(er) learners to create a strong meta-learner.

Dataset

The dataset consists of 960 images divided into 7 classes. The data was split into Training (70%), Validation (15%), and Testing (15%) sets.

Classes:

1. cirriform clouds

2. clear sky

3. cumulonimbus clouds

4. cumulus clouds

5. high cumuliform clouds

6. stratiform clouds

7. stratocumulus clouds

Model Architecture

The solution uses a Stacking Ensemble architecture:

Level 0: Base Learners

Three pre-trained models (weights from ImageNet) were used as feature extractors. The top layers were removed and replaced with a custom classification head:

1. ResNet50 (Input: 224x224)

2. VGG16 (Input: 224x224)

3. InceptionV3 (Input: 299x299)

Custom Head Structure:

• GlobalAveragePooling2D

• Dense(256, activation='relu') with L2 Regularization (0.01)

• Dropout(0.6) (To prevent overfitting)

• Dense(7, activation='softmax')

Level 1: Meta-Learner

The predictions (probability vectors) from the three base models are concatenated to form a meta-input vector (size 21). This is fed into a dense neural network:

• Input: Concatenated Predictions

• Hidden Layer: Dense(16, relu) + Dropout(0.4)

• Output: Final Classification

Technical Implementation Details

Data Preprocessing

To handle the small dataset size and prevent overfitting, aggressive Data Augmentation was applied during training:

• Rotation range: 40°

• Width/Height shift: 0.25

• Shear/Zoom: 0.25 / 0.3

• Horizontal & Vertical Flips

• Brightness adjustment: [0.7, 1.3]

Class Balancing

Class weights were computed using sklearn.utils.class_weight to penalize the model more for misclassifying rare classes (e.g., Cumulonimbus which had a weight of ~5.33).

Hyperparameters

• Optimizer: Adam (Learning Rate: 0.0001 for base, 0.001 for meta)

• Loss Function: Categorical Crossentropy

• Batch Size: 64

• Epochs: 75 (with Early Stopping and ReduceLROnPlateau)

Results

The Ensemble Meta-Model outperformed the individual base models on the test set.

• Final Accuracy: 86%

• F1-Score (Weighted): 0.85

Classification Report

Detailed performance metrics by class:

                        precision    recall  f1-score   support

      cirriform clouds       0.87      0.95      0.91        21
             clear sky       1.00      1.00      1.00        18
   cumulonimbus clouds       0.00      0.00      0.00         4
        cumulus clouds       0.81      0.94      0.87        32
high cumuliform clouds       0.89      0.86      0.87        36
     stratiform clouds       1.00      0.85      0.92        13
  stratocumulus clouds       0.70      0.70      0.70        20

              accuracy                           0.86       144
             macro avg       0.75      0.76      0.75       144
          weighted avg       0.84      0.86      0.85       144

Performance Visualizations

Training vs Validation Accuracy

Confusion Matrix

Installation & Usage

Prerequisites

pip install tensorflow numpy pandas matplotlib seaborn scikit-learn pillow requests

Training

The training pipeline is automated:

1. Load and split data.
2. Calculate class weights.
3. Train ResNet50, VGG16, and InceptionV3 individually.
4. Generate validation predictions from all three models.
5. Train the Meta-Learner on these predictions.

Credits

• Author: Muhammed Ömer ERKOÇ

• Organization: Youth AI Initiative

• Dataset Source: SkyVision Cloud Dataset

This project is part of the educational curriculum at the Youth AI Initiative, fostering the next generation of AI specialists.