Forecast future CO2 emission in Sri Lanka

You can adjust following range input to predict CO2 emission in next 20 years from 2019.

We can improve this model by changing the model architecture, and adding more training data. At this level I wanted to showcase my work towards implementation and deployment of Machine Learning model.

2019
2020
2039

Development summary

High-level architecture of the application

Model summary

Training RMSE: 0.0307 Validation RMSE: 0.2005 
                Model: "sequential_11"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 lstm_17 (LSTM)              (None, 64)                16896     
                                                                 
 dense_34 (Dense)            (None, 32)                2080      
                                                                 
 dense_35 (Dense)            (None, 32)                1056      
                                                                 
 dense_36 (Dense)            (None, 32)                1056      
                                                                 
 dense_37 (Dense)            (None, 1)                 33        
                                                                 
=================================================================
Total params: 21121 (82.50 KB)
Trainable params: 21121 (82.50 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________