This project predicts weather (i.e., min-max temperature) from historical data. The dataset includes hourly inputs of pressure, humidity, temperature, wind speed, and wind direction of 36 cities from the year 2012 to 2017. From the dataset preprocessing is done to engineer attributes to predict min and max temperature of Toronto. Data from 2012-2016 is used as the training dataset, while the attempt is to predict the min and max temp of 2017.

• Tensorflow 2.0 is used.
• Bidirectional LSTM is used to train the model.
• Performance for the maximum temperature prediction is R2: 0.78, MAE:0.21, MSE: 0.07 and for the minimum temperature prediction is R2:0.74, MAE: 0.22, MSE: 0.08.

This Project’s GitHub Repository

• Regression
• RNN