Deep Learning for Hydrometeorology and Environmental Science

Chapter 1            Introduction

1.1          What is  deep learning?

1.2          Pros and cons of deep learning

1.3          Recent applications of deep learning in hydrometeorological and environmental studies

1.4          Organization of chapters

1.5          Summary and conclusion

Chapter 2            Mathematical Background

2.1          Linear regression model

2.2          Time series model

2.3          Probability distributions

Chapter 3            Data Preprocessing

3.1          Normalization

3.2          Data splitting for training and testing

Chapter 4            Neural Network

4.1          Terminology in neural network

4.2          Artificial neural network

Chapter 5            . Training a Neural Network

5.1          Initialization

5.2          Gradient descent

5.3          Backpropagation

Chapter 6            . Updating Weights

6.1          Momentum

6.2          Adagrad

6.3          RMSprop

6.4          Adam

6.5          Nadam

6.6          Python coding of updating weights

Chapter 7            . Improving model performance

7.1          Batching and minibatch

7.2          Validation

7.3          Regularization

Chapter 8            Advanced Neural Network Algorithms

8.1          Extreme Learning Machine (ELM)

8.2          Autoencoding

Chapter 9            Deep learning for time series

9.1          Recurrent neural network

9.2          Long Short-Term Memory (LSTM)

9.3          Gated Recurrent Unit (GRU)

Chapter 10          Deep learning for spatial datasets

10.1        Convolutional Neural Network (CNN)

10.2        Backpropagation of CNN

Chapter 11          Tensorflow and Keras Programming for Deep Learning

11.1        Ba