Książki

This book provides a step-by-step methodology and derivation of deep learning algorithms as Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN), especially for estimating parameters, with back-propagation as well as examples with real datasets of hydrometeorology (e.g. streamflow and temperature) and environmental science (e.g. water quality).

Deep learning is known as part of machine learning methodology based on the artificial neural network. Increasing data availability and computing power enhance applications of deep learning to hydrometeorological and environmental fields. However, books that specifically focus on applications to these fields are limited.

Most of deep learning books demonstrate theoretical backgrounds and mathematics. However, examples with real data and step-by-step explanations to understand the algorithms in hydrometeorology and environmental science are very rare.

This book focuses on the explanation of deep learning techniques and their applications to hydrometeorological and environmental studies with real hydrological and environmental data. This book covers the major deep learning algorithms as Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN) as well as the conventional artificial neural network model.

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)

Chapter 11          Tensorflow and Keras Programming for Deep Learning

11.1        Basic Keras modeling

11.2        Temporal deep learning (LSTM and GRU)

11.3        Spatial deep learning (CNN)

Chapter 12          Hydrometeorological Applications of deep learning

12.1        Stochastic simulation with LSTM

12.2        Forecasting daily temperature with LSTM

Chapter 13          Environmental Applications of deep learning

13.1        Remote sensing of water quality using CNN