Atjaunināt sīkdatņu piekrišanu

E-grāmata: Hydrological Data Driven Modelling: A Case Study Approach

,
  • Formāts: PDF+DRM
  • Sērija : Earth Systems Data and Models 1
  • Izdošanas datums: 03-Nov-2014
  • Izdevniecība: Springer International Publishing AG
  • Valoda: eng
  • ISBN-13: 9783319092355
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 100,53 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Hydrological Data Driven Modelling: A Case Study ApproachPalielināt
  • Formāts: PDF+DRM
  • Sērija : Earth Systems Data and Models 1
  • Izdošanas datums: 03-Nov-2014
  • Izdevniecība: Springer International Publishing AG
  • Valoda: eng
  • ISBN-13: 9783319092355
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This book explores a new realm in data-based modeling with applications to hydrology. Pursuing a case study approach, it presents a rigorous evaluation of state-of-the-art input selection methods on the basis of detailed and comprehensive experimentation and comparative studies that employ emerging hybrid techniques for modeling and analysis. Advanced computing offers a range of new options for hydrologic modeling with the help of mathematical and data-based approaches like wavelets, neural networks, fuzzy logic, and support vector machines. Recently machine learning/artificial intelligence techniques have come to be used for time series modeling. However, though initial studies have shown this approach to be effective, there are still concerns about their accuracy and ability to make predictions on a selected input space.

1 Introduction
1(18)
1.1 Modelling in Hydrology
3(2)
1.1.1 Model Classification
4(1)
1.2 Stochastic Modelling Case Studies in This Book
5(5)
1.2.1 Data Driven Rainfall-Runoff Modelling
5(2)
1.2.2 Data Driven Solar Radiation Modelling
7(1)
1.2.3 Data Driven Evapotranspiration Modelling
8(2)
1.3 Why Do You Read This Book?
10(9)
References
13(6)
2 Hydroinformatics and Data-Based Modelling Issues in Hydrology
19(22)
2.1 Hydroinformatics
20(1)
2.2 Why Overfitting and How to Avoid
21(3)
2.3 Input Variable (Data) Selection
24(2)
2.4 Redundancy in Input Data and Model
26(3)
2.5 Data-Based Modeling---Complexity, Uncertainty, and Sensitivity
29(6)
2.5.1 Modeling Uncertainty
30(1)
2.5.2 Model Complexity
31(1)
2.5.3 Training Data Requirements
32(1)
2.5.4 Flexibility for a Model
33(1)
2.5.5 Sensitivity of a Model
34(1)
2.5.6 Predictive Error of a Model
34(1)
2.5.7 Identifiability of a Model
34(1)
2.6 Index of Model Utility (U)
35(1)
2.7 Conclusions
36(5)
References
36(5)
3 Model Data Selection and Data Pre-processing Approaches
41(30)
3.1 Implementation of Gamma Test
41(5)
3.1.1 Background on Gamma Statistic, V-Ratio, and M-Test
42(2)
3.1.2 Assumptions in the Gamma Test
44(1)
3.1.3 Data Analysis Using Gamma Test
44(2)
3.1.4 Delta Test
46(1)
3.2 Implementation of Entropy Theory
46(6)
3.2.1 Multidimensional Extensions of Entropy Theory
49(2)
3.2.2 Application of Entropy Theory
51(1)
3.3 Implementation of AIC and BIC
52(2)
3.4 Implementation of Cluster Analysis
54(7)
3.4.1 Hierarchical Tree Cluster Analysis
55(4)
3.4.2 Partition Clustering (K-Means Clustering)
59(2)
3.5 Implementation of Principal Component Analysis
61(2)
3.6 Traditional Approaches in Data and Model Selection
63(4)
3.6.1 The Holdout Method
63(1)
3.6.2 Random Sub-sampling
64(1)
3.6.3 K-Fold Cross-Validation
65(1)
3.6.4 Leave-One-Out Cross-Validation
66(1)
3.6.5 Cross-Correlation Method
66(1)
3.7 Conclusions
67(4)
References
67(4)
4 Machine Learning and Artificial Intelligence-Based Approaches
71(40)
4.1 Transfer Function Models
73(4)
4.1.1 Autoregressive Model
74(1)
4.1.2 Moving Average Model
74(1)
4.1.3 Autoregressive Moving Average Model: ARMA (P, Q)
74(1)
4.1.4 Autoregressive Moving Integrated Average Model: ARIMA (P, Q)
75(1)
4.1.5 AutoRegressive with exogenous Input (ARX) Model
75(1)
4.1.6 AutoRegressive Moving Average with Exogenous Input (ARMAX) Model
76(1)
4.2 Local Linear Regression Model
77(1)
4.3 Artificial Neural Networks Model
78(7)
4.3.1 Feed-Forward Neural Network Architecture
79(2)
4.3.2 Recurrent Artificial Neural Networks
81(1)
4.3.3 Elman Artificial Neural Networks
81(1)
4.3.4 Jordan Artificial Neural Networks
82(1)
4.3.5 Hopfield Networks
82(2)
4.3.6 Long Short Term Memory Networks
84(1)
4.4 Training Algorithms
85(4)
4.4.1 Conjugate Gradient Algorithm
86(1)
4.4.2 Broyden--Fletcher--Goldfarb--Shanno Algorithm
87(1)
4.4.3 Levenberg--Marquardt Algorithms
88(1)
4.5 Discrete Wavelet Transforms
89(4)
4.6 Hybrid Models
93(18)
4.6.1 Neural Network Autoregressive with Exogenous Inputs (NNARX) Model
94(1)
4.6.2 Fuzzy Inference System
94(2)
4.6.3 Adaptive Neuro-Fuzzy Inference System (ANFIS) Model
96(2)
4.6.4 Support Vector Machines
98(5)
4.6.5 Neuro-Wavelet Model
103(1)
4.6.6 Wavelet-ANFIS Model (W-ANFIS)
104(1)
4.6.7 Wavelet-Support Vector Machines (W-SVM) Model
104(1)
References
105(6)
5 Data Based Solar Radiation Modelling
111(40)
5.1 Introduction
111(4)
5.1.1 The River Brue Catchment
112(1)
5.1.2 Data from the Hydrological Radar Experiment (HYREX) Project
113(2)
5.1.3 Details of River Brue Catchment Data
115(1)
5.2 Statistical Indices for Data Based Model Comparison
115(2)
5.3 Data Based Six-Hourly Solar Radiation Modelling
117(9)
5.3.1 Input Data and Training Data Length Selection Using Entropy Theory
117(3)
5.3.2 Data Selection Results from the Gamma Test
120(2)
5.3.3 Data Selection Results from the AIC and BIC
122(1)
5.3.4 Modelling Results Using ANN and LLR on 6-Hourly Records
123(3)
5.4 Data Based Daily Solar Radiation on Beas Database
126(18)
5.4.1 Data Analysis and Model Input Selection Based on the Gamma Test
127(2)
5.4.2 Non-linear Model Construction and Testing Results
129(15)
5.5 Model Selection in Daily Solar Radiation Estimation in Terms of Overall Model Utility
144(3)
5.6 Discussions and Conclusions
147(4)
References
149(2)
6 Data Based Rainfall-Runoff Modelling
151(32)
6.1 Introduction
151(1)
6.2 Study Area: Brue Catchment
152(1)
6.3 Statistical Indices for Comparison
153(1)
6.4 Data Selection Approaches in Data Based Rainfall-Runoff Modelling
154(10)
6.4.1 Gamma Test for Data Length Selection and Input Identification
155(2)
6.4.2 Entropy Theory for Data Length Selection and Input Identification
157(3)
6.4.3 Data Length Selection and Input Identification with Traditional Approaches
160(2)
6.4.4 Model Data Selection Using AIC and BIC for Daily Rainfall Runoff Modelling
162(2)
6.5 Data Based Rainfall: Runoff Modelling
164(16)
6.5.1 Modelling with ARX, ARMAX and ANN
164(3)
6.5.2 Influence of Data Interval on Data Based Real Time Flood Forecasting
167(3)
6.5.3 Data Driven Modelling with LLR, NNARX and ANFIS
170(3)
6.5.4 Data Driven Rainfall-Runoff Modelling with Neuro-Wavelet (NW) Model
173(1)
6.5.5 Rainfall-Runoff Modelling with SVM, W-ANFIS and W-SVM Models
174(6)
6.6 Conclusions
180(3)
References
181(2)
7 Data-Based Evapotranspiration Modeling
183(48)
7.1 Introduction
183(1)
7.2 Study Area
184(5)
7.2.1 Santa Monica CIMIS Station
184(1)
7.2.2 Brue Catchment, United Kingdom
185(2)
7.2.3 The Sistan Region, Iran
187(2)
7.3 Statistical Indices for Model Comparison
189(1)
7.4 Modelling with Traditional Reference Evapotranspiration Models
190(17)
7.4.1 Mathematical Details of the ET0 Models
190(4)
7.4.2 Model Performance Analysis Relative to FAO56-PM
194(13)
7.5 Data-Based Evaporation Modeling: Data Selection Approaches
207(9)
7.5.1 Gamma Test for Input Selection in Evaporation Modeling
207(4)
7.5.2 Entropy Theory for Data Analysis in Evaporation Modeling
211(2)
7.5.3 AIC and BIC for Data Analysis in Evaporation Modeling
213(2)
7.5.4 Data Analysis in Evaporation Modeling with Data Splitting and Cross Correlation Approaches
215(1)
7.6 Data-Based Modeling in Evaporation Modeling
216(8)
7.6.1 Data-Based Evaporation Modeling with LLR, ANNs, ANFIS, and SVMs
216(5)
7.6.2 Evaporation Modeling with Hybrid Models NNARX, NW, W-ANFIS, and W-SVM
221(3)
7.7 Evaporation Data Model Selection in Terms of Overall Model Utility
224(3)
7.8 Discussions and Conclusions
227(4)
References
229(2)
8 Application of Statistical Blockade in Hydrology
231(18)
8.1 Introduction: Statistical Blockade
231(3)
8.2 Statistical Blockade Steps
234(4)
8.3 Case Study in Hydrology
238(8)
8.3.1 Study Area
238(1)
8.3.2 Application of Statistical Blockade
238(3)
8.3.3 Application of Artificial Neural Network
241(3)
8.3.4 Application of Support Vector Machines
244(2)
8.4 Conclusions
246(3)
References
246(3)
Index 249
Dr Renji Remesan is a research fellow in Cranfield Water Science Institute at Cranfield University in United Kingdom. Dr Remesans research interests include non-linear modelling of hydro-metrological time series, artificial intelligence in hydrology, numerical weather modelling and river basin/catchment modelling using physically/ conceptual lumped models and distributed hydrological models. He is an Associate Fellow of the UK Higher Education Academy and editorial member of the Journal of Earth science and Climate change. He holds a PhD from the University of Bristol and an M.Tech from the Indian Institute of Technology, Kharagpur.

Dr Jimson Mathew received a PhD in Computer Science from University of Bristol, UK. He has held positions with the Centre for Wireless Communications, National University of Singapore, Bell Laboratories Research (Lucent Technologies) North Ryde, Australia and Royal Institute of Technology (KTH), Stockholm, Sweden.  Since 2005, he has been with the Department of Computer Science, University of Bristol, UK. His research interest primarily focuses on Fault-tolerant Computing.
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97833190923552e.html
Keywords: