Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments: an Example of the Chindwin River in Myanmar

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments: an Example of the Chindwin River in Myanmar. / Latt, Zaw Zaw ; Wittenberg, Hartmut; Urban, Brigitte.
In: Water Resources Management, Vol. 29, No. 3, 01.02.2015, p. 913-928.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{607c664db6e74672a26f7e64cd0a0ec7,
title = "Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments: an Example of the Chindwin River in Myanmar",
abstract = "A neural network-based regionalization approach using catchment descriptors was proposed for flood management of ungauged catchments in a developing country with low density of the hydrometric network. Through the example of the Chindwin River basin in Myanmar, the study presents the application of principal components and clustering techniques for detecting hydrological homogeneous regions, and the artificial neural network (ANN) approach for regional index flood estimation. Based on catchment physiographic and climatic attributes, the principal component analysis yields three component solutions with 79.2 % cumulative variance. The Ward's method was used to search initial cluster numbers prior to k-means clustering, which then objectively classifies the entire catchment into four homogeneous groups. For each homogeneous region clustered by the leading principal components, the regional index flood models are developed via the ANN and regression methods based on the longest flow path, basin elevation, basin slope, soil conservation curve number and mean annual rainfall. The ANN approach captures the nonlinear relationships between the index floods and the catchment descriptors for each cluster, showing its superiority towards the conventional regression method. The results would contribute to national water resources planning and management in Myanmar as well as in other similar regions.",
keywords = "Environmental planning, Artificial neural network, Index flood estimation, Multivariate clustering, Physiographic parameter, Principal component, Ungauged catchment",
author = "Latt, {Zaw Zaw} and Hartmut Wittenberg and Brigitte Urban",
year = "2015",
month = feb,
day = "1",
doi = "10.1007/s11269-014-0851-4",
language = "English",
volume = "29",
pages = "913--928",
journal = "Water Resources Management",
issn = "0920-4741",
publisher = "Springer Science and Business Media B.V.",
number = "3",

}

RIS

TY - JOUR

T1 - Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments

T2 - an Example of the Chindwin River in Myanmar

AU - Latt, Zaw Zaw

AU - Wittenberg, Hartmut

AU - Urban, Brigitte

PY - 2015/2/1

Y1 - 2015/2/1

N2 - A neural network-based regionalization approach using catchment descriptors was proposed for flood management of ungauged catchments in a developing country with low density of the hydrometric network. Through the example of the Chindwin River basin in Myanmar, the study presents the application of principal components and clustering techniques for detecting hydrological homogeneous regions, and the artificial neural network (ANN) approach for regional index flood estimation. Based on catchment physiographic and climatic attributes, the principal component analysis yields three component solutions with 79.2 % cumulative variance. The Ward's method was used to search initial cluster numbers prior to k-means clustering, which then objectively classifies the entire catchment into four homogeneous groups. For each homogeneous region clustered by the leading principal components, the regional index flood models are developed via the ANN and regression methods based on the longest flow path, basin elevation, basin slope, soil conservation curve number and mean annual rainfall. The ANN approach captures the nonlinear relationships between the index floods and the catchment descriptors for each cluster, showing its superiority towards the conventional regression method. The results would contribute to national water resources planning and management in Myanmar as well as in other similar regions.

AB - A neural network-based regionalization approach using catchment descriptors was proposed for flood management of ungauged catchments in a developing country with low density of the hydrometric network. Through the example of the Chindwin River basin in Myanmar, the study presents the application of principal components and clustering techniques for detecting hydrological homogeneous regions, and the artificial neural network (ANN) approach for regional index flood estimation. Based on catchment physiographic and climatic attributes, the principal component analysis yields three component solutions with 79.2 % cumulative variance. The Ward's method was used to search initial cluster numbers prior to k-means clustering, which then objectively classifies the entire catchment into four homogeneous groups. For each homogeneous region clustered by the leading principal components, the regional index flood models are developed via the ANN and regression methods based on the longest flow path, basin elevation, basin slope, soil conservation curve number and mean annual rainfall. The ANN approach captures the nonlinear relationships between the index floods and the catchment descriptors for each cluster, showing its superiority towards the conventional regression method. The results would contribute to national water resources planning and management in Myanmar as well as in other similar regions.

KW - Environmental planning

KW - Artificial neural network

KW - Index flood estimation

KW - Multivariate clustering

KW - Physiographic parameter

KW - Principal component

KW - Ungauged catchment

UR - http://www.scopus.com/inward/record.url?scp=84925519936&partnerID=8YFLogxK

U2 - 10.1007/s11269-014-0851-4

DO - 10.1007/s11269-014-0851-4

M3 - Journal articles

VL - 29

SP - 913

EP - 928

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 3

ER -

Recently viewed

Publications

  1. Selecting and Adapting Methods for Analysis and Design in Value-Sensitive Digital Social Innovation Projects: Toward Design Principles
  2. Invariant subspaces for grasping internal forces and non-interacting force-motion control in robotic manipulation
  3. Classical PI Controllers with Anti-Windup Techniques Applied on Level Systems
  4. Lagged Multidimensional Recurrence Quantification Analysis for Determining Leader–Follower Relationships Within Multidimensional Time Series
  5. Effective informational entropy reduction in multi-robot systems based on real-time TVS
  6. Positioning Improvement for a Laser Scanning System using cSORPD control
  7. Improved sensorimotor control is not connected with improved proprioception
  8. Machine Learning and Knowledge Discovery in Databases
  9. Competing Vegetation Structure Indices for Estimating Spatial Constrains in Carabid Abundance Patterns in Chinese Grasslands Reveal Complex Scale and Habitat Patterns
  10. Advances in Dynamics, Optimization and Computation
  11. Does thinking-aloud affect learning, visual information processing and cognitive load when learning with seductive details as expected from self-regulation perspective?
  12. Cognitive load and instructionally supported learning with provided and learner-generated visualizations
  13. Resource extraction technologies - is a more responsible path of development possible?
  14. Using augmented video to test in-car user experiences of context analog HUDs
  15. Robust Control of Mobile Transportation Object with 3D Technical Vision System
  16. How Much Home Office is Ideal? A Multi-Perspective Algorithm
  17. Efficient Order Picking Methods in Robotic Mobile Fulfillment Systems
  18. Guided discovery learning with computer-based simulation games
  19. Probabilistic approach to modelling of recession curves
  20. Eighth Workshop on Mining and Learning with Graphs
  21. Mostly harmless econometrics? Statistical paradigms in the ‘top five’ from 2000 to 2018
  22. Learning and Re-learning from net- based cooperative learning discourses
  23. Using Heider’s Epistemology of Thing and Medium for Unpacking the Conception of Documents: Gantt Charts and Boundary Objects
  24. Topic Embeddings – A New Approach to Classify Very Short Documents Based on Predefined Topics
  25. Transfer operator-based extraction of coherent features on surfaces
  26. Optimising business performance with standard software systems
  27. Reality-Based Tasks with Complex-Situations
  28. On the Difficulty of Forgetting
  29. An experience-based learning framework
  30. Soft Skills for Hard Constraints
  31. Should learners use their hands for learning? Results from an eye-tracking study
  32. Influence of Process Parameters and Die Design on the Microstructure and Texture Development of Direct Extruded Magnesium Flat Products