Improving Flood Forecasting in a Developing Country: A Comparative Study of Stepwise Multiple Linear Regression and Artificial Neural Network

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Authors

Due to limited data sources, practical situations in most developing countries favor black-box models in real time operations. In a simple and robust approach, this study examines performances of stepwise multiple linear regression (SMLR) and artificial neural network (ANN) models, as tools for multi-step forecasting Chindwin River floods in northern Myanmar. Future river stages are modeled using past water levels and rainfall at the forecasting station as well as at the hydrologically connected upstream station. The developed models are calibrated with flood season data from 1990 to 2007 and validated with data from 2008 to 2011. Model performances are compared for 1- to 5-day ahead forecasts. With a high accuracy, both candidate models performed well for forecasting the full range of flood levels. The ANN models were superior to the SMLR models, particularly in predicting the extreme floods. Correlation analysis was found to be useful for determining the initial input variables. Contribution of upstream data to both models could improve the forecasting performance with higher R 2 values and lower errors. Considering the commonly available data in the region as primary predictors, the results would be useful for real time flood forecasting, avoiding the complexity of physical processes.

OriginalspracheEnglisch
ZeitschriftWater Resources Management
Jahrgang28
Ausgabenummer8
Seiten (von - bis)2109-2128
Anzahl der Seiten20
ISSN0920-4741
DOIs
PublikationsstatusErschienen - 06.2014

DOI

Zuletzt angesehen

Publikationen

  1. Wohin blicken Lehramtsstudierende beim Unterrichten?
  2. Elastomeric Prepregs for Soft Robotics Applications
  3. Toward the Next Generation of Air Quality Monitoring
  4. The economics of biodiversity and ecosystem services
  5. In situ tensile texture analysis of a new Mg-RE alloy
  6. Processability of Mg-Gd Powder via Friction Extrusion
  7. Erklärung der individuellen Existenzgründungsabsicht
  8. Die Aufgabenfülle der Grundschule und ihrer Pädagogik
  9. On the utility of indirect methods for detecting faking
  10. Avoiding Algorithm Error in Computer-Aided Text Analyses
  11. Risk preferences under heterogeneous environmental risk
  12. Begabungsdiagnostik mit dem Grundintelligenztest (CFT 20-R)
  13. Homogenization modeling of thin-layer-type microstructures
  14. A Kalman estimator for detecting repetitive disturbances
  15. The liquidity regulation and savings banks' liquid assets
  16. Proxy Indicators for the Quality of Open-domain Dialogues
  17. Communities of ground-living spiders in deciduous forests
  18. Freistellung von Betriebsräten - eine Beschäftigungsbremse?
  19. Influence of cerium on stress corrosion cracking in AZ91D
  20. The German Bank Restructuring Act: An Economic Perspective
  21. Dynamic Lot Size Optimization with Reinforcement Learning
  22. Using Complexity Metrics to Assess Silent Reading Fluency
  23. School Leader Trust and Collective Teacher Innovativeness
  24. Meta-analytic cointegrating rank tests for dependent panels
  25. Einflüsse der Land- und Wassernutzung auf das Niedrigwasser
  26. Productivity premia for many modes of internationalization.
  27. Study on Mg–Si–Sr ternary alloys for biomedical applications
  28. Corrosion behaviour of electropolished magnesium materials
  29. Das Individuum und die Peers - eine strukturelle Perspektive
  30. Perfect anti-windup in output tracking scheme with preaction
  31. Dynamics of Supply Chains Under Mixed Production Strategies
  32. The Cox ring of the space of complete rank two collineations
  33. Does more respect from leaders postpone the desire to retire?
  34. Propagation of particles injected from interplanetary shocks
  35. Does Internet-based guided self-help for depression cause harm?
  36. Gesellschaftliche Naturverhältnisse zwischen Krise und Vision
  37. Wo lernen Kinder mit sonderpädagogischem Förderbedarf besser?
  38. Product diversification and stability of employment and sales
  39. Do learner characteristics moderate the seductive-details-effect?