Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model

Deo, Ravinesh C. and Kisi, Ogzur and Singh, Vijay P. (2017) Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model. Atmospheric Research, 184. pp. 149-175. ISSN 0169-8095

[img]
Preview
Text (Accepted Version)
Deo_Kisi_Singh_AV.pdf

Download (1722Kb) | Preview

Abstract

Drought forecasting using standardized metrics of rainfall is a core task in hydrology and water resources management. Standardized Precipitation Index (SPI) is a rainfall-based metric that caters for different time-scales at which the drought occurs, and due to its standardization, is well-suited for forecasting drought at different periods in climatically diverse region. This study advances drought modelling using multivariate adaptive regression splines (MARS), least square support vector machine (LSSVM), and M5Tree models by forecasting SPI in eastern Australia. MARS model incorporated rainfall as mandatory predictor with month (periodicity), Southern Oscillation Index, Pacific Decadal Oscillation Index and Indian Ocean Dipole, ENSO Modoki and Nino 3.0, 3.4 and 4.0 data added gradually. The performance was evaluated with root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (r2). Best MARS model required different input combinations, where rainfall, sea surface temperature and periodicity were used for all stations, but ENSO Modoki and Pacific Decadal Oscillation indices were not required for Bathurst, Collarenebri and Yamba, and the Southern Oscillation Index was not required for Collarenebri. Inclusion of periodicity increased the r2 value by 0.5–8.1% and reduced RMSE by 3.0–178.5%. Comparisons showed that MARS superseded the performance of the other counterparts for three out of five stations with lower MAE by 15.0–73.9% and 7.3–42.2%, respectively. For the other stations, M5Tree was better than MARS/LSSVM with lower MAE by 13.8–13.4% and 25.7–52.2%, respectively, and for Bathurst, LSSVM yielded more accurate result. For droughts identified by SPI ≤ − 0.5, accurate forecasts were attained by MARS/M5Tree for Bathurst, Yamba and Peak Hill, whereas for Collarenebri and Barraba, M5Tree was better than LSSVM/MARS. Seasonal analysis revealed disparate results where MARS/M5Tree was better than LSSVM. The results highlight the importance of periodicity in drought forecasting and also ascertains that model accuracy scales with geographic/seasonal factors due to complexity of drought and its relationship with inputs and data attributes that can affect the evolution of drought events.


Statistics for USQ ePrint 29858
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Accepted version deposited in accordance with the copyright policy of the publisher. Dr RC Deo was supported by Academic Division Researcher Activation Incentive Scheme (RAIS; July– September 2015) grant and Australian Government Endeavor Executive Fellowship (2015).
Faculty / Department / School: Current - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences
Date Deposited: 18 Oct 2016 00:25
Last Modified: 01 Feb 2018 02:17
Uncontrolled Keywords: standardized precipitation index; drought forecasting; multivariate adaptive regression spline; least square support vector machine; M5Tree model
Fields of Research : 04 Earth Sciences > 0401 Atmospheric Sciences > 040104 Climate Change Processes
05 Environmental Sciences > 0502 Environmental Science and Management > 050204 Environmental Impact Assessment
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
04 Earth Sciences > 0406 Physical Geography and Environmental Geoscience > 040607 Surface Processes
05 Environmental Sciences > 0502 Environmental Science and Management > 050206 Environmental Monitoring
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080110 Simulation and Modelling
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation
01 Mathematical Sciences > 0102 Applied Mathematics > 010207 Theoretical and Applied Mechanics
09 Engineering > 0905 Civil Engineering > 090509 Water Resources Engineering
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970105 Expanding Knowledge in the Environmental Sciences
D Environment > 96 Environment > 9610 Natural Hazards > 961099 Natural Hazards not elsewhere classified
D Environment > 96 Environment > 9602 Atmosphere and Weather > 960202 Atmospheric Processes and Dynamics
D Environment > 96 Environment > 9603 Climate and Climate Change > 960303 Climate Change Models
D Environment > 96 Environment > 9602 Atmosphere and Weather > 960203 Weather
Funding Details:
Identification Number or DOI: 10.1016/j.atmosres.2016.10.004
URI: http://eprints.usq.edu.au/id/eprint/29858

Actions (login required)

View Item Archive Repository Staff Only