Intelligent data analytics for time series, trend analysis and drought indices comparison
Edited book (chapter)
Chapter Title | Intelligent data analytics for time series, trend analysis and drought indices comparison |
---|---|
Book Chapter Category | Edited book (chapter) |
ERA Publisher ID | 3337 |
Book Title | Intelligent data analytics for decision-support systems in hazard mitigation: theory and practice of hazard mitigation |
Authors | Dayal, Kavina S. (Author), Deo, Ravinesh C. (Author) and Apan, Armando A. (Author) |
Editors | Deo, Ravinesh C., Samui, Pijush, Kisi, Ozgur and Yaseen, Zaher Mundher |
Page Range | 151-169 |
Series | Springer Transactions in Civil and Environmental Engineering |
Chapter Number | 8 |
Number of Pages | 19 |
Year | 2021 |
Publisher | Springer |
Place of Publication | Singapore |
ISBN | 9789811557712 |
9789811557729 | |
ISSN | 2363-7633 |
2363-7641 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-981-15-5772-9_8 |
Web Address (URL) | https://link.springer.com/chapter/10.1007/978-981-15-5772-9_8 |
Abstract | This chapter develops intelligent data analytics approaches to compare the frequently used drought-monitoring indices and applies the change-point analysis technique to detect subtle changes in the drought index trends for natural hazard and disaster risk mitigation. The Standardised Precipitation-Evapotranspiration Index (SPEI), used in this chapter, is able to identify extreme drought events better than the Standardised Precipitation Index (SPI). SPEI highly correlates with Precipitation-based Drought Indices (DIs), especially with SPI and Rainfall Decile-based Drought Index (RDDI) but can additionally provide complementary information about hydrological effects of drought. Illustrated by the wavelet analysis, the SPEI concurs with all major drought events largely, significant at 95% confidence interval, compared to SPI, RDDI and Rainfall Anomaly Index (RAI). The change-point analysis is able to detect changes in the SPEI trend with associated confidence levels and confidence intervals. The study found the location R4 (in arid/semi-arid region) to have undergone 26 changes in SPEI trend compared to R1, R2 and R3 with 0, 9 and 6, respectively. The location of study matters where inland from the coastline experiences more variability in the environmental parameters that define the SPEI. The methods proposed this chapter can be useful for disaster risk mitigation, particularly, quantifying drought events for decision-making processes. |
Keywords | intelligent data analytics; drought monitoring indices; drought index trends; Standardised Precipitation-Evapotranspiration Index |
ANZSRC Field of Research 2020 | 410402. Environmental assessment and monitoring |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia |
School of Sciences | |
School of Civil Engineering and Surveying | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q5wqw/intelligent-data-analytics-for-time-series-trend-analysis-and-drought-indices-comparison
213
total views9
total downloads5
views this month0
downloads this month