Detecting hydrological droughts in ungauged areas from remotely sensed hydro-meteorological variables using rule-based m
- PDF / 4,323,695 Bytes
- 28 Pages / 439.37 x 666.142 pts Page_size
- 109 Downloads / 233 Views
Detecting hydrological droughts in ungauged areas from remotely sensed hydro‑meteorological variables using rule‑based models Jinyoung Rhee1 · Kyungwon Park1 · Seongkyu Lee1 · Sangmin Jang1 · Sunkwon Yoon2 Received: 12 February 2020 / Accepted: 10 June 2020 © Springer Nature B.V. 2020
Abstract As a method of detecting hydrological droughts in ungauged areas, we propose rule-based models using percentiles from remotely sensed key hydro-meteorological variables. Four rule-based models of the Decision Trees, Adaptive Boosting of Decision Trees (Adaboost), Random Forest, and Extremely Randomized Trees are used for their capabilities of modeling nonlinear relationships, and their results are compared to the multiple linear regression. The temporal information of month and the percentiles of key variables of water and energy balance including precipitation, actual evapotranspiration, Normalized Difference Vegetation Index (NDVI), land surface temperature, and soil moisture are used as input variables. Drought severity values are calculated from streamflow percentiles for 3-, 6-, 9-, and 12-month time scales as an indicator for hydrological droughts. Data from six basins of the case study area are used for tuning model parameters and training, and the remaining two basins are used for final evaluation. Models with an ensemble of trees successfully detect hydrological droughts despite the limited input variables (for Adaboost, correlation coefficients ≥ 0.85, mean absolute error ≤ 0.12, root-mean-square error–observations standard deviation ratio ≤ 0.53, and larger Nash–Sutcliffe efficiency of drought severity ≥ 0.72 for the test data set). The most important variable is precipitation, followed by soil moisture (3-month time scale) or NDVI (longer time scales). Hydrological droughts in various time scales are detected in ungauged areas of the case study area. Serious droughts in early 2002, from late 2006 to mid-2007, from early 2008 to 2009, and from mid-2013 to 2017 are detected. Keywords Hydrological droughts · Rule-based models · Remote sensing · Ungauged areas
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s1106 9-020-04114-5) contains supplementary material, which is available to authorized users. * Jinyoung Rhee [email protected] 1
Climate Services and Research Department, APEC Climate Center, Busan, Republic of Korea
2
Department of Safety and Disaster Prevention Research, Seoul Institute of Technology, Seoul, Republic of Korea
13
Vol.:(0123456789)
Natural Hazards
Abbreviations 7Q10 The annual minimum 7-day mean streamflow with an annual exceedance probability of 90% ANNs Artificial neural networks BoM Bureau of meteorology CCA Canonical correlation analysis EANN Ensemble of ANNs ELM Extreme learning machine EMI El Nino-Southern Oscillation Modoki Index Full-tobit Type I tobit regression GAM Gaussian generalized additive model GBM Gradient boosting machine GEFS NOAA global ensemble forecasting system GEP Gene expression programming GL
Data Loading...
