Exploring spatiotemporal meteorological correlations for basin scale meteorological drought forecasting using data minin
- PDF / 1,930,524 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 0 Downloads / 225 Views
ORIGINAL PAPER
Exploring spatiotemporal meteorological correlations for basin scale meteorological drought forecasting using data mining methods Banafsheh Zahraie 1 & Mohsen Nasseri 1 & Fariborz Nematizadeh 2
Received: 3 February 2017 / Accepted: 20 September 2017 # Saudi Society for Geosciences 2017
Abstract In this paper, two data mining methods, support vector machine (SVM) and group method of data handling (GMDH), were used to identify spatiotemporal meteorological correlations, which can be used to forecast basin scale seasonal droughts. Standardized Precipitation Index (SPI) was used as a meteorological drought severity index. The case study of this paper consists of the basins of four major dams in Iran that supply domestic water demands of Tehran, the capital city of Iran. A GMDH and an SVM model optimized by particle swarm optimization (PSO) were used to predict seasonal SPIs in the fall, winter, spring, and some combined seasons. The historical time series of the meteorological variables including air temperature and geopotential height at the surface, and 300, 500, 700, and 850 mbar levels in the geographical zone covering 10 to 60° north latitudes and 0 to 90° east longitudes were selected as the model predictors. Average mutual information (AMI) index was used for feature selection among the mentioned predictors. The selected predictors in the months of April to August were used as the SVM and GMDH inputs. The results showed that the seasonal SPI values could be forecasted by the proposed model with 2- to 5-month lead-time with enough accuracy. Hence, the
* Mohsen Nasseri [email protected] Banafsheh Zahraie [email protected] Fariborz Nematizadeh [email protected] 1
School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran
2
Water Institute, University of Tehran, Tehran, Iran
proposed method can be used in mid-term water resource management in the study area. Keywords Meteorological drought forecasting . Standardized precipitation index (SPI) . Support vector machine (SVM) . Group method of data handling (GMDH) . Particle swarm optimization (PSO) . Average mutual information (AMI)
Introduction The climate of the Middle East and North African (MENA) region is mostly characterized by frequent and severe drought events. Predicting dry spells and their severities play an important role in water resource management in this region. This topic has brought into focus the need for improving the accuracy of the techniques for predicting droughts. Spatiotemporal climatological correlation analysis and numerical simulation are known as suitable methods for meteorological drought prediction. Researchers focusing on correlation analysis have tried to identify spatial patterns of climate variability in geographical zones highly affected by some of the well-known teleconnection structures such as El Niño-Southern Oscillation (ENSO) and PacificNorth American teleconnection (Oguntoyinbo 1986). While these patterns tend to reappear occasionally, less work has been done to identif
Data Loading...
