Determination and prediction of standardized precipitation index (SPI) using TRMM data in arid ecosystems
- 141 Downloads
Drought over a period threatens the water resources, agriculture, and socioeconomic activities. Therefore, it is crucial for decision makers to have a realistic anticipation of drought events to mitigate its impacts. Hence, this research aims at using the standardized precipitation index (SPI) to predict drought through time series analysis techniques. These adopted techniques are autoregressive integrating moving average (ARIMA) and feed-forward backpropagation neural network (FBNN) with different activation functions (sigmoid, bipolar sigmoid, and hyperbolic tangent). After that, the adequacy of these two techniques in predicting the drought conditions has been examined under arid ecosystems. The monthly precipitation data used in calculating the SPI time series (SPI 3, 6, 12, and 24 timescales) have been obtained from the tropical rainfall measuring mission (TRMM). The prediction of SPI was carried out and compared over six lead times from 1 to 6 using the model performance statistics (coefficient of correlation (R), mean absolute error (MAE), and root mean square error (RMSE)). The overall results prove an excellent performance of both predicting models for anticipating the drought conditions concerning model accuracy measures. Despite this, the FBNN models remain somewhat better than ARIMA models with R ≥ 0.7865, MAE ≤ 1.0637, and RMSE ≤ 1.2466. Additionally, the FBNN based on hyperbolic tangent activation function demonstrated the best similarity between actual and predicted for SPI 24 by 98.44%. Eventually, all the activation function of FBNN models has good results respecting the SPI prediction with a small degree of variation among timescales. Therefore, any of these activation functions can be used equally even if the sigmoid and bipolar sigmoid functions are manifesting less adjusted R2 and higher errors (MAE and RMSE). In conclusion, the FBNN can be considered a promising technique for predicting the SPI as a drought monitoring index under arid ecosystems.
KeywordsArtificial intelligence SPI TRMM data Water resources
Analyses and visualizations used in this paper were produced with the Giovanni online data system, developed and maintained by the NASA GES DISC.
The Project was Financially Supported by King Saud University, Vice Deanship of Research Chairs.
- Ayuso LJ, Ayuso-Ruiz P, García-Marín PA, Estévez J, Taguas VE (2015) Local analysis of the characteristics and frequency of extreme droughts in Málaga using the SPI (standardized precipitation index). In: Ayuso Muñoz LJ, Yagüe Blanco LJ, Capuz-Rizo FS (eds) Project management and engineering: selected papers from the 17th international AEIPRO Congress held in Logroño, Spain, in 2013. Springer International Publishing, Cham, pp 167–179Google Scholar
- Box GEP, Jenkins GM (1976) Time series analysis. Forecasting and control. Revised ed. Holden-Day, San Francisco, p 575Google Scholar
- Brown ME (2008) Famine early warning systems and remote sensing data. Springer, Berlin, p 78Google Scholar
- Karakoc U, Patil S (2016) Comparison of TRMM satellite and ground-based precipitation data for predicting streamflow in Kucuk Menderes River Basin, Turkey. In: EGU General Assembly Conference Abstracts, p 1467Google Scholar
- Lohani VK, Loganathan GV, Mostaghimi S (1998) Long-term analysis and short-term forecasting of dry spells by palmer drought severity index. Hydrol Res 29:21–40Google Scholar
- Maca P, Pech P (2016) Forecasting SPEI and SPI drought indices using the integrated artificial neural networks. Intell Neuroscience 2016:14–14Google Scholar
- McKee T, Doesken N, Kleist J (1993) The relation of drought frequency and duration to time scales. In: Proceedings of the 8th Conference on Applied Climatology, Anaheim, CA. American Meteorological Society, Boston, MA, pp 179–184Google Scholar
- Olivares BO, Cortez A, Lobo D, Parra RM, Rey BJC, Rodríguez MF (2016) Study of meteorological drought in the venezuelan plains using the standardized precipitation index. Acta Nova 7:266Google Scholar
- Qureshi AS, Akhtar M (2004) Analysis of drought-coping strategies in Baluchistan and Sindh provinces of Pakistan. Sri Lanka, International Water Management Institute, Working paper 86Google Scholar
- Raudkivi AJ (2013) Hydrology: an advanced introduction to hydrological processes and modelling. Elsevier Science, p 272Google Scholar
- Sassa K, Canuti P, Yin Y (2014) Landslide science for a safer geoenvironment. Volume 2: methods of landslide studies. Springer International Publishing, p 302Google Scholar
- Smakhtin VU, Hughes DA (2004) Review, automated estimation and analyses of drought indices in South Asia. International Water Management Institute, p 24Google Scholar
- Strelcová K et al (2008) Bioclimatology and natural hazards. Springer, Netherlands, p 87Google Scholar