Meteorological Drought Assessment and Prediction in Association with Combination of Atmospheric Circulations and Meteorological Parameters via Rule Based Models

Abstract

The development of data-driven models in conjunction with the advances in technologies regarded as remote sensing in generating recorded data from satellites has guided water management studies towards using these technologies, especially in the regions dealing with drought, like the Lake Urmia basin, Iran. In this basin, the agricultural sector has been exposed to dryness due to a decrease in rainfall and uncontrolled water consumption. In the last decade, many studies have tried to brighten this arena of water knowledge. However, the relationship between meteorological variables and atmospheric circulation with the meteorological drought of Lake Urmia had never been determined. The relationship between meteorological variables and atmospheric circulation with Lake Urmia's meteorological drought has been determined. This study calculated Standardized Precipitation Evapotranspiration Index (SPEI) values based on meteorological variables. Then a combination of the meteorological variables and atmospheric circulation values was considered a data mining model input for estimating the droughts. The series of the SPEI values for 3-, 6-, 9-, 12-, 24-, and 48-month time scales were obtained during 1988-2016. In this study, both the M5 Tree model and Associate Rules were used to predict and analyze the meteorological drought at six synoptic stations in the basin, considering both the atmospheric circulations (North Atlantic Oscillation (NAO), Southern Oscillation Index (SOI), Mediterranean Oscillation Index of Gibraltar-Israel (Mogi), Mediterranean Oscillation Index of Algiers-Cairo (MOac), Western Mediterranean Oscillation Index (WEMO), Mediterranean, Red, Black, Caspian, and Persian Gulf SSTs) and the meteorological variables (lagged relative humidity, evapotranspiration, average temperature, minimum-maximum temperature, and pressure). The results showed that using a combination of the atmospheric circulation indices and meteorological variables in the models increases the model's accuracy and improves the results in a long-term period. The best result in the study of drought in the Lake Urmia basin is related to SPEI48 (R = 0.85, RMSE = 0.08, MAE = 0.11), and in the association rules, the value of the lifting index of the best rule is 1.32. Although both approaches provided acceptable results, the M5 Tree model had a comparative advantage due to simple and practical linear relationships.

Keywords

• SPEI
• The Urmia Lake basin
• M5 Tree Model
• Associate Rules
• Iran

References

1. Alam, NM, Sharma GC, Moreira E, Jana C, Mishra PK, Sharma NK, Mandal D (2017) Evaluation of drought using SPEI drought class transitions and log-linear models for different agro-ecological regions of India. Physics and Chemistry of the Earth Parts A/B/C 100:31-43. https://doi.org/10.1016/j.pce.2017.02.008
2. Almeida CT, Oliveira-Júnior JF, Delgado RC, Cubo P, Ramos MC (2016) Spatiotemporal rainfall and temperature trends throughout the Brazilian Legal Amazon. 1973-2013. Int J Climatol 37:2013–2026.
3. Barlow M, Nigam S, Berbery EH (2001) ENSO Pacific decadal variability and US summertime precipitation drought and streamflow. J Clim 14:2105–2128. https://doi.org/10.1175/1520-0442(2001)014<2105:EPDVAU>2.0.CO;2
4. Buttafuoco G, Caloiero T, Ricca N, Guagliardi I (2018) Assessment of drought and its uncertainty in a southern Italy area (Calabria region). Measurement 113:205-210. https://doi.org/10.1016/j.measurement.2017.08.007
5. Demisse GB (2013) Knowledge Discovery from Satellite Images for Drought Monitoring. PhD diss, Addis Ababa University, Addis Ababa.
6. Dracup JA, Kahya E (1994) The relationships between US streamflow and La Niña events. Water Resources Research 30(7):2133-2141. https://doi.org/10.1029/94WR00751.
7. Etemad-Shahidi A, Mahjoobi J (2009) Comparison between M5 model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Engineering 36(15-16):1175-1181. https://doi.org/10.1016/j.oceaneng.2009.08.008
8. Hall M A (1999) Correlation-based Feature Selection for Machine Learning, Ph.D. thesis University of Waikato.

9. Hayes M (2003) Drought indices. Available online at ‏ http://www.drought.unl.edu/whatis/indices.html Indurkhya N, Weiss SM (1998) Estimating performance gains for voted decision trees. Intelligent Data Analysis 2(4):303-310.
10. Kahya E, Dracup J A (1994) The Influences of Type I ENSO and La Nina Events on Stream flows in the Southwestern United States. Journal of Climate 7:965-976. https://doi.org/10.1175/1520-0442(1994)007%3C0965:TIOTEN%3E2.0.CO;2
11. Kahya E, Karabörk MC (2001) The Analysis of El Nino and La Nina Signals in stream flows of Turkey. International Journal of Climatology 21:1231-1250. https://doi.org/10.1002/joc.663
12. Karabörk M Ç, Kahya E (2003) The Teleconnections between the Extreme Phases of the Southern Oscillation and Precipitation Patterns over Turkey. International Journal of Climatology 23:1607-1625. https://doi.org/10.1002/joc.958.
13. Le MH, Perez GC, Solomatine D, Nguyen LB (2016) Meteorological drought forecasting based on climate signals using artificial neural network–a case study in Khanhhoa Province Vietnam. Procedia Engineering 154:1169-1175.
14. Lee JH, Julien PY (2017) Influence of the El Niño/Southern Oscillation on South Korean Streamflow Variability: El Niño/Southern Oscillation on South Korean Streamflow Variability. Hydrological Processes 12:2162-2178., DOI: 10.1002/hyp.11168.
15. Lloyd-Hughes B, Saunders MA (2002) A drought climatology for Europe. Int J Climatol 22:1571–1592. https://doi.org/10.1002/joc.846.
16. Lyra GB, Oliveira-Júnior JF, Gois G, Cunha-Zeri G, Zeri M (2017) Rainfall variability over Alagoas under the influences of SST anomalies. Meteorog Atmos Phys 129:157–171. https://doi.org/10.1007/s00703-016-0461-1
17. Masocha M, Murwira A, Magadza CH, Hirji R, Dube T (2017) Remote sensing of surface water quality in relation to catchment condition in Zimbabwe. Physics and Chemistry of the Earth Parts A/B/C 100:13-18. https://doi.org/10.1016/j.pce.2017.02.013
18. McKee TB, Doesken NJ, Kleist J (1993) The relationship of drought frequency and duration to time scales. In Proceedings of the 8th Conference on Applied Climatology. AMS Boston MA 17(22):179–184.
19. Mishra AK, Singh VP (2010) A Review of Drought Concepts. Journal of Hydrology 391:202-216. https://doi.org/10.1016/j.jhydrol.2010.07.012
20. Moreira EE (2016) SPI drought class prediction using log-linear models applied to wet and dry seasons. Physics and Chemistry of the Earth Parts A/B/C 94:136-145. https://doi.org/10.1016/j.pce.2015.10.019
21. Nam WH, Tadesse T, Wardlow BD, Hayes MJ, Svoboda MD, Hong E M, Jang MW (2018) Developing the vegetation drought response index for South Korea (VegDRI-SKorea) to assess the vegetation condition during drought events. International Journal of Remote Sensing 39(5):1548-1574. https://doi.org/10.1080/01431161.2017.1407047.
22. Nandintsetseg B, Shinoda M (2013) Assessment of drought frequency duration and severity and its impact on pasture production in Mongólia. Nat Hazards 66:995–1008. https://doi.org/10.1007/s11069-012-0527-4
23. Nikzad M, Behbahani M, Rahimi Good A (2013) Detection of dependencies between oceanic-wet and climatic parameters for drought monitoring by data mining method Case study Khuzestan province. Iranian Journal of Water Research (13) 7:183-175.
24. Nourani V, Molajou, A (2017) Application of a hybrid association rules/decision tree model for drought monitoring. Global and Planetary Change 159:37-45. https://doi.org/10.1016/j.gloplacha.2017.10.008
25. Nourani V, Davanlou Tajbakhsh A, Molajou A, Gokcekus H (2019) Hybrid wavelet-M5 model tree for rainfall-runoff modeling. Journal of Hydrologic Engineering 24(5):04019012.
26. Nourani V, Sattari MT, Molajou A (2017) Threshold-based hybrid data mining method for long-term maximum precipitation forecasting. Water Resources Management 31(9):2645-2658. https://doi.org/10.1007/s11269-017-1649-y
27. Nourani V, Tajbakhsh AD, Molajou A (2019) Data mining based on wavelet and decision tree for rainfall-runoff simulation. Hydrology Research 50(1):75-84.
28. Palmer WC (1965) Meteorological Drought. Research paper, n 45, U. S. Department of Commerce Weather Bureau, Washington, D. C:58. Park S, Im J, Jang E, Rhee J (2016) Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions. Agricultural and forest meteorology 216:157-169. https://doi.org/10.1016/j.agrformet.2015.10.011
29. Parry S, Wilby RL, Prudhomme C, Wood P (2016) A systematic assessment of drought termination in the United Kingdom. Hydrol. Earth Syst Sci 20: 4265–4281. https://doi.org/10.5194/hess-20-4265-2016
30. Quinlan J R (1992) Learning with Continuous Classes. Proceedings of AI’92 World Scientific 92:343–348.
31. Sattari MT, Anli AS, Apaydin H, Kodal S (2012) Decision trees to determine the possible drought periods in Ankara. Atmósfera 25(1):65-83.
32. Sattari MT, Apaydin H, Ozturk F, Baykal N (2012) Application of a data mining approach to derive operating rules for the Eleviyan irrigation reservoir. Lake and Reservoir Management 28(2):142–152. https://doi.org/10.1080/07438141.2012.678927
33. Sattari MT, Shaker Sureh F, Kahya E (2020) Monthly precipitation assessments in association with atmospheric circulation indices by using tree-based models. Natural Hazards https://doi.org/10.1007/s11069-020-03946-5
34. Stagge JH, Tallaksen LM, Gudmundsson L, Van Loon AF, Stahl K (2015) Candidate distributions for climatological drought indices (SPI and SPEI). Int J Climatol 35:4027–4040. https://doi.org/10.1002/joc.4267
35. Tadesse T, Wilhite DA, Harms SK, Hayes MJ, Goddard S (2004) Drought Monitoring Using Data Mining Techniques: A Case Study for Nebraska USA. Natural Hazards 33(1):137- 159. https://doi.org/10.1023/B:NHAZ.0000035020.76733.0b
36. Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res 106:7183–7192. https://doi.org/10.1029/2000JD900719
37. Teodoro PE, Correa CCG, Torres FE, Oliveira Júnior JF, Silva Junior CA, Gois G, Delgado RC (2015) Analysis of the occurrence of wet and drought periods using standardized precipitation index in Mato Grosso do Sul state. Brazil J Agr 14:80–86.
38. Vicente-Serrano SM, Beguería S, López-Moreno JI (2010) A multiscale drought index sensitive to global warming: the standardized precipitation evapotranspiration index. Journal of Climate 23(7):1696-1718. https://doi.org/10.1175/2009JCLI2909.1
39. Vicente-Serrano SM, Beguería S, Juan IA (2011) A multiscalar global evaluation of the impact of ENSO on droughts. J Geophys Res Atm 116. https://doi.org/10.1029/2011JD016039
40. Wang W, Zhu Y, Xu R, Liu J (2015) Drought severity change in China during 1961–2012 indicated by SPI and SPEI. Nat Hazards 75:2437–2451. https://doi.org/10.1007/s11069-014-1436-5
41. Yurekli K, Sattari MT, Anli AS, Hinis M A (2012) Seasonal and annual regional drought prediction by using data-mining approach. ATMOSFERA 25(1):85-105.