Iranian Water Research Journal

Iranian Water Research Journal

Predicting the impact of climate change on the underground water level using meta-evolutionary algorithms (case study: Dasht-e Riz-Bushehr)

Document Type : Original Article

Authors
Khosrow Hosseini 1
Fahime Taghvaee 1
Ali Asghar Hashemi 2
1 Water Engineering Department- Civil Engineering Faculty- Semnan University
2 Semnan Agricultural and Natural Resources Research and Education Center Agricultural Research, Education and Extension Organization (AREEO),
10.22034/IWRJ.2023.14484.2548
Abstract
Abstract

Introduction:

Assessment of the quantity of underground water is of particular importance in water resources management. Using new methods, including meta-evolutionary algorithms, in estimating underground water tables changes, due to their speed, convergence and very high efficiency, leads to save money and cost reduction on water resources management. Climate change produced by air warming and increasing evaporation and transpiration from surface water resources, as well as increasing demand for water consumption on the one hand, and decreasing the rainfall and recharging the underground water sources on the other hand, has augmented the stress on groundwater resources, which conducted to the drop in the ground water table.

The reports of the International Commission on Climate Change indicates that the phenomenon of climate change has occurred in Iran in recent decades, also its severity and its consequences in the future are increasd. The purpose of this research is to evaluate the changes in the underground water level of Dasht-e Riz in Bushehr province in the south of Iran in the future under the influence of climate change. The study area is located in Jam city, 265 km from Bushehr (the capital of the province) and 25 km from the Persian Gulf. Dasht-e Rez watershed is located between 52˚00’ to 52˚18’ east longitudes and 27˚49’ to 27˚07’ north latitudes.



Methods:

Groundwater table and meteorological data of Dasht-e Riz from 1992 to 2020 were analyzed to determine the effect of temperature, rainfall on ground water table. The meteorological information collected from Jam synoptic station between 1992 and 2020. Reconstruction of the missing data of this station has been done by using the data of Bandardir and Asalouye synoptic stations, which are located in the vicinity of Jam station. The information for determining the hydrograph of underground water obtained from 16 observation wells. In order to determine the parameters affecting the changes in the groundwater table level of the Dasht-e Riz, the hybrid of meta-evolutionary Slime Mold Algorithm (SMA) and the Support Vector Regression (SVR) algorithm was used. It should be noted that by analyzing the determination coefficients, the results of the hybrid solution had the better results in comparison with support vector regression algorithm.

Coupled three-dimensional models of the general circulation of the ocean are used for introducing the climate change. Due to the dependence of the effects of climate change on the results of climate release models and scenarios, to achieve more favorable visualization in the future period the climate models presented in the sixth report are used due to their greater accuracy. For evaluating the climate change, the output of the MRI-ESM2-0 model from the set of available CMIP6 models under the SSP5-8.5 release scenario was used for the base period (1992-2020) and the future period (2050-2021). After simulation, downscaling was performed; using Lars WG-v6 model.



Results:

According to the results, the total monthly rainfall will decrease in the months of January, February, April, September, October, November and December and increase in the months of March, June, July and August, while the changes in monthly rainfall in May will not change significantly. Based on the obtained results, the monthly rainfall in winter, spring and autumn (wetter months of the year) will decrease and in the summer (dry months of the year) will be on increasing trend, which will lead to a 17.1% decrease in annual rainfall.

The error on estimating the changes in groundwater table level; using the support vector regression algorithm, the combined slime mold-support vector regression algorithm was 15% and 11%, respectively, which shows the better performance of the slime mold-support vector regression combined algorithm compared to the support vector regression alone.

The evaluation of the hydrograph of Dasht-e Riz underground water unit in the future period shows that the severity of the drop in water table level in the future period is due to the upward trend in the demand for water consumption due to the increase in evaporation and transpiration, as well as the decrease in water resources due to the decrease in precipitation. It will cause the intensity of the water level drop in the future period to occur faster than the base period. The water table drop in the future period will be 0.78 meters per year, which compared to the water table drop in the base period which is 0.75 meters per year, the water level drop is more severe in the future.
Keywords
Keywords: Support Vector Regression (SVR) Algorithm
Slime Mold Algorithm (SMA)
Climate Change
Dasht-e Riz
Groundwater Hydrograph
Subjects
1.       Abbasnovinpour, E., Sadeghi, F. and Kaki, M., 2021. The effect of climate change on surface and groundwater resources in Rozeh Tea Plain. New findings in applied geology, 15(29): 15-27. [In Persian].
 
2.       Abbasi, S., Javidnejad, A. and Jafari, Sh. 2017. Investigating hydrological drought and changes in Dasht Riz underground water table (water supply sources of Fajr Jam Gas Refining Company) using GRI index. 4th comprehensive crisis management and HSE conference. [In Persian].
 
3.       Ansari, S., Dehban, H., Zareian, M. and Farokhnia, A., 2022. Investigation of temperature and precipitation changes in the Iran's basins in the next 20 years based on the output of CMIP6 model. Iranian Water Research Journal,16(1): 11-24. [In Persian].
 
4.       Chen, H., Zhao, Y., Feng, H., Li, H. and Sun, B., 2014. Assessment of climate change impacts on soil organic carbon and crop yield based on long-term fertilization applications in Loess Plateau, China. Plant and Soil, 390(1): 401-417.
 
5.       Danshgar, H., Bagheri, M. and Mardani, M., 2021. Evaluation of Consequences of Climate Change and Adaptation Strategies in Bushkan Plain of Bushehr Province. Agricultural Economics and Development, 35(1): 63-78. [In Persian].
 
6.       Eyring, V., Bony, S., Meehl, G.A., Senior, C.A., Stevens, B., Stouffer, R.J. and Taylor, K.E., 2016. Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. Geoscientific Model Development, 9(5): 1937-1958.
 
7.       Heshmati, S. and Etedali, H.R., 2021. Drought Forecasting for Future Periods Using LARS-WG Model: The Case Study of Kermanshah City. Town & Country Planning, 13(2): 647-669. [In Persian].
 
8.       Khosravi, I., Akhundzadeh, M. and Khoshgoftar, M., 2015. Modeling and predicting the drought indices using machine learning methods in order to managing hazards (case study: Eastern district of Isfahan). Environmental Risk Management, 2(1): 51-65. [In Persian].
 
9.       Mortezaii, Gh., Lotfi, J., Khalighi Sigarodi, Sh., Saravi, M. and Nazari, A., 2020. Analysis and evaluation of hydrological drought indicators in Kurdistan Province. Watershed Engineering and Management. 2(12): 441-453. [In Persian].
 
10.    O'Neill, B.C., Tebaldi, C., Van Vuuren, D.P., Eyring, V., Friedlingstein, P., Hurtt, G., Knutti, R., Kriegler, E., Lamarque, J.F., Lowe, J. and Meehl, G.A., 2016. The scenario model intercomparison project (ScenarioMIP) for CMIP6. Geoscientific Model Development, 9(9): 3461-3482.
 
11.    Rogelj, J., Popp, A., Calvin, K.V., Luderer, G., Emmerling, J., Gernaat, D., Fujimori, S., Strefler, J., Hasegawa, T., Marangoni, G. and Krey, V., 2018. Scenarios towards limiting global mean temperature increase below 1.5 C. Nature climate change, 8(4): 325-332.
 
12.    Salari, S., Moghaddasi, M., Mohammadi, M. and Akbari, M., 2021. Groundwater level prediction in Golpayegan aquifer using ANFIS and PSO combination. Iranian Journal of soil and water research, 52(3): 721-732. [In Persian].
 
13.    Shahi Nejad, B. and Dehghani, R., 2017. Evaluation and performance of support vector machine model in estimation of suspended sediment. Irrigation and Water Engineering, 8(1): 30-42. [In Persian].
 
14.    Sharafati, A., Nabaei, S. and Shahid, S., 2020. Spatial assessment of meteorological drought features over different climate regions in Iran. International Journal of Climatology, 40(3): 1864-1884.
 
15.    Stouffer, R.J., Eyring, V., Meehl, G.A., Bony, S., Senior, C., Stevens, B. and Taylor, K.E., 2017. CMIP5 scientific gaps and recommendations for CMIP6. Bulletin of the American Meteorological Society, 98(1): 95-105.
 
16.    Supreetha, B.S., Shenoy, N. and Nayak, P., 2020. Lion Algorithm-Optimized Long Short-Term Memory Network for Groundwater Level Forecasting in Udupi District, India. Applied Computational Intelligence and Soft Computing, 2020(1):2: 1-8.
 
17.    Taheri, A.S., 2022. Optimizing the operation of the dam reservoir using slime mold algorithm and comparing with genetic algorithm and ant community under drought conditions (case study: Aydogmosh Dam). Master's thesis, Semnan University, 98 p. [In Persian].
 
18.    Zarrin, A. and Dadashi Roudbari, A.A., 2020. Projection the long-term outlook Iran future temperature based on the output of the coupled model intercomparison project phase 6 (CMIP6). Journal of the Earth and Space Physics, 46(3): 583-602. [In Persian].
 
19.    Zeinalie, M., Ansari Ghojghar, M., Mehri, Y., Hosseini, S.M., 2020. Evaluation of the combination of optimization algorithms and adaptive fuzzy-neural inference system compared to time series models in groundwater level estimation. Iran-Water Resources Research, 16(3): 245-256. [In Persian].
 

  • Receive Date 07 August 2023
  • Revise Date 14 November 2023
  • Accept Date 16 November 2023
  • Publish Date 21 June 2024