A state-of-the-art Fuzzy Nonlinear Additive Regression (FNAR) model for groundwater level prediction

Sepideh Zeraati Neyshabouri; Abbas Khashei-Siuki; Mohammad Ghasem Akbari

doi:10.26599/JGSE.2026.9280074

Volume 14 Issue 1

Mar. 2026

Turn off MathJax

Article Contents

Article Navigation > Journal of Groundwater Science and Engineering > 2026 > 14(1): 83-99

Neyshabouri SZ, Khashei-Siuki A, Akbari MG. 2026. A state-of-the-art Fuzzy Nonlinear Additive Regression (FNAR) model for groundwater level prediction. Journal of Groundwater Science and Engineering, 14(1): 83-99 doi: 10.26599/JGSE.2026.9280074

Citation:

PDF( 1903 KB)

A state-of-the-art Fuzzy Nonlinear Additive Regression (FNAR) model for groundwater level prediction

doi: 10.26599/JGSE.2026.9280074

1.
Department of Water Engineering, University of Birjand, Birjand, Iran
2.
Department of Mathematical Sciences, University of Birjand, Birjand, Iran
3.
Department of Statistics, Faculty of Mathematical Sciences, Ferdowsi University of Mashhad, Mashhad, Iran

More Information

Corresponding author: abbaskhashei@yahoo.com
Received Date: 2025-05-15
Accepted Date: 2025-11-16

Available Online: 2026-01-15

Publish Date: 2026-03-15

Abstract

Abstract

Groundwater modeling remains challenging due to heterogeneity and complexity of aquifer systems, necessitating endeavors to quantify Groundwater Levels (GWL) dynamics to inform policymakers and hydrogeologists. This study introduces a novel Fuzzy Nonlinear Additive Regression (FNAR) model to predict monthly GWL in an unconfined aquifer in eastern Iran, using a 19-year (1998–2017) dataset from 11 piezometric wells. Under three distinct scenarios with progressively increasing input complexity, the study utilized readily available climate data, including Precipitation (Prc), Temperature (Tave), Relative Humidity (RH), and Evapotranspiration (ETo). The dataset was split into training (70%) and validation (30%) subsets. Results showed that among three input scenarios, Scenario 3 (Sc3, incorporating all four variables) achieved the best predictive performance, with RMSE ranging from 0.305 m to 0.768 m, MAE from 0.203 m to 0.522 m, NSE from 0.661 to 0.980, and PBIAS from 0.771% to 0.981%, indicating low bias and high reliability. However, Sc2 (excluding ETo) with RMSE ranging from 0.4226 m to 0.9909 m, MAE from 0.3418 m to 0.8173 m, NSE from 0.2831 to 0.9674, and PBIAS from −0.598% to 0.968% across different months offers practical advantages in data-scarce settings. The FNAR model outperforms conventional Fuzzy Least Squares Regression (FLSR) and holds promise for GWL forecasting in data-scarce regions where physical or numerical models are impractical. Future research should focus on integrating FNAR with deep learning algorithms and real-time data assimilation expanding applications across diverse hydrogeological settings.
- Birjand aquifer,
- Data-scarce regions,
- Fuzzy-based approach,
- Groundwater table,
- Novel statistical model,
- Soft computing

FullText(HTML)

References(38)

References

Adnan RM, Dai HL, Mostafa RR, et al. 2023. Modelling groundwater level fluctuations by ELM merged advanced metaheuristic algorithms using hydroclimatic data. Geocarto International, 38(1): 2158951. DOI: 10.1080/10106049.2022.2158951.

Ahmadi A, Olyaei M, Heydari Z, et al. 2022. Groundwater level modeling with machine learning: A systematic review and meta-analysis. Water, 14(6): 949. DOI: 10.3390/w14060949.

Ahmadifar R, Safavi HR, Mirabbasi R, et al. 2025. A hybrid vine copula-fuzzy model for groundwater level simulation under uncertainty. Environmental Monitoring and Assessment, 197(4): 403. DOI: 10.1007/s10661-025-13856-3.

Ang YK, Talei A, Zahidi I, et al. 2023. Past, present, and future of using neuro-fuzzy systems for hydrological modeling and forecasting. Hydrology, 10(2): 36. DOI: 10.3390/hydrology10020036.

Aryafar A, Khosravi V, Karami, S. 2020. Groundwater quality assessment of Birjand plain aquifer using kriging estimation and sequential Gaussian simulation methods. Environmental Earth Sciences, 79: 1−21. DOI: 10.1007/s12665-020-08905-8.

Asadolahi M, Akbari MG, Hesamian G, et al. 2021. A robust support vector regression with exact predictors and fuzzy responses. International Journal of Approximate Reasoning, 132: 206−225. DOI: 10.1016/j.ijar.2021.02.006.

Bardossy A, Duckstein L. 2022. Fuzzy rule-based modeling with applications to geophysical, biological, and engineering systems. CRC Press, London, United Kingdom. DOI: 10.1201/9780138755133

Bhadani V, Singh A, Kumar, V, et al. 2024. Nature-inspired optimal tuning of input membership functions of a fuzzy inference system for groundwater level prediction. Environmental Modelling and Software, 175: 105995. DOI: 10.1016/j.envsoft.2024.105995.

Bogardi I, Bardossy A, Duckstein L. 1983. Regional management of an aquifer for mining under fuzzy environmental objectives. Water Resources Research, 19(6): 1394−1402. DOI: 10.1029/WR019i006p01394.

Boo KBW, El-Shafie A, Othman F, et al. 2024. Groundwater level forecasting using ensemble coactive neuro-fuzzy inference system. Science of The Total Environment, 912: 168760. DOI: 10.1016/j.scitotenv.2023.168760.

Borzì I. 2025. Modeling groundwater resources in data-scarce regions for sustainable management: Methodologies and limits. Hydrology, 12(1): 2306−5338. DOI: 10.3390/hydrology12010011.

Condon LE, Kollet S, Bierkens MF, et al. 2021. Global groundwater modeling and monitoring: Opportunities and challenges. Water Resources Research, 57(12): e2020WR029500. DOI: 10.1029/2020WR029500.

Feng F, Ghorbani H, Radwan AE. 2024. Predicting groundwater level using traditional and deep machine learning algorithms. Frontiers in Environmental Science, 12: 1291327. DOI: 10.3389/fenvs.2024.1291327.

Hoogesteger J. 2022. Regulating agricultural groundwater use in arid and semi-arid regions of the Global South: Challenges and socio-environmental impacts. Current Opinion in Environmental Science and Health, 100341. DOI: 10.1016/j.coesh.2022.100341

Hu H, Yang K, Sharma A, et al. 2020. Assessment of water and energy scarcity, security and sustainability into the future for the Three Gorges Reservoir using an ensemble of RCMs. Journal of Hydrology, 586: 124893. DOI: 10.1016/j.jhydrol.2020.124893.

Kambalimath S, Deka PC. 2020. A basic review of fuzzy logic applications in hydrology and water resources. Applied Water Science, 10(8): 1−14. DOI: 10.1007/s13201-020-01276-2.

Koonce JE. 2016. Water balance and moisture dynamics of an arid and semi-arid soil: A weighing lysimeter and field study. DOI: 10.34917/9112095

Kuang X, Liu J, Scanlon BR, et al. 2024. The changing nature of groundwater in the global water cycle. Science, 383(6686): eadf0630. DOI: 10.1126/science.adf0630.

Lall U, Josset L, Russo T. 2020. A snapshot of the world's groundwater challenges. Annual Review of Environment and Resources, 45(1): 171−194. DOI: 10.1146/annurev-environ-102017-025800.

Loucks DP. 2023. Hydroinformatics: A review and future outlook. Cambridge Prisms: Water, 1: e10. DOI: 10.1017/wat.2023.10.

Malakar P, Bhanja SN, Dash AA, et al. 2022. Delineating variabilities of groundwater level prediction across the agriculturally intensive transboundary aquifers of South Asia. ACS ES& T Water, 3(6): 1547−1560. DOI: 10.1021/acsestwater. 2c00220.

Moges E, Demissie Y, Larsen L, et al. 2021. Sources of hydrological model uncertainties and advances in their analysis. Water, 13(1): 28. DOI: 10.3390/w13010028.

NavaleV, Mhaske S. 2023. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) model for Forecasting groundwater level in the Pravara River Basin, India. Modeling Earth Systems and Environment, 9(2): 2663−2676. DOI: 10.1007/s40808-022-01639-5.

Rahimi M, Ebrahimi H. 2023. Data-driven driven to underground water level using artificial intelligence hybrid algorithms. Scientific Reports, 13(1): 10359. DOI: 10.1038/s41598-023-35255-9.

Ramezani N. 2022. Modern statistical modeling in machine learning and big data analytics: Statistical models for continuous and categorical variables. In research anthology on machine learning techniques, methods, and applications (pp. 90−106). IGI Global. DOI: 10.4018/978-1-6684-6291-1.ch007.

Rashidi GH, Katibeh H, Maleki A. 2024. Forecasting groundwater fluctuations caused by earthquakes using fuzzy logic and AHP Method: A case study from Iran. Earth Science Informatics, 17(3): 2143−2158. DOI: 10.1007/s12145-024-01264-z.

Saikrishnamacharyulu I, Mohanta NR, Kumar MH, et al. 2022. Simulation of water table depth using a hybrid CANFIS model: A Case study. In Intelligent System Design: Proceedings of INDIA 2022 (pp. 319−328). Singapore: Springer Nature Singapore. DOI: 10.1007/978-981-19-4863-3_30.

Samani S, Vadiati M, Azizi F, et al. 2022. Groundwater level simulation using soft computing methods with emphasis on major meteorological components. Water Resources Management, 36(10): 3627−3647. DOI: 10.1007/s11269-022-03217-x.

Samantaray S, Biswakalyani C, Singh DK, et al. 2022. Prediction of groundwater fluctuation based on a hybrid ANFIS-GWO approach in an arid Watershed, India. Soft Computing, 26(11): 5251−5273. DOI: 10.1007/s00500-022-07097-6.

Samantaray S, Sahoo A, Baliarsingh F. 2024. Groundwater level prediction using an improved SVR model integrated with hybrid particle swarm optimization and firefly algorithm. Cleaner Water, 1: 100003. DOI: 10.1016/j.clwat.2024.100003.

Sun J, Hu L, Li D, et al. 2022. Data-driven models for accurate groundwater level prediction and their practical significance in groundwater management. Journal of Hydrology, 608: 127630. ‏ DOI: 10.1016/j.jhydrol.2022.127630

Tao H, Hameed MM, Marhoon HA, et al. 2022. Groundwater level prediction using machine learning models: A comprehensive review. Neurocomputing, 489: 271−308. DOI: 10.1016/j.neucom.2022.03.014.

Theodoridou PG, Varouchakis EA, Karatzas GP. 2017. Spatial analysis of groundwater levels using fuzzy logic and geostatistical tools. Journal of Hydrology, 555: 242−252. DOI: 10.1016/j.jhydrol.2017.10.027.

Varouchakis EA, Theodoridou PG, Karatzas GP. 2019. Spatiotemporal geostatistical modeling of groundwater levels under a Bayesian framework using means of physical background. Journal of Hydrology, 575: 487−498. DOI: 10.1016/j.jhydrol.2019.05.055.

Yang X, Zhang Z. 2022. A CNN-LSTM model based on a meta-learning algorithm to predict groundwater level in the middle and lower reaches of the Heihe River, China. Water, 14(15): 2377. DOI: 10.3390/w14152377.

Zaresefat M, Derakhshani R. 2023. Revolutionizing groundwater management with hybrid AI models: A practical review. Water, 15(9): 1750. DOI: 10.3390/w15091750.

Zarinmehr H, Tizro AT, Fryar AE, et al. 2022. Prediction of groundwater level variations based on gravity recovery and climate experiment (GRACE) satellite data and a time-series analysis: a case study in the Lake Urmia basin, Iran. Environmental Earth Sciences, 81(6): 180. DOI: 10.1007/s12665-022-10296-x.

Zowam FJ, Milewski AM. 2024. Groundwater level prediction using machine learning and geostatistical interpolation models. Water, 16(19): 2771. DOI: 10.3390/w16192771.

2305-7068/© Journal of Groundwater Science and Engineering Editorial Office. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0)

Relative Articles

[1]	Su-duan Hu, Wen-da Liu, Jun-jian Liu, Jiang-Yulong Wang, Jun-jie Yang, Zhao-yi Li, Zhi-yang Tang, Guo-qiang Wang, Tian-cun Yu, 2025: Evaluation of water quality and water resources carrying capacity using a varying fuzzy pattern recognition model: A case study of small watersheds in Hilly Region, Journal of Groundwater Science and Engineering, 13, 386-405. doi: 10.26599/JGSE.2025.9280061
[2]	Ali Al-Maktoumi, 2025: A review of factors affecting the performance and impact of managed aquifer recharge projects: Insights from arid regions, Journal of Groundwater Science and Engineering, 13, 312-340. doi: 10.26599/JGSE.2025.9280057
[3]	Md. Hossain Ali, 2025: Development of a model to estimate groundwater recharge, Journal of Groundwater Science and Engineering, 13, 406-422. doi: 10.26599/JGSE.2025.9280062
[4]	Sajjad Moradi Nazarpoor, Mohsen Rezaei, Hadi Jafari, Yazdan Mohebi, Reza Mirbageri, 2025: Introducing a new geostatistical approach to classify groundwater samples based on Stiff diagram: Case study of Chahardoly aquifer, west of Iran, Journal of Groundwater Science and Engineering, 13, 423-433. doi: 10.26599/JGSE.2025.9280063
[5]	ILUNGA Nyembwe, AMADI Akobundu Nwanosike, Gilbert NDATIMANA, Nelson OKOT, Raphaël TSHIMANGA Muamba, 2024: Evaluation of aquifer hydraulic properties from resistivity and pumping test data in parts of Gwagwalada, Northcentral Nigeria, Journal of Groundwater Science and Engineering, 12, 309-320. doi: 10.26599/JGSE.2024.9280023
[6]	Li-qiang Ge, Yan-pei Cheng, Qing Yi, Xue-ru Wen, Hua Dong, Kun Liu, Jian-kang Zhang, 2024: Research on groundwater ecological environment mapping based on ecological service function: A case study of five Central Asian countries and neighboring regions of China, Journal of Groundwater Science and Engineering, 12, 339-346. doi: 10.26599/JGSE.2024.9280025
[7]	Jun Zhang, Rong-zhe Hou, Kun Yu, Jia-qiu Dong, Li-he Yin, 2024: Impact of water table on hierarchically nested groundwater flow system, Journal of Groundwater Science and Engineering, 12, 119-131. doi: 10.26599/JGSE.2024.9280010
[8]	Jun Liu, Yan-pei Cheng, Feng-e Zhang, Xue-ru Wen, Liu Yang, 2023: Research hotspots and trends of groundwater and ecology studies: Based on a bibliometric approach, Journal of Groundwater Science and Engineering, 11, 20-36. doi: 10.26599/JGSE.2023.9280003
[9]	Wondesen Fikade Niway, Dagnachew Daniel Molla, Tarun Kumar Lohani, 2022: Holistic approach of GIS based Multi-Criteria Decision Analysis (MCDA) and WetSpass models to evaluate groundwater potential in Gelana watershed of Ethiopia, Journal of Groundwater Science and Engineering, 10, 138-152. doi: 10.19637/j.cnki.2305-7068.2022.02.004
[10]	Chun-lei GUI, Zhen-xing WANG, Rong MA, Xue-feng ZUO, 2021: Aquifer hydraulic conductivity prediction via coupling model of MCMC-ANN, Journal of Groundwater Science and Engineering, 9, 1-11. doi: 10.19637/j.cnki.2305-7068.2021.01.001
[11]	Mehmood Qaisar, Arshad Muhammad, Rizwan Muhammad, Hamid Shanawar, Mehmood Waqas, Ansir Muneer Muhammad, Irfan Muhammad, Anjum Lubna, 2020: Integration of geoelectric and hydrochemical approaches for delineation of groundwater potential zones in alluvial aquifer, Journal of Groundwater Science and Engineering, 8, 366-380. doi: 10.19637/j.cnki.2305-7068.2020.04.007
[12]	Yacob T Tesfaldet, Avirut Puttiwongrak, Tanwa Arpornthip, 2020: Spatial and temporal variation of groundwater recharge in shallow aquifer in the Thepkasattri of Phuket, Thailand, Journal of Groundwater Science and Engineering, 8, 10-19. doi: 10.19637/j.cnki.2305-7068.2020.01.002
[13]	Mehdi Bahrami, Elmira Khaksar, Elahe Khaksar, 2020: Spatial variation assessment of groundwater quality using multivariate statistical analysis(Case Study: Fasa Plain, Iran), Journal of Groundwater Science and Engineering, 8, 230-243. doi: 10.19637/j.cnki.2305-7068.2020.03.004
[14]	Abdelhakim LAHJOUJ, Abdellah EL HMAIDI, Karima BOUHAFA, 2020: Spatial and statistical assessment of nitrate contamination in groundwater: Case of Sais Basin, Morocco, Journal of Groundwater Science and Engineering, 8, 143-157. doi: 10.19637/j.cnki.2305-7068.2020.02.006
[15]	A Muthamilselvan, N Rajasekaran, R Suresh, 2019: Mapping of hard rock aquifer system and artificial recharge zonation through remote sensing and GIS approach in parts of Perambalur District of Tamil Nadu, India, Journal of Groundwater Science and Engineering, 7, 264-281. doi: DOI: 10.19637/j.cnki.2305-7068.2019.03.007
[16]	SOSI Benjamin, BARONGO Justus, GETABU Albert, MAOBE Samson, 2019: Electrical-hydraulic conductivity model for a weathered-fractured aquifer system of Olbanita, Lower Baringo Basin, Kenya Rift, Journal of Groundwater Science and Engineering, 7, 360-372. doi: DOI: 10.19637/j.cnki.2305-7068.2019.04.007
[17]	YU Kai-ning, LI Jian, LI Hui, CHEN Kang, LV Bing-xu, ZHAO Long-hui, 2016: Statistical characteristics of heavy metals content in groundwater and their interrelationships in a certain antimony mine area, Journal of Groundwater Science and Engineering, 4, 284-292.
[18]	Dana Mawlood, Jwan Mustafa, 2016: Comparison between Neuman (1975) and Jacob (1946) application for analysing pumping test data of unconfined aquifer, Journal of Groundwater Science and Engineering, 4, 165-173.
[19]	LIU Jun-qiu, XIE Xin-min, 2016: Numerical simulation of groundwater and early warnings from the simulated dynamic evolution trend in the plain area of Shenyang, Liaoning Province (P.R. China), Journal of Groundwater Science and Engineering, 4, 367-376.
[20]	, 2013: The Study of Statistical Damage Constitutive Models of Rock and Its Parameters Based on Lade-Duncan Criterion, Journal of Groundwater Science and Engineering, 1, 74-79.