Supplementary Files
Keywords
Time series (TS)
Water treatment
Machine learning (ML)
Membrane distillation (MD)
How to Cite
Abstract
Membrane life and performance are crucial factors in adopting membrane-based processes for water treatment and separations. This study investigated various time series models using hold-out validation of experimentally generated water vapor flux and salt rejection rates. Membrane properties were optimized by incorporating carbon-based nanomaterials to enhance anti-wetting and porosity, developing correlations between membrane characteristics and high fluxes. Fine-tuned Autoregressive Integrated Moving Average (ARIMA), Prophet, Exponential Smoothing, and Neural Prophet models were trained on an experimental dataset (N=434) collected over 36 hours to forecast performance for 72 hours. Results demonstrate the superiority of the Exponential Smoothing statistical model in predicting and forecasting membrane performance, yielding the lowest root mean square error (RMSE) of 0.006 and mean absolute error (MAE) of 0.007. This outperformance is attributed to its non-linear data fitting approach, which employs weighted averages to mitigate non-stationary behavior in time series data, a characteristic often observed in membrane performance over time. While other models showed promise, they did not match the accuracy of Exponential Smoothing in this context. The proposed modeling approach offers a more efficient alternative to traditional experimental studies, potentially leading to significant cost and time savings in the research and development phase of membrane distillation processes. This method's applicability to various membrane types and operational conditions warrants further investigation.
References
Ridwan MG, Altmann T, Yousry A, Das R. Intelligent framework for coagulant dosing optimization in an industrial-scale seawater reverse osmosis desalination plant. Machine Learning with Applications. 2023;12: 100475. https://doi.org/10.1016/j.mlwa.2023.100475
Jeong N, Wiltse ME, Boyd A, Blewett T, Park S, Broeckling C. Efficacy of nanofiltration and reverse osmosis for the treatment of oil-field produced water intended for beneficial reuse. ACS ES&T Eng. 2023; 3(10): 1568-81. https://doi.org/10.1021/acsestengg.3c00138
Campisi G, Cosenza A, Giacalone F, Randazzo S, Tamburini A, Micale G. Desalination of oilfield produced waters via reverse electrodialysis: a techno-economical assessment. Desalination. 2023; 548: 116289. https://doi.org/10.1016/j.desal.2022.116289
Liu Y, Wang J, Hoek EMV, Municchi F, Tilton N, Cath TY, et al. Multistage surface-heated vacuum membrane distillation process enables high water recovery and excellent heat utilization: a modeling study. Environ Sci Technol. 2022; 57(1): 643-54. https://doi.org/10.1021/acs.est.2c07094
Wang P, Cheng W, Zhang X, Liu Q, Li J, Ma J, et al. Membrane scaling and wetting in membrane distillation: mitigation roles played by humic substances. Environ Sci Technol. 2022; 56(5): 3258-66. https://doi.org/10.1021/acs.est.1c07294
Hammami MA, Croissant JG, Francis L, Alsaiari SK, Anjum DH, Ghaffour N, et al. Engineering hydrophobic organosilica nanoparticle-doped nanofibers for enhanced and fouling resistant membrane distillation. ACS Appl Mater Interfaces. 2017; 9(2): 1737-45. https://doi.org/10.1021/acsami.6b11167
Lu KJ, Cheng ZL, Chang J, Luo L, Chung TS. Design of zero liquid discharge desalination (ZLDD) systems consisting of freeze desalination, membrane distillation, and crystallization powered by green energies. Desalination. 2019; 458: 66-75. https://doi.org/10.1016/j.desal.2019.02.001
Omar ANM, Othman MHD, Tai ZS, Amhamed AOA, Kurniawan TA, Puteh MH, et al. Recent progress, bottlenecks, improvement strategies and the way forward of membrane distillation technology for arsenic removal from water: a review. J Water Process Eng. 2023; 52: 103504. https://doi.org/10.1016/j.jwpe.2023.103504
Hong SK, Kim H, Lee H, Lim G, Cho SJ. A pore-size tunable superhydrophobic membrane for high-flux membrane distillation. J Membr Sci. 2022; 641: 119862. https://doi.org/10.1016/j.memsci.2021.119862
Shirazi MMA, Dumée LF. Membrane distillation for sustainable wastewater treatment. J Water Process Eng. 2022; 47: 102670. https://doi.org/10.1016/j.jwpe.2022.102670
Jiang X, Shao Y, Li J, Wu M, Niu Y, Ruan X, et al. Bioinspired hybrid micro/nanostructure composited membrane with intensified mass transfer and antifouling for high saline water membrane distillation. ACS nano. 2020; 14(12): 17376-86. https://doi.org/10.1021/acsnano.0c07543
Li Z, Zhang P, Chiao YH, Guan K, Gonzales RR, Xu P, et al. Improvement of anti-wetting and anti-scaling properties in membrane distillation process by a facile fluorine coating method. Desalination. 2023; 566: 116936. https://doi.org/10.1016/j.desal.2023.116936
Vafaei K, Ashtiani FZ, Karimi M, Ghorabi S. Engineering hydrophobic surface on polyethersulfone membrane with bio‐inspired coating for desalination with direct contact membrane distillation. Polym Adv Technol. 2023; 34(8): 2419-36. https://doi.org/10.1002/pat.6061
Ashrafian S, Saljoughi E, Mousavi SM, Jahanshahi M. High-performance robust graphitic carbon nitride nanosheets embedded membranes for desalination through direct contact membrane distillation. J Ind Eng Chem. 2024; 129: 243-66. https://doi.org/10.1016/j.jiec.2023.08.038
Zhao L, Liu Z, Wang Z, Smith SJD, Lu X, Wu C, et al. MOF incorporated adsorptive nanofibrous membranes for enhanced ammonia removal by membrane distillation. Desalination. 2023; 568: 117018. https://doi.org/10.1016/j.desal.2023.117018
Behnam P, Shafieian A, Zargar M, Khiadani M. Development of machine learning and stepwise mechanistic models for performance prediction of direct contact membrane distillation module-A comparative study. Chem Eng Process. 2022; 173: 108857. https://doi.org/10.1016/j.cep.2022.108857
Ma J, Xu H, Wang A, Wang A, Gao L, Ding M. Machine learning-guided underlying decisive factors of high-performance membrane distillation system: Membrane properties, operation conditions and solution composition. Sep Purif Technol. 2023; 327: 124964. https://doi.org/10.1016/j.seppur.2023.124964
Gil JD, Mendes PR, Camponogara E, Roca L, Alvarez JD, Normey-Rico JE. A general optimal operating strategy for commercial membrane distillation facilities. Renew Energy. 2020; 156: 220-34. https://doi.org/10.1016/j.renene.2020.04.074
Tai ZS, Othman MHD, Koo KN, Mustapa WNFW, Kadirkhan F. Membrane innovations to tackle challenges related to flux, energy efficiency and wetting in membrane distillation: A state-of-the-art review. Sustain Mater Technol. 2023; 39: e00780. https://doi.org/10.1016/j.susmat.2023.e00780
Dudchenko AV, Mauter MS. Neural networks for estimating physical parameters in membrane distillation. J Membr Sci. 2020; 610: 118285. https://doi.org/10.1016/j.memsci.2020.118285
Fetanat M, Keshtiara M, Low ZX, Keyikoglu R, Khataee A, Orooji Y, et al. Machine learning for advanced design of nanocomposite ultrafiltration membranes. Ind Eng Chem Res. 2021; 60(14): 5236-50. https://doi.org/10.1021/acs.iecr.0c05446
Binger ZM, Achilli A. Surrogate modeling of pressure loss & mass transfer in membrane channels via coupling of computational fluid dynamics and machine learning. Desalination. 2023; 548: 116241. https://doi.org/10.1016/j.desal.2022.116241
Ray SS, Verma RK, Singh A, Myung S, Park YI, Kim IC, et al. Exploration of time series model for predictive evaluation of long-term performance of membrane distillation desalination. Process Saf Environ Prot. 2022; 160: 1-12. https://doi.org/10.1016/j.psep.2022.01.058
Wu JJ. Improving membrane filtration performance through time series analysis. Discov Chem Eng. 2021; 1(1): 7. https://doi.org/10.1007/s43938-021-00007-6
Dash S, Giri SK, Mallik S, Pani SK, Shah MA, Qin H. Predictive healthcare modeling for early pandemic assessment leveraging deep auto regressor neural prophet. Sci Rep. 2024; 14(1): 5287. https://doi.org/10.1038/s41598-024-55973-y
Taylor SJ, Letham B. Forecasting at scale. Am Stat. 2018; 72(1): 37-45. https://doi.org/10.1080/00031305.2017.1380080
Triebe O, Laptev N, Rajagopal R. AR-Net: A simple auto-regressive neural network for time-series. arXiv Preprint. 2019. arXiv:1911.12436
Bajaj B, Joh HI, Jo SM, Kaur G, Sharma A, Tomar M, et al. Controllable one-step copper coating on carbon nanofibers for flexible cholesterol biosensor substrates. J Mater Chem B. 2016; 4(2): 229-36. https://doi.org/10.1039/C5TB01781E
Shumway RH, Stoffer DS. ARIMA models. In: Time Series Analysis and Its Applications: With R Examples. 2017: 75-163. https://doi.org/10.1007/978-3-319-52452-8_3
Martins A, Lagarto J, Canacsinh H, Reis F, Cardoso MG. Short-term load forecasting using time series clustering. Optim Eng. 2022; 23(4): 2293-314. https://doi.org/10.1007/s11081-022-09760-1
Lewis PA, Ray BK. Nonlinear modelling of periodic threshold autoregressions using TSMARS. J Time Ser Anal. 2002; 23(4): 459-71. https://doi.org/10.1111/1467-9892.00269
Hyndman RJ. The interaction between trend and seasonality. Int J Forecast. 2004; 20(4): 561-3. https://doi.org/10.1016/j.ijforecast.2004.03.005
Raha S, Gayen SK. Simulation of meteorological drought using exponential smoothing models: a study on Bankura District, West Bengal, India. SN Appl Sci. 2020; 2(5): 909. https://doi.org/10.1007/s42452-020-2730-3
Liashchynskyi P, Liashchynskyi P. Grid search, random search, genetic algorithm: a big comparison for NAS. arXiv Prepr. 2019; arXiv:1912.06059.
Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE). Geosci Model Dev Discuss. 2014; 7(1): 1525-34. https://doi.org/10.5194/gmd-7-1247-2014
Hodson TO. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci Model Dev. 2022; 15(14): 5481-7. https://doi.org/10.5194/gmd-15-5481-2022
Colan SD. The why and how of Z scores. J Am Soc Echocardiogr. 2013; 26(1): 38-40. https://doi.org/10.1016/j.echo.2012.11.005
Monfared MAS, Ghandali R, Esmaeili M. A new adaptive exponential smoothing method for non-stationary time series with level shifts. J Ind Eng Int. 2014; 10: 209-16. https://doi.org/10.1007/s40092-014-0075-5
Kahraman E, Akay O. Comparison of exponential smoothing methods in forecasting global prices of main metals. Miner Econ. 2023; 36(3): 427-35. https://doi.org/10.1007/s13563-022-00354-y
Papacharalampous G, Tyralis H, Koutsoyiannis D. Predictability of monthly temperature and precipitation using automatic time series forecasting methods. Acta Geophys. 2018; 66: 807-31. https://doi.org/10.1007/s11600-018-0120-7
Gamassa PKP, Chen Y. Application of several models for the forecasting of the container throughput of the Abidjan Port in Ivory Coast. Int J Eng Res Afr. 2017; 28: 157-68. https://doi.org/10.4028/www.scientific.net/JERA.28.157
Munim ZH, Fiskin CS, Nepal B, Chowdhury MMH. Forecasting container throughput of major Asian ports using the Prophet and hybrid time series models. Asian J Ship Logist. 2023; 39(2): 67-77. https://doi.org/10.1016/j.ajsl.2023.02.004
Makridakis S, Spiliotis E, Assimakopoulos V. M5 accuracy competition: results, findings, and conclusions. Int J Forecast. 2022; 38(4): 1346-64. https://doi.org/10.1016/j.ijforecast.2021.11.013
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2024 Jamal Ansary, Saketh Merugu, Anju Gupta