Su Tüketimi Tahmininde Yapay Zekâ: Sistematik İnceleme

Abstract

Su tüketiminin tahmin edilmesi, su kaynaklarının sürdürülebilir bir şekilde yönetilmesi ve dünya genelindeki su sorunlarının çözülmesi açısından hayati öneme sahiptir. Su, tüm canlıların yaşamı için vazgeçilmez olduğundan, uzun süredir birçok çalışmanın odağında yer almıştır. Bu çalışmalarda yapay zekâ, makine öğrenmesi ve geleneksel istatistiksel yöntemler kullanılmıştır. Bu makale, su tüketimi tahmininde yapay zekâ uygulamalarına dair mevcut araştırmaları kapsamlı bir şekilde incelemektedir. Çalışma, 2019 ile 2024 yılları arasında yayımlanmış ve SpringerLink, IEEE Xplore ve Scopus gibi akademik veri tabanlarından elde edilmiş makaleler üzerinden yürütülmüştür. İncelenen literatür, su tüketimini tahmin etmek için kullanılan algoritmalara göre sınıflandırılmıştır. Ayrıca, su tüketimi tahmin çalışmalarında kullanılan yapay zekâ yöntemlerinin avantajları, dezavantajları ve karşılaşılan zorluklar da değerlendirilmiştir. Elde edilen sonuçlar, Uzun Kısa Süreli Bellek (LSTM) modellerinin performansının diğer yöntemlere kıyasla daha iyi olduğunu ortaya koymaktadır. Bununla birlikte, veri kalitesi ve erişilebilirliği sınırlayıcı faktörler arasında yer almaktadır. Bu çalışma, yapay zekâ tabanlı yöntemlerle su tüketimi tahminine yönelik son gelişmeleri incelemekte ve bu alandaki gelecekteki araştırmalar için potansiyel yönleri vurgulamaktadır.

Keywords

• Makine öğrenmesi
• su tüketimi tahmini
• su talebi yönetimi
• yapay zeka

Artificial Intelligence in Water Consumption Forecasting: A Systematic Review

Abstract

Predicting water consumption is crucial for the sustainable management of water resources and for solving the world's water problems. Water is the subject of numerous studies as it is essential for the survival of all living beings. Artificial intelligence, machine learning and conventional statistical methods have been used in these studies. This article provides a comprehensive overview of the research about AI applications for water consumption predictions. The study was conducted using articles published between 2019 and 2024, retrieved from academic databases such as SpringerLink, IEEE Xplore and Scopus. The analyzed literature was categorized based on water studies in relation to the algorithms used to predict water consumption. The study also investigated the advantages, disadvantages and difficulties of artificial intelligence methods used in water consumption estimation studies. The results show that the performance of Long Short-Term Memory models is better than other methods. Nevertheless, data quality and availability are limiting factors. This study examines recent advances in predicting water consumption using AI-based methods and identifies potential areas for further research in this field.

Keywords

• Artificial intelligence
• machine learning
• water demand management
• water forecasting

References

1. Al-Ghamdi, A. B., Kamel, S., & Khayyat, M. (2022). A Hybrid Neural Network-based Approach for Forecasting Water Demand. Computers, Materials & Continua, 73(1), 1365-1363. https://doi.org/10.32604/cmc.2022.026246
2. Bejarano, G., Kulkarni, A., Raushan, R., Seetharam, A., & Ramesh, A. (2019). Swap: Probabilistic graphical and deep learning models for water consumption prediction. In Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 233-242. https://doi.org/10.1145/3360322.3360846
3. Bhushan, S. (2022). The use of LSTM models for water demand forecasting and analysis. In Proceedings of 3rd International Conference on Machine Learning, Advances in Computing, Renewable Energy and Communication: MARC 2021 (pp. 247-256). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-19-2828-4_24
4. Boudhaouia, A., & Wira, P. (2021). A real-time data analysis platform for short-term water consumption forecasting with machine learning. Forecasting, 3(4), 682-694. https://doi.org/10.3390/forecast3040042
5. Boudhaouia, A., & Wira, P. (2022). SARIMA and neural network models combination for time series forecasting: Application to daily water consumption. In 2022 International Conference on Theoretical and Applied Computer Science and Engineering, 169-174. https://doi.org/10.1109/ictacse50438.2022.10009716
6. Cao, L., Yuan, X., Tian, F., Xu, H., & Su, Z. (2023). Forecasting of water consumption by integrating spatial and temporal characteristics of short-term water use in cities. Physics and Chemistry of the Earth, Parts A/B/C, 130, 103390. https://doi.org/10.1016/j.pce.2023.103390
7. Cao, Z., Yan, H., Wu, Z., Li, D., & Wen, B. (2024). A Novel Model Based on Deep Learning Approach Combining Data Decomposition Technique and Grouping Distribution Strategy for Water Demand Forecasting of Urban Users. Journal of Circuits, Systems and Computers, 33(01), 2450007. https://doi.org/10.1142/S0218126624500075
8. Chen, Y., Yin, G., & Liu, K. (2021). Regional differences in the industrial water use efficiency of China: The spatial spillover effect and relevant factors. Resources, Conservation and Recycling, 167, 105239. https://doi.org/10.1016/j.resconrec.2020.105239.

9. Dong, C., Schoups, G., & Van de Giesen, N. (2013). Scenario development for water resource planning and management: a review. Technological forecasting and Social change, 80(4), 749-761. https://doi.org/10.1016/j.techfore.2012.09.015
10. Du, H., Zhao, Z., & Xue, H. (2020). ARIMA-M: A new model for daily water consumption prediction based on the autoregressive integrated moving average model and the Markov chain error correction. Water, 12(3), 760. https://doi.org/10.3390/w12030760
11. El Hanjri, M., Kabbaj, H., Kobbane, A., & Abouaomar, A. (2023). Federated learning for water consumption forecasting in smart cities. In ICC 2023-IEEE International Conference On Communications (pp. 1798-1803). IEEE. https://doi.org/10.1109/ICC45041.2023.10279576
12. Faiz, M., & Daniel, A. K. (2023). A hybrid WSN based two-stage model for data collection and forecasting water consumption in metropolitan areas. International Journal of Nanotechnology, 20 (5-10), 851-879. https://doi.org/10.1504/IJNT.2023.134038.
13. Farah, E., Abdallah, A., & Shahrour, I. (2019). Prediction of water consumption using Artificial Neural Networks modelling (ANN). In MATEC Web of Conferences 295, 01004. EDP Sciences. https://doi.org/10.1051/matecconf/201929501004
14. Gao, X., Zeng, W., Shen, Y., Guo, Z., Yang, J., Cheng, X., ... & Yu, K. (2020). Integrated Deep Neural Networks‐Based Complex System for Urban Water Management. Complexity, 2020(1), 8848324. https://doi.org/10.1155/2020/8848324
15. García-Soto, C. G., Torres, J. F., Zamora-Izquierdo, M. A., Palma, J., & Troncoso, A. (2024). Water consumption time series forecasting in urban centers using deep neural networks. Applied Water Science, 14(2), 21. https://doi.org/10.1007/s13201-023-02072-4
16. Görenekli, K., & Gülbağ, A. (2024). Comparative analysis of machine learning techniques for water consumption prediction: a case study from kocaeli province. Sensors, 24(17), 5846.
17. Gutiérrez, S., Ponce, H., & Espinosa, R. (2020). An Intelligent Water Consumption Prediction System based on Internet of Things. In 2020 IEEE International Conference on Engineering Veracruz (ICEV) (pp. 1-6). IEEE. 10.1109/ICEV50249.2020.9289683
18. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
19. Huang, H., Lin, Z., Liu, S., & Zhang, Z. (2023). A neural network approach for short-term water demand forecasting based on a sparse autoencoder. Journal of Hydroinformatics, 25(1), 70-84. https://doi.org/10.2166/hydro.2022.089
20. Kavurucu, B., Ekmen, E., Yaman, Ö., Yazan, S.Y., Kanmaz, N., Ünver, Ü.: Türkiye’de Endüstriyel Su Tüketimi ve Arıtımı. İleri Mühendislik Çalışmaları ve Teknolojileri Dergisi, 3,19-33 (2022). https://dergipark.org.tr/tr/pub/imctd/issue/71276/1052809
21. Kim, D., Choi, S., Kang, S., & Noh, H. (2023). A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station. Water, 15(23), 4160. https://doi.org/10.3390/w15234160
22. Liu, J., Zhou, X. L., Zhang, L. Q., & Xu, Y. P. (2023). Forecasting short-term water demands with an ensemble deep learning model for a water supply system. Water Resources Management, 37(8), 2991-3012. ). https://doi.org/10.1007/s11269-023-03471-7.
23. Moher, D., Liberati, A., Tetzlaff, J., & Altman, D. G. (2009). Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. Bmj, 339.
24. Monjardin, C. E. F., de Jesus, K. L. M., Claro, K. S. E., Paz, D. A. M., & Aguilar, K. L. (2020). Projection of water demand and sensitivity analysis of predictors affecting household usage in urban areas using artificial neural network. In 2020 IEEE 12th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) (pp. 1-6). IEEE. https://doi.org/10.1109/HNICEM51456.2020.9400043
25. Oyebode, O. (2019). Evolutionary modelling of municipal water demand with multiple feature selection techniques. Journal of Water Supply: Research and Technology—AQUA, 68(4), 264-281. https://doi.org/10.2166/aqua.2019.145
26. Oyebode, O., & Ighravwe, D. E. (2019). Urban water demand forecasting: a comparative evaluation of conventional and soft computing techniques. Resources, 8(3), 156. https://doi.org/10.3390/resources8030156
27. Piasecki, A., Jurasz, J., & Kaźmierczak, B. (2018). Forecasting daily water consumption: a case study in Torun, Poland. Periodica Polytechnica Civil Engineering, 62(3), 818-824. https://doi.org/10.3311/PPCI.11930.
28. Pourmousavi, M., Nasrollahi, H., Najafabadi, A. A., & Kalhor, A. (2022). Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand. Water Supply, 22(8), 6833-6854. https://doi.org/10.2166/ws.2022.243.
29. Ribeiro, M. H. D. M., Da Silva, R. G., Larcher, J. H. K., De Lima, J. D., Mariani, V. C., & Coelho, L. D. S. (2021). Seasonal-trend and multiobjective ensemble learning model for water consumption forecasting. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. https://doi.org/10.1109/IJCNN52387.2021.9534104
30. Rustam, F., Ishaq, A., Kokab, S. T., de la Torre Diez, I., Mazón, J. L. V., Rodríguez, C. L., & Ashraf, I. (2022). An artificial neural network model for water quality and water consumption prediction. Water, 14(21), 3359. https://doi.org/10.3390/w14213359
31. Said, N. M., Zin, Z. M., Ismail, M. N., & Bakar, T. A. (2021). Univariate water consumption time series prediction using deep learning in neural network (DLNN). International Journal of Advanced Technology and Engineering Exploration, 8(76), 473. https://doi.org/10.19101/IJATEE.2020.762165
32. Sajjanshetty, A. S., Jayanth, V., Mohan, R., Pahari, S., & Deepti, C. (2023). Estimation of Community Water Consumption Using Multivariate Ensemble Approach. In 2023 IEEE International Conference on Contemporary Computing and Communications (InC4) 1,1-5. https://doi.org/10.1109/InC457730.2023.10263265
33. Shirkoohi, M. G., Doghri, M., & Duchesne, S. (2021). Short-term water demand predictions coupling an artificial neural network model and a genetic algorithm. Water Supply, 21(5), 2374-2386. https://doi.org/10.2166/ws.2021.049
34. Tzanes, G., Papapostolou, C., Gymnopoulos, M., Kaldellis, J., & Stamou, A. (2023). Evaluation of the Performance Gains in Short-Term Water Consumption Forecasting by Feature Engineering via a Fuzzy Clustering Algorithm in the Context of Data Scarcity. Environmental Sciences Proceedings, 26(1), 105. https://doi.org/10.3390/environsciproc2023026105
35. Wang, R., Zou, X., & Song, H. (2023) An applied study of a technique incorporating machine learning algorithms to optimize water demand prediction. Applied Mathematics and Nonlinear Sciences, 9(1), 1-14. https://doi.org/10.2478/amns-2024-0807
36. Wei, H., Xu, W., Kang, B., Eisner, R., Muleke, A., Rodriguez, D., ... & Harrison, M. T. (2024). Irrigation with artificial intelligence: problems, premises, promises. Human-Centric Intelligent Systems, 4(2), 187-205. https://doi.org/10.1007/s44230-024-00072-4
37. Willmott, C. J. (1981). On the validation of models. Physical geography, 2(2), 184-194. https://doi.org/10.1080/02723646.1981.10642213
38. Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 30(1), 79-82. https://www.int-res.com/articles/cr2005/30/c030p079.pdf
39. Yan, J., Liu, K., & Yu, Y. (2022). Water consumption prediction model based on clustering and Multi-layer Perceptron. In 2022 4th International Academic Exchange Conference on Science and Technology Innovation (IAECST) (pp. 464-467). 10.1109/IAECST57965.2022.10061996
40. Yu, Y., Si, X., Hu, C., & Zhang, J. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 31(7), 1235-1270. https://doi.org/10.1162/neco_a_01199
41. Zheng, Y., Zhang, W., Xie, J., & Liu, Q. (2022). A water consumption forecasting model by using a nonlinear autoregressive network with exogenous inputs based on rough attributes. Water, 14(3), 329. https://doi.org/10.3390/w14030329
42. Zubaidi, S. L., Abdulkareem, I. H., Hashim, K. S., Al-Bugharbee, H., Ridha, H. M., Gharghan, S. K., ... & Al-Khaddar, R. (2020). Hybridised artificial neural network model with slime mould algorithm: a novel methodology for prediction of urban stochastic water demand. Water, 12(10), 2692. https://doi.org/10.3390/w12102692