با همکاری انجمن علمی گیاهان دارویی ایران

نوع مقاله : مقاله علمی پژوهشی

نویسندگان

1 پژوهشگر پژوهشکده زعفران،دانشگاه تربت حیدریه، تربت حیدریه، ایران.

2 استاد، گروه مهندسی آب، دانشگاه بیرجند، ایران و پژوهشگر پژوهشکده زعفران،دانشگاه تربت حیدریه، تربت حیدریه، ایران.

3 دانشیار گروه علوم و مهندسی آب، دانشگاه بیرجند، بیرجند، ایران.

چکیده

مدل‌سازی گروهی به‌عنوان یک مقوله نوظهور در بسیاری از رشته‌های مهندسی به‌خصوص زمینه‌های مختلف مهندسی آب در حال گسترش است. تخمین دقیق نیاز آبی زعفران به عنوان محصول راهبردی شرق کشور یکی از مهم‌ترین اقدامات تأثیرگذار در برنامه‌ریزی منابع آب منطقه خواهد بود. از این‌رو، این پژوهش اقدام به بررسی عملکرد مدل‌سازی گروهی در بهبود مدل‌سازی نیاز آبی زعفران در منطقه بیرجندِ استان خراسان جنوبی کرد. داده‌های واقعی نیاز آبی زعفران در سال دوم کشت در گام نخست در محل آزمایشگاه لایسی‌متری دانشگاه بیرجند جمع‌آوری شد. مدل‌سازی نیاز آبی زعفران با استفاده از داده‌های اقلیمی و نیاز آبی زعفران در بستر ماشین یادگیری درخت تصمیم انجام شد. همچنین، از دو روش Boosting و Bagging جهت ارتقای نتایج مدل درخت تصمیم استفاده شد. به‌منظور کمی کردن اثر مدل‌سازی گروهی آزمون‌های مقایسه‌ای متعددی نظیر شاخص‌های ارزیابی (RMSE و MAE)، مقایسه توزیع پراکنش داده‌ها (تحلیل وایولین Violin assessment)، ارزیابی کم/بیش تخمینی، مقایسه سری زمانی و تحلیل بهبود خطا استفاده شد. نتایج نشان داد که علی‌رغم دقت و کارایی نسبی مدل درخت تصمیم در شبیه‌سازی نیاز آبی زعفران، امکان بهبود نتایج همچنان وجود دارد. همچنین، نتایج اثبات کرد که مدل‌سازی گروهی ظرفیت بالقوه‌ی خوبی در زمینه ارتقای نتایج دارد. به‌طوری‌که یادگیری گروهی بانظارت (Boosting) دقت مدل درخت تصمیم را بیش از 30 درصد بهبود بخشید (کاهش قدر مطلق خطا از 36 میلی‌متر به 65/23 میلی‌متر) و این موضوع عامل کاهش RMSE را از 44/0 میلی‌متر به 07/0 میلی‌متر شد. علاوه‌بر این، نتایج آزمون‌های مقایسه‌ای تأیید کرد که خروجی تولید شده توسط روش Boosting از کیفیت بسیار بهتری نسبت به خروجی مدل درخت تصمیم و روش Bagging برخوردار است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Applicability of ensemble modeling techniques in water requirement simulations

نویسندگان [English]

  • Ahmad Jafarzadeh 1
  • Abbas Khashei Siuki 2
  • Ali Shahidi 3

1 Saffron Institute, University of Torbat Heydarieh, Torbat Heydarieh, Iran

2 Professor, Department of Water Engineering, University of Birjand, Birjand and Saffron Institute, University of Torbat Heydarieh, Torbat Heydarieh, Iran

3 Associated Professor, Department of of Water Engineering, University of Birjand, Birjand, Iran.

چکیده [English]

Ensemble modelling is expanding in several areas of engineering, especially different aspects of water engineering. Accurate estimation of saffron water requirement (SWR), an essential strategic production of the agriculture sector, is a crucial and influencing act in local water planning of this region. Hence, this study aimed to check the applicability of ensemble modelling in enhancing SWR at Birjand, Southern Khorasan, Iran. The actual water requirement of saffron was recorded in the field lysimetric laboratory at the University of Birjand. The simulation of water requirement was conducted utilizing Decision Tree Regression (DTR) with input climate features. Additionally, Boosting and Bagging methods were employed to establish and enhance the ensemble process of soil water requirement (SWR) simulations. To track the effectiveness of any method, some comparative tests were designed, such as statistical criteria (RMSE and MAE) detection, Violin plot analysis, over/underestimation, times series comparison, and error improvement test. Results indicated that although the acceptable performance of DTR in simulating SWR, the probable improvement was potentially felt. Derived results confirmed that supervised ensemble modelling (Boosting) could enhance the accuracy of DTR by more than 30 percent (reducing absolute error from 36 mm to 23.65 mm), resulting in declining RMSE from 0.44 mm to 0.07 mm. Further, different experiment outcomes revealed that the Boosting algorithm quality is more appealing than DTR and Bagging outputs.

کلیدواژه‌ها [English]

  • Artificial Intelligence
  • Error improvement
  • Lysimetric lab
  • Supervised ensemble modelling
  • Violin plot analysis
 
Ardabili, S., Mosavi, A., & Várkonyi-Kóczy, A.R. (2020). Advances in machine learning modeling reviewing hybrid and ensemble methods. In Engineering for Sustainable Future: Selected papers of the 18th International Conference on Global Research and Education Inter-Academia–2019 18 (pp. 215-227). Springer International Publishing. doi.org/10.1007/978-3-030-36841-8_21
Asadollah, S.B.H.S., Sharafati, A., Motta, D., & Yaseen, Z.M. (2021). River water quality index prediction and uncertainty analysis: A comparative study of machine learning models. Journal of Environmental Chemical Engineering, 9(1), 104599. doi.org/10.1016/j.jece.2020.104599.
Ashrafzadeh, M.R., Naghipour, A.A., Haidarian, M., & Khorozyan, I. (2019). Modeling the response of an endangered flagship predator to climate change in Iran. Mammal Research, 64, 39-51. doi.org/10.1007/s13364-018-0384-y.
Başakın, E.E., Ekmekcioğlu, Ö., Stoy, P.C., & Özger, M. (2023). Estimation of daily reference evapotranspiration by hybrid singular spectrum analysis-based stochastic gradient boosting. MethodsX, 102163. doi.org/10.1016/j.mex.2023.102163.
Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. doi.org/10.1023/A:1010933404324.
Chapagain, R., Remenyi, T.A., Harris, R.M., Mohammed, C.L., Huth, N., Wallach, D., & Ojeda, J.J. (2022). Decomposing crop model uncertainty: A systematic review. Field Crops Research, 279, 108448. doi.org/10.1016/j.fcr.2022.108448.
Chen, W., Hong, H., Li, S., Shahabi, H., Wang, Y., Wang, X., & Ahmad, B.B. (2019). Flood susceptibility modelling using novel hybrid approach of reduced-error pruning trees with bagging and random subspace ensembles. Journal of Hydrology, 575, 864-873. doi.org/10.1016/j.jhydrol.2019.05.089.
Dertimanis, V.K., Chatzi, E.N., Azam, S.E., & Papadimitriou, C. (2019). Input-state-parameter estimation of structural systems from limited output information. Mechanical Systems. doi.org/10.1016/j.ymssp.2019.02.040.
Freund, Y., Schapire, R., & Abe, N. (1999). A short introduction to boosting. Journal-Japanese. Society for Artificial Intelligence, 14(771-780), 1612. http://www.yorku.ca/gisweb/eats4400/boost.pdf.
Gibert, K., Izquierdo, J., Sànchez-Marrè, M., Hamilton, S.H., Rodríguez-Roda, I., & Holmes, G. (2018). Which method to use? An assessment of data mining methods in Environmental Data Science. Environmental Modelling & Software, 110, 3-27. doi.org/10.1016/j.envsoft.2018.09.021.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys (CSUR), 51(5), 1-42. doi.org/10.1145/3236009.
Günther, D., Marke, T., Essery, R., & Strasser, U. (2019). Uncertainties in snowpack simulations—Assessing the impact of model structure, parameter choice, and forcing data error on point‐scale energy balance snow model performance. Water Resources Research, 55(4), 2779-2800. doi.org/10.1029/2018WR023403.
Jafarzadeh, A., Khashei-Siuki, A., & Pourreza-Bilondi, M. (2022). Performance assessment of model averaging techniques to reduce structural uncertainty of groundwater modeling. Water Resources Management, 36(1), 353-377. doi.org/10.1007/s11269-021-03031-x.
Jafarzadeh, A., Pourreza-Bilondi, M., Akbarpour, A., Khashei-Siuki, A., & Samadi, S. (2021). Application of multi-model ensemble averaging techniques for groundwater simulation: synthetic and real-world case studies. Journal of Hydroinformatics, 23(6), 1271-1289. doi.org/10.2166/hydro.2021.058.
Jamei, M., Karimi, B., Ali, M., Alinazari, F., Karbasi, M., Maroufpoor, E., & Chu, X. (2023). A comprehensive investigation of wetting distribution pattern on sloping lands under drip irrigation: A new gradient boosting multi-filtering-based deep learning approach. Journal of Hydrology, 129402. doi.org/10.1016/j.jhydrol.2023.129402.
Joshi, R.C., Ryu, D., Lane, P.N., & Sheridan, G.J. (2023). Seasonal forecast of soil moisture over Mediterranean-climate forest catchments using a machine learning approach. Journal of Hydrology, 619, 129307. doi.org/10.1016/j.jhydrol.2023.129307.
Khan, M., Islam, M.Z., & Hafeez, M. (2012). Evaluating the performance of several data mining methods for predicting irrigation water requirement. In The 10th Australasian Data Mining Conference: AusDM 2012 (pp. 199-208). Australian Computer Society Inc. https://researchoutput.csu.edu.au/en/publications/evaluating-the-performance-of-several-data-mining-methods-for-pre.
Khashei-Siuki, A., Shahidi, A., Behdani, M.A., Hjiabadi, F., & Shirzadi, F. (2020). Determination of single and dual crop coefficients of saffron (Crocus sativus L.) in the first year of cultivation. Journal of Saffron Research. (In press). doi.org/10.22077/jsr.2020.3825.1143.
Mirzaei, S., Vafakhah, M., Pradhan, B., & Alavi, S.J. (2021). Flood susceptibility assessment using extreme gradient boosting (EGB), Iran. Earth Science Informatics, 14, 51-67. doi.org/10.1007/s12145-020-00530-0.
Nazeri Tahroudi, M., & Ramezani, Y. (2021). Joint frequency analysis of rainfall and precipitation concentration index (PCI) at Birjand and Tabas meteorological stations, South Khorasan Province, Iran. Water Harvesting Research, 4(2), 133-144. doi.org/10.22077/jwhr.2022.5009.1052.
Nisbet, R., Elder, J., & Miner, G.D. (2009). Handbook of statistical analysis and data mining applications. Academic press. 705-718. https://www.elsevier.com/books/handbook-of-statistical-analysis-and-data-mining-applications/nisbet/978-0-12-374765-5.
Nourali, M., Ghahraman, B., Pourreza-Bilondi, M., & Davary, K. (2016). Effect of formal and informal likelihood functions on uncertainty assessment in a single event rainfall-runoff model. Journal of Hydrology, 540,  549-564. doi.org/10.1016/j.jhydrol.2016.06.022.
Pekel, E. (2020). Estimation of soil moisture using decision tree regression. Theoretical and Applied Climatology, 139(3-4), 1111-1119. doi.org/10.1007/s00704-019-03048-8.
Perea, R.G., Poyato, E.C., Montesinos, P., & Díaz, J.R. (2019). Prediction of irrigation event occurrence at farm level using optimal decision trees. Computers and Electronics in Agriculture, 157, 173-180. doi.org/10.1016/j.compag.2018.12.043.
Rezaei, F., Ghorbani, R., & Mahjouri, N. (2022). Improving daily and monthly river discharge forecasts using geostatistical ensemble modeling. Water Resources Management, 36(13), 5063-5089. doi.org/10.1007/s11269-022-03292-0.
Sajedi-Hosseini, F., Malekian, A., Choubin, B., Rahmati, O., Cipullo, S., Coulon, F., & Pradhan, B. (2018). A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of the Total Environment, 644, 954-962.
Salam, R., & Islam, A.R.M.T. (2020). Potential of RT, Bagging, and RS ensemble learning algorithms for reference evapotranspiration prediction using climatic data-limited humid region in Bangladesh. Journal of Hydrology, 590, 125241. doi.org/10.1016/j.jhydrol.2020.125241.
Sarıgöl, M., & Katipoğlu, O.M. (2023). Estimation of monthly evaporation values using gradient boosting machines and mode decomposition techniques in the Southeast Anatolia Project (GAP) area in Turkey. Acta Geophysica, 1-18. doi.org/10.1007/s11600-023-01067-8.
Tso, G.K., & Yau, K.K. (2007). Predicting electricity energy consumption: A comparison of regression analysis, decision tree, and neural networks. Energy, 32(9), 1761-1768. doi.org/10.1016/j.energy.2006.11.010.
Wei, L., Huang, C., Wang, Z., Wang, Z., Zhou, X., & Cao, L. (2019). Monitoring of urban black-odor water based on Nemerow index and gradient boosting decision tree regression using UAV-borne hyperspectral imagery. Remote Sensing, 11(20), 2402. doi.org/10.3390/rs11202402.
Zhou, X., Liu, H., Pourpanah, F., Zeng, T., & Wang, X. (2022). A survey on epistemic (model) uncertainty in supervised learning: Recent advances and applications. Neurocomputing, 489, 449-465. doi.org/10.1016/j.neucom.2021.10.119.
Zounemat-Kermani, M., Batelaan, O., Fadaee, M., & Hinkelmann, R. (2021). Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 598, 126266. doi.org/10.1016/j.jhydrol.2021.126266.