Iran-Water Resources Research

Iran-Water Resources Research

Prediction of Evaporation Using Chaos Theory and Artificial Intelligence in Dry Lands (Case Study: Semnan Province)

Document Type : Original Article

Authors
1 Ph.D. Graduate in Desert Management and Control, Faculty of Desert Studies, Semnan University, Semnan, Iran.
2 Associate Professor, Faculty of Desert Studies, Semnan University, Semnan, Iran.
3 Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran.
Abstract
Evaporation is one of the important phenomena of the hydrological cycle and its prediction is essential for water management, planning and conservation. Since chaos theory deals with the study of dynamic systems, in this research the prediction of the evaporation process was carried out using the combination of chaos theory and intelligent models, including support vector machine, decision tree, group learning, and Gaussian process. Data of the Semnan synoptic station during the period of 1995-2019 was selected. The optimal values ​​of delay and mutual information were respectively obtained as 18 and 9 using false nearest neighbor methods in order to reconstruct the variable phase space of evaporation. According to different combinations of variables, the most optimal response of all models was determined for the combination of all parameters, and the two factors of evaporation and temperature had the greatest impact on the prediction. In general, the support vector machine model with R2 = 85.5 and MAE = 1.4 had the best performance followed by the methods of Gaussian process, group learning and decision tree method as next bests. The combined use of chaos theory along with intelligent algorithms has a good ability to estimate evaporation.
Keywords

Subjects


Alberg D, Last M, Kandel A (2012) Knowledge discovery in data streams with regression tree methods. WIREs Data Mining Know Discover 2:69-78
Alsumaiei A A (2020) Utility of artificial neural networks in modeling pan evaporation in hyper-arid climates. Water 12(5):1508
Ayodele T R, Ogunjuyigbe A S O, Amedu A, Munda J L (2019) Prediction of global solar irradiation using hybridized k-means and support vector regression algorithms. Renwable Energy Focus 29:78-93
Benzaghta M A (2014) Estimation of evaporation from a reservoir in semi arid environments using artificial neural network and climate based models. Journal of Applied Science and Technology 4(24):3501-3518
El Bilali A, Abdeslam A, Ayoub N, Lamane H, Abdellah Ezzaouini M, Elbeltagi A (2023) An interpretable machine learning approach based on DNN, SVR, Extra Tree, and XGBoost models for predicting daily pan evaporation. Journal of Environmental Management 327:116890
Farzin S, Farzin N, Hassanzadeh Y, Aalami MT (2012) An investigation on changes and prediction of Urmia Lake water surface evaporation by Chaos Theory. International Journal of Environmental Reaserch 6(3):815-824
Farzin S, Hajiabadi, R, Ahmadi M H (2017) Application of Chaos Theory and artificial neural networks to evaluate evaporation from lake's water surface. Water and Soil 31(1):61-74
Ferreira L B, Da Cunha F, OliveraD R, Fernandes EI (2019) Estimation of reference evapotranspiration in Brazil with limited meteorological data using ANN and SVM–A new approach. Journal of Hydrology 527:556-570
Jerome H (2001) 1999 Reitz lecture greedy function approxi mation: a gradeient boosting machine. The Annals of Statictis 29 (5):1189-1232
Kisi O (2015) Pan evaporation modeling using least square support vector machine multivariate adaptive regression splines and M5 model tree. Journal of Hydrology 528:312-320
Kumar Goyal M, Birendra B, Quilty J, Adamowksi J, Pandey A (2017) Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS. Expert Systems with Applications 41:5267-5276
Kocak K, Bali A, Bektasoglu B (2007) Prediction of monthly flows by using chaotic approach. International Congress on River Basin Management, 22-24 March, Antalya, Turkey, p. 553-559
Khullar S, Singh N (2022) Water quality assessment of a river using deep learning Bi-LSTM methodology: Forecasting and validation. Environmental Science and Pollution Research 29(9):12875-89
La Fuente S, Jennings E, Gal G, Kirillin G, Shatwell T, Ladwig R, Moore T, Couture T. M. Cote M, Vinna R, Woolway I (2022) Multi-model projections of future evaporation in a sub-tropical lake. Journal of Hydrology 615:Part A, 128729
Malik A, Kuma, A, Kisi O (2019) Monthly pan-evaporation estimation in Indian central Himalayas using different heuristic approaches and climate based models. Computers and Electronics in Agriculture 143:302-313
Ozlem B, Kasim K (2014) SVR-based prediction of evaporation combined with chaotic approach. Journal of Hydrology 508:356-363
Pal M, Deswal S (2010) Modelling pile capacity using Gaussian process regression. Computers and Geotechnics 37:942-947
Rasmussen C E, Williams C K (2006) Gaussian process for machine learning. Massachusetts. MIT Press, p 266.
Rocha S, Molinas E, Rodrigues I (2023) Assessment of total evaporation rates and its surface distribution by tridimensional modelling and remote sensing. Journal of Environmental Management 327:116846
Sik Kim M, Cha D, Mi Lee S, Jeong H, Lee L (2023) Prediction of brine evaporation rate in a pond: Development of different models under controlled meteorological conditions and comparative evaluation. Desalination 551:116415
Taghipour K (2023) Application of chaos theory in electrical engineering. Journal of Science Engineering Elites 8(1):35-48
Wang Y, Jiang T, Bothe O, Fraedrich K (2007) Changes of pan evaporation and reference evapotranspiration in the Yangtze River basin. Theoretical and Applied Climatology 90(1-2):13-23
Wang W, Xu D, Chau K, Chen S (2013) Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD. Journal of Hydroinformatics 15:1377–1390
Webber C L, Zbilut J P (2005) Recurrence quantifcation analysis of nonlinear dynamical systems. Tutorials in Contemporary Nonlinear Methods for the
Behavioral Sciences 26–94
Wang L, Niu Z, Kisi O, Li C, Yu D (2017) Pan evaporation modeling using four different heuristic approaches. Computers and Electronics in Agriculture 140:203-213
Vapnik V (1995) The nature of statistical learning theory. Data Mining and Knowledge Discovery, Springer, Berlin
Wallot S, Mønster D (2018) Calculation of Average Mutual Information (AMI) and False-Nearest Neighbors (FNN) for the estimation of embedding parameters of multidimensional time series in matlab. Frontiers in psychology 10(9): 1679
hang H, Gorelick S M, Zimba PV, Zhang X (2017) A remote sensing method for estimating regional reservoir area and evaporative loss. Journal of Hydrology 555:213-227
Zhao G, Gao H (2019) Estimating reservoir evaporation losses for the United States: Fusing remote sensing and modeling approaches. Remote Sensing of Environment 226:09-124

  • Receive Date 19 November 2023
  • Revise Date 18 April 2024
  • Accept Date 23 April 2024