Long-term monthly evapotranspiration modeling by several data-driven methods without climatic data

https://doi.org/10.1016/j.compag.2015.04.015Get rights and content

Highlights

  • Different data-driven methods are compared in predicting monthly ET0.

  • The longitude, latitude and altitude data from 50 stations are used as inputs.

  • The gene expression programming provides the worst estimates.

  • ET0 of any site can be successfully estimated without climatic measurements.

  • The ET0 maps show that the highest amounts of ET0 occurred in the southern and especially southeastern parts of the Iran.

Abstract

In this study, the ability of four different data-driven methods, multilayer perceptron artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS) with grid partition (GP), ANFIS with subtractive clustering (SC) and gene expression programming (GEP), was investigated in predicting long-term monthly reference evapotranspiration (ET0) by using data from 50 stations in Iran. The periodicity component, station latitude, longitude and altitude values were used as inputs to the applied models to predict the long-term monthly ET0 values. The overall accuracies of the multilayer perceptron ANN, ANFIS-GP and ANFIS-SC models were found to be similar to each other. The GEP model provided the worst estimates. The maximum determination coefficient (R2) values were found to be 0.997, 998 and 0.994 for the ANN, ANFIS-GP and ANFIS-SC models in Karaj station, respectively. The highest R2 value (0.978) of GEP model was found for the Qom station. The minimum R2 values were respectively found as 0.959 and 0.935 for the ANN and ANFIS-GP models in Bandar Abbas station while the ANFIS-SC and GEP models gave the minimum R2 values of 0.937 and 0.677 in the Tabriz and Kerman stations, respectively. The results indicated that the long-term monthly reference evapotranspiration of any site can be successfully estimated by data-driven methods applied in this study without climatic measurements. The interpolated maps of ET0 were also obtained by using the optimal ANFIS-GP model and evaluated in the study. The ET0 maps showed that the highest amounts of reference evapotranspiration occurred in the southern and especially southeastern parts of the Iran.

Introduction

Evapotranspiration (ET) is a process of losing water to the atmosphere via the combined process of evaporation from the soil and transpiration from the plants. In agriculture science especially in arid and semiarid areas, proper prediction of the given crop evapotranspiration (ETc) is important. Therefore, the ability to obtain or estimate evapotranspiration (ET) is of great importance for operating irrigation systems (Karimadldini et al., 2012). ETc can be calculated by multiplying ET0 (reference evapotranspiration) to the crop coefficient (Kc) of the crop.

Several methods and techniques could be applied for calculating or estimating ET including (1) direct, (2) indirect and (3) data-driven methods. Direct measurement method by using lysimeter is the best options for obtaining ET crop and ET0 but is a difficult task because it is time-consuming and needs potential financial and environmental resources. As a result, a large number of indirect methods such as empirical, semi-empirical equations and data driven models have been developed for measuring ET0 from meteorological data (Karimadldini et al., 2012). Some of the indirect ET0 estimation methods can be named as simple pan evaporation-based methods and combination methods such as (Penman, 1963), Penman–Monteith (Monteith, 1965) and etc.

One of the best known indirect method is the Food and Agricultural Organization of the United Nations (FAO) method in which combines the equation of Penman–Monteith modified by Allen in 1998 (FAO-56 PM equation) as a reference equation for ET0 estimation. The FAO-56 Penman–Monteith (PM-56) equation is influenced by several weather parameters including measurement of the maximum and minimum air temperature, maximum and minimum relative air humidity, wind speed and solar radiation. With an exception to the air temperature which is available at most weather stations, the remaining variables are often incomplete or not always available for many locations and even not always reliable (Rahimikhoob, 2010). Regarding the above contexts, there are so many factors affecting ET estimation based on indirect methods, thereafter it is extremely difficult to formulate the ET0 equation that can produce reliable estimates.

The main problem with modeling ET process is its nonlinear dynamic and high complexity, in this respect, using data-driven methods (e.g. ANN, ANFIS, SVM ...) based on soft computing techniques could be considered as proper methods for estimating ET0. These methods are known for their ability in dealing with complex problems, with only sets of available data. In the following, the application of soft computing techniques to evapotranspiration modeling is presented.

Among different soft computing methods, artificial neural networks (ANNs) due to their high ability in the modeling of nonlinear processes such as ET0 are very appropriate tools. In the past decades, ANNs were used to estimate evapotranspiration (Kumar et al., 2002, Sudheer et al., 2003, Trajkovic, 2005, Kim and Kim, 2008, Landeras et al., 2008, Traore et al., 2010). Rahimikhobb (2010) examined the potential for the use of ANNs to estimate ET0 based on air temperature data under humid subtropical conditions on the southern coast of the Caspian Sea. He claimed that the ANN model was superior to indirect empirical equations. A comprehensive and recent review of ANN applications in ET0 modeling can be refereed to Kumar et al. (2011). They showed that the performance of most of the ANN models depends on a few meteorological stations which have recorded weather data for a specific period.

In addition to ANNs, more recently adaptive neuro-fuzzy inference systems (ANFIS) was used to simulate/predict ET0 (Kisi and Ozturk, 2007, Aytek, 2009, Dogan, 2009, Cobaner, 2011, Kisi and Zounemat-Kermani, 2014). ANFIS provides an efficient way of modeling the uncertainty for complicated systems lacking adequate data. Kisi and Ozturk (2007) investigated the capability of the ANFIS in the estimation of ET0 in Los Angeles. The results showed that the ANFIS models could be considered as proper tools in modeling ET0 process. Aytek (2009) applied a coactive neuro-fuzzy inference system (CANFIS) technique for modeling daily ET0, in three stations and compared the results with some empirical formulas. They claimed that CANFIS can be employed as an alternative ET0 model to the existing conventional methods. Cobaner (2011) investigated the potential of grid partition-based fuzzy inference system (G-ANFIS) and subtractive clustering-based fuzzy inference system (S-ANFIS) and ANNs, in modeling of ET0. They found that the S-ANFIS model achieved more accurate results with fewer amounts of iterations as compared to the G-ANFIS and ANN models in modeling ET0 process.

Karimaldini et al. (2012) investigated the potential of the adaptive neuro-fuzzy computing technique (ANFIS) for daily ET0 modeling under arid conditions from limited weather data. The comparison results indicated that by using similar meteorological inputs, the ANFIS models performed better than conventional methods. Tabari et al. (2013) investigated the accuracy of the ANFIS and support vector machines (SVM) for potato ETc estimation. The results confirmed that the SVM models could provide more accurate ETc estimates than the ANFIS and empirical equations. Kisi and Zounemat-Kermani (2014), applied two different types of ANFIS (with grid partition method and ANFIS with subtractive clustering method) in modeling daily ET0. Results indicated that the three-and four-input ANFIS models were superior to the corresponding empirical equations in modeling ET0 while the calibrated two-parameter Ritchie and Valiantzas’ equations were found to be better than the two-input ANFIS models.

Gene-expression programming (GEP) interface is a powerful technique applied in many engineering researches with good generalization ability (Azamathulla et al., 2011, Shiri et al., 2014a, Shiri et al., 2014b, Shiri et al., 2014c, Marti et al., 2015, Kisi and Sanikhani, 2015). It has been observed that related studies in the literature related to the use for ET0 modeling are scare. Guven et al. (2008) presented genetic programming for the estimation of ET0 by using daily atmospheric variables obtained from the California Irrigation Management Information System database. The results of the GEP model were compared to seven conventional models and were found to be in good agreement. Results showed that the GEP model gave a fast and practical method for the estimation of ET0 to obtain accurate results and encourage the use of GEP in other aspects of water engineering studies. In another study, Traore and Guven (2012) investigated the performance ability of the GEP for modeling ET0 using decadal climatic data in Burkina Faso. They claimed that GEP is an effectual modeling tool for successfully computing evapotranspiration. To the knowledge of the writers, there is not any published paper in the literature that compares the ability of ANN, ANFIS with grid partition (ANFIS-GP), ANFIS with subtractive clustering (ANFIS-SC) and GEP in predicting long-term monthly ET0.

The aim of this study is to investigate the accuracy of multilayer perceptron ANN, ANFIS-GP, ANFIS-SC and GEP in predicting long-term monthly ET0 by using data from 50 stations in Iran.

Section snippets

Case study

The study area used in this study lays over the entire region of Iran’s geographical area (25°00′N and 38°39′N latitudes and between 44°00′E and 63°25′E longitudes) of about 1650,000 km2. According to Dinpashoh et al. (2011) generally, Iran is categorized as having arid (BW) and semi-arid (BS) climates based on the Koppen climatic classification (Ahrens, 1998). Precipitation is the main source of water in Iran, which normally amounts to 251 mm or 413 billion cubic meters annually. More than 70%

ANFIS

Neuro-fuzzy systems which are based on the rule-based fuzzy systems uses the capability of neural networks learning algorithm for adapting their rule-base parameters (Zounemat-Kermani and Scholz, 2013). Generally, in ANFIS a six layers multilayer neural network-based fuzzy system is constructed. In this system architecture, the input and output nodes represent the input states (variables) and output response (target), respectively, while in the hidden layers membership functions (MF) and rules

Application and results

Four different data-driven methods, ANN, ANFIS-GP, ANFIS-SC and GEP, were applied for estimating long-term monthly mean ET0. Latitude, longitude, altitude and periodicity component (month of the year) data were used as inputs to the each model. Monthly data of 40 weather stations (40 stations × 12 months = 480 data) were used for training and 10 stations’ data (10 stations × 12 months = 120 data) were used for testing. The stations used for the testing procedure are Mashahd, Bandar abbas, Semnan, Shiraz,

Conclusion

In this study, the accuracy of four different data-driven methods, ANN, ANFIS-GP, ANFIS-SC and GEP, were investigated to predict long-term monthly reference evapotranspiration by using geographical input data. The periodicity component, station altitude, longitude and latitude values were used as inputs to the applied models to estimate the long-term monthly ET0 values. Data from 50 weather stations in Iran were used for training and testing of the models. The data-driven models were compared

Acknowledgement

This study was partly supported by The Turkish Academy of Sciences (TUBA). The first author would like to thank TUBA for their support of this study.

References (37)

  • M. Zounemat-Kermani et al.

    Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff

    Appl. Soft Comput.

    (2013)
  • K.C. Abbaspour et al.

    Assessing the impact of climate change on water resources in Iran

    Water Resour. Res.

    (2009)
  • C. Ahrens

    Essentials of Meteorology: An Introduction to the Atmosphere

    (1998)
  • A. Aytek

    Co-active neurofuzzy inference system for evapotranspiration Modeling

    Soft Comput.

    (2009)
  • H.M. Azamathulla et al.

    Gene-expression programming for the development of a stage-discharge curve of the Pahang River

    Water Resour. Manage.

    (2011)
  • E. Dogan

    Reference evapotranspiration estimation using adaptive neuro-fuzzy inference systems

    Irrig. Drain.

    (2009)
  • C. Ferreira

    Gene expression programming: a new adaptive algorithm for solving problems

    Complex Syst.

    (2001)
  • C. Ferreira

    Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence

    (2006)
  • Cited by (100)

    • A comparative analysis of SLR, MLR, ANN, XGBoost and CNN for crop height estimation of sunflower using Sentinel-1 and Sentinel-2

      2023, Advances in Space Research
      Citation Excerpt :

      The basic theory of the MLR can be viewed from the study of Tranmer et al. (2020). Artificial neural networks (ANNs) are designed based on biologically computational models that are formed by many interconnected neurons with coefficients composing the neural structure (Kisi et al., 2015, Inyurt and Sekertekin 2019, Gullu and Narin 2019). The ANNs can define the correlations between input and output variables and generate a model by considering these relationships (Kisi et al., 2016).

    View all citing articles on Scopus
    View full text