Artificial Neural Network Models to Predict Wheat Crop Evapotranspiration (original) (raw)
Related papers
Estimating wheat and maize daily evapotranspiration using artificial neural network
Theoretical and Applied Climatology, 2018
In this research, artificial neural network (ANN) is used for estimating wheat and maize daily standard evapotranspiration. Ten ANN models with different structures were designed for each crop. Daily climatic data [maximum temperature (T max), minimum temperature (T min), average temperature (T ave), maximum relative humidity (RH max), minimum relative humidity (RH min), average relative humidity (RH ave), wind speed (U 2), sunshine hours (n), net radiation (Rn)], leaf area index (LAI), and plant height (h) were used as inputs. For five structures of ten, the evapotranspiration (ET C) values calculated by ET C = ET 0 × K C equation (ET 0 from Penman-Monteith equation and K C from FAO-56, ANN C) were used as outputs, and for the other five structures, the ET C values measured by weighing lysimeter (ANN M) were used as outputs. In all structures, a feed forward multiple-layer network with one or two hidden layers and sigmoid transfer function and BR or LM training algorithm was used. Favorite network was selected based on various statistical criteria. The results showed the suitable capability and acceptable accuracy of ANNs, particularly those having two hidden layers in their structure in estimating the daily evapotranspiration. Best model for estimation of maize daily evapotranspiration is «M»ANN 1 C (8-4-2-1), with T max , T min , RH max , RH min , U 2 , n, LAI, and h as input data and LM training rule and its statistical parameters (NRMSE, d, and R 2) are 0.178, 0.980, and 0.982, respectively. Best model for estimation of wheat daily evapotranspiration is «W»ANN 5 C (5-2-3-1), with T max , T min , Rn, LAI, and h as input data and LM training rule, its statistical parameters (NRMSE, d, and R 2) are 0.108, 0.987, and 0.981 respectively. In addition, if the calculated ET C used as the output of the network for both wheat and maize, higher accurate estimation was obtained. Therefore, ANN is suitable method for estimating evapotranspiration of wheat and maize.
Agronomy, 2022
Reference crop evapotranspiration (ETo) is an important component of the hydrological cycle that is used for water resource planning, irrigation, and agricultural management, as well as in other hydrological processes. The aim of this study was to estimate the ETo based on limited meteorological data using an artificial neural network (ANN) method. The daily data of minimum temperature (Tmin), maximum temperature (Tmax), mean temperature (Tmean), solar radiation (SR), humidity (H), wind speed (WS), sunshine hours (Ssh), maximum global radiation (gradmax), minimum global radiation (gradmin), day length, and ETo data were obtained over the long-term period from 1969 to 2019. The analysed data were divided into two parts from 1969 to 2007 and from 2008 to 2019 for model training and testing, respectively. The optimal ANN for forecasting ETo included Tmax, Tmin, H, and SR at hidden layers (4, 3); gradmin, SR, and WS at (6, 4); SR, day length, Ssh, and Tmean at (3, 2); all collected para...
This study compares the daily crop evapotranspiration estimated by artificial neural network (ANN), neural network-genetic algorithm (NNG), and nonlinear regression (NLR) methods. Using a 6-year (2000)(2001)(2003)(2004)(2005) daily meteorological data, recorded at Tabriz synoptic station, and Penman-Monteith FAO 56 standard approach (PMF 56), the daily crop evapotranspiration (ET C ) was determined during the growing season (April-September). Air temperature, wind speed at 2 meters height, net solar radiation, air pressure, relative humidity and crop coefficient for every day of the growing season were selected as the input of artificial neural network models. In this study, the genetic algorithm was applied for optimization of parameters which used in ANN approach. It was found that the optimization of input parameters did not improve the performance of ANN method. The results indicate that NLR, ANN and NNG methods were able to predict potato crop evapotranspiration (ET C ) at the desirable level of accuracy. However, the NLR method with highest coefficient of determination (R 2 > 0.96, P value<0.05) and minimum errors provided the superior performance among the other methods.
In the present study an attempt has been develop artificial neural network (ANN) for estimation of daily pan evaporation (Ep) for Hawalbagh, Uttarakhand, India. The daily data of temperature (T), relative humidity (Rh), wind velocity (W), sunshine hours (S) and evaporation (Ep) data of years 2010-2012 were used to train the models and remaining data of year 2013 were used for test the models of ANN. The daily meteorological data of 4 years such as temperature, relative humidity, wind velocity and sunshine hours as input parameters and evaporation as output. The artificial neural networks were used for designing of models based on different learning algorithm (DBD, L-M, Step, Momentum, C-G and Quickprop) activation function TanhAxon, sigmoid and linear sigmoid were used evaporation estimation. The performances indices of the models were evaluated by; viz. normalized mean square error (NMSE), and coefficient of efficiency (CE). The comparisons of the different combinations of ANN models and select a best suited model for estimating daily pan evaporation of the Hawalbagh Uttarakhand. Evaporation is one of the major processes in the hydrologic cycle, and its accurate estimation is essential for hydrologic water-balance, irrigation, and water resources planning and management. correlation coefficient (r) Water resources of a country constitute one of its vital assets. The evaporation process represents a major component of the energy and water balance of bare soil and green cover (i.e. forest and farm) ecosystems. Estimation of the water loss by evaporation is of primary importance for monitoring, survey and management of water resources, design of irrigation and drainage systems and irrigation scheduling (Molina Martinez et al., 2005; Gundekar et al., 2008). It is generally made by some commonly used approaches such as mass transfer or water balance methods. One of the direct methods for Ep measurements is the pan evaporation (Eslamian et al., 2008). Pan performance is affected by instrumental limits and operational problems such as human errors, instrumentation errors, turbidity of water, watering of birds or other animals, as well as other maintenance problems which can affect the accuracy of Ep measurements. Accurate estimation of evaporation is essential for the balancing of irrigation water use in arid and semiarid regions, highly conditioned by water shortages, where responsible irrigation engineering and watershed management is mandatory. It is a key factor for irrigation system design and management, crop production, environmental assessment water resources management and planning. Estimation of evaporation for remote rural areas where no evaporation data are available is of great attention to the hydrologists and meteorologists (Kisi 2006). The most important factors affecting evapotranspiration are solar radiation, air temperature, air humidity and wind speed, vapour pressure deficit (Allen et al., 1998). Sudheer et al. (2002) showed that the neural computing technique could be employed successfully in modelling the evaporation process from the available climatic data set. Evaporation estimation by multilayer perceptron based artificial neural network and multiple linear regression techniques (Bhagwat et al., 2017). However, an analysis of the residuals from the ANN models developed revealed that the models showed significant error in predictions during the validation, implying loss of generalization of ANN models unless trained carefully. Recent experiment have reported that ANN may offer a promising alternative in the hydrological context developed feed forward ANN models for modelling daily evaporation and found that the ANN model performed better the conventional method. An attempt has been made to develop models for computation of evaporation by the available wheatear data of Hawalbagh. The objectives to develop the ANN based evaporation estimation models with different learning algorithms and to evaluate performance and adequacy of the developed models.
Theoretical and Applied Climatology
Evapotranspiration (ET) is a main factor of the hydrologic balance. Estimating precise ET is necessary for managing the water supply in a basin. In this study, daily barley standard evapotranspiration (DBSE) is obtained (1) directly by weighing lysimeter and (2) indirect methods. In the first step, DBSE was obtained by two weighing lysimeters in a semi-arid region (Kooshkak, Iran). In the next step, indirect methods for estimating the DBSE, the Penman–Monteith (PM), and the artificial neural networks (ANNs), including the radial basis functions (RBF), and the multi-layer perceptron (MLP), were utilized. Results showed that DBSE can be successfully calculated in semi-arid region by MLP-ANN, RBF-ANN, and PM methods. The ANN methods were offered as the best method because they need fewer input data and can be easily used for other developed programs that applied for water allocation and therefore solve the conflicts between stakeholders and optimize water usage. Finally, the sensitivity of ANNs to input data was investigated by relating changes in the daily metrological data to the dimensionless scaled sensitivities (DSS) index. Results showed that in the multi-layer perceptron, ET c was more sensitive to sunshine hours and less sensitive to wind speed and the radial basic function has different patterns which are more sensitive to sunshine hours. When the sunshine hours decrease by more than 10%, the standard crop evapotranspiration (ET c ) was more sensitive to average humidity and less sensitive to wind speed.
International Journal of Scientific & Technology Research, 2014
The potential of modeling the FAO Penman-Monteith (FAO-56 PM) method for computing reference crop evapotranspiration (ETo) using feed-forward backpropagation artificial neural networks (FFBANN) with minimal measured climate data such as with the air temperature (maximum and minimum) was investigated using local climatic data from the Wa Meteorological weather station. Three FFBANN models were developed and trained with the Levenberg-Marquardt algorithm and the early stopping approach. These three FFBANN models are temperaturebased models and have the same input variable as the established temperature-based empirical methods; the Hargreaves, Blaney-Criddle and the Thornthwaite methods. A comparative study was carried to see how these FFBANN models performed relative to the other three established temperature-based empirical methods using the FAO-56 PM method as the benchmark. In general, the FFBANN models outperformed these established methods in estimating the ETo and should be pref...
International Journal of Engineering Sciences & Research Technology, 2014
A feature based Artificial Neural Network (ANN) model was developed for prediction of Evapotranspiration (ET) of eucalyptus. Six weather parameters namely maximum temperatures, minimum temperature, relative humidity first, relative humidity second, wind velocity and sunshine hour were used by the ANN model. The network was trained using the pattern matching capability of artificial neural network to recognize the pattern of daily metrological data. Results of ANN model training, testing and validation by back propagation technique were observed to be in good agreement with those of measured ET by lysimeter of eucalyptus plant. Correlation coefficient (r2) between measured and predicted ET during training phase were found 0.9810, during testing phase 0.8770 and during validating phase 0.9010.
Artificial neural networks application to predict wheat yield using climatic data
… International Conference on …, 2004
Prediction of crop yield mainly strategic plants such as, wheat, corn and rice has since long been an interesting research area to agrometeorologists, as it is important in national and international economic programming. The main purpose of such studies is to estimate the crop production a few days or months before harvesting, using meteorological data. Recently, the application of Artificial Neural Networks (ANNs) has developed into a powerful tool that can compute most complicated equations and numerical analyses to the best approximation. The goal * of this study was to apply the ANNs to predict dry farming wheat yield. According to the available data and information from different areas in Iran, this research was accomplished using Sararood station data in Kermanshah Province which has the most complete homogeneous statistics. In this study, the results of climatology for the period (1990-99) for each of the eleven phenological stages of wheat including sowing, germination, emergence, third leaves, tillerng, stem formation, heading, flowering, milk maturity, wax maturity, full maturity and also eleven meteorological factors including: mean daily minimum temperature, extreme daily minimum temperature, mean daily maximum temperature, extreme daily maximum temperature, total daily rainfall, number of rainfall days, sum of sun hours, mean daily wind speed, extreme daily wind speed, mean daily relative humidity and sum of water requirement were collected separately for each farming year and arranged in two matrices: A matrix whose rows are repetitions of the statistical years (i) at each phenological stages of wheat (j) and the columns are meteorological factors (k). A matrix whose rows form each of the statistical years (i) and the columns are meteorological factors (k) at each phenological stage (j).
Estimation of soil moisture in paddy field using Artificial Neural Networks
International Journal of Advanced Research in Artificial Intelligence, 2012
In paddy field, monitoring soil moisture is required for irrigation scheduling and water resource allocation, management and planning. The current study proposes an Artificial Neural Networks (ANN) model to estimate soil moisture in paddy field with limited meteorological data. Dynamic of ANN model was adopted to estimate soil moisture with the inputs of reference evapotranspiration (ET o ) and precipitation. ET o was firstly estimated using the maximum, average and minimum values of air temperature as the inputs of model. The models were performed under different weather conditions between the two paddy cultivation periods. Training process of model was carried out using the observation data in the first period, while validation process was conducted based on the observation data in the second period. Dynamic of ANN model estimated soil moisture with R 2 values of 0.80 and 0.73 for training and validation processes, respectively, indicated that tight linear correlations between observed and estimated values of soil moisture were observed. Thus, the ANN model reliably estimates soil moisture with limited meteorological data.
In the present study, an attempt has been made to compare the reference evapotranspiration (ET o), computed by eight different methods, namely, Penman-Monteith, Modified Penman-Monteith, Hargreaves-Samani, Irmak, Hargreaves, Valiantzas, ANN and FAO(24) model for the dry sub-humid agro-ecological region (Varanasi). An attempt was also made to find out utility of artificial neural networks (ANN) for estimation of ET 0 with minimum input. Feed forward network has been used for prediction of ETo using resilient back-propagation method and the architecture 2-2-1(having parameters T mean and solar radiation) was found to be the best one. The average annual evapotranspiration (by Penman–Monteith method) for Varanasi was found to be 1447.4 mm. When compared among the different methods for estimation of reference evapotranspiration with Penman-Monteith method, the FAO-24 and Hargraves-Samani (3) under estimate, however, Modified Penman-Monteith, Hargreaves-Samani, Irmak, Hargreaves, Valiantzas overestimate and ANN closely estimates reference evapotranspiration.