A. Mosaedi; S. Mohammadi Moghaddam; M. Ghabaei Sough
Abstract
Introduction: Weather features and their variations have an important role in the yield of agricultural products, especially in rain-fed conditions. The main metrological variables that affected yields consist of precipitation, temperature, soil moisture and solar radiation. Also, drought is one of the ...
Read More
Introduction: Weather features and their variations have an important role in the yield of agricultural products, especially in rain-fed conditions. The main metrological variables that affected yields consist of precipitation, temperature, soil moisture and solar radiation. Also, drought is one of the major constraints to production, especially the mid-season drought which occurs during the podand seed formation stages and the terminal drought which occurs during the pod filling stage. The results of investigating the relation between drought indices such as Standardized Precipitation Index (SPI), Palmer Drought Severity Index (PDSI), Crop Moisture index (CMI) and Z index with crop yields indicated the capability of these indices to estimate variations in crop yields. The objective of this study in the first step is investigation of relations among wheat and barley crop yields with climatic variables and SPI and RDI drought indices based on Principle Component Analysis (PCA) method at Bojnourd, Mashhad and Birjand stations. In addition, by selecting the prominent variables via PCA method, the best models of estimating each crop’s yield based on multivariate regression methods at selected stations were determined.
Materials and Methods: In this study, the relationship between yields of rain-fed wheat and barley with weather variables consisting of minimum, mean and maximum temperature, precipitation, evapotranspiration and drought indices including SPI and RDI were investigated and modeled at Bojnourd, Mashhad and Birjand stations. For this purpose, the values of each variable were calculated for 34 time scales of 1, 2, 3, 4, 6, and 9 months and wet periods (nine 1-month periods, eight 2- month periods, seven 3- month periods, six 4- month periods, two 6- month periods, one wet period (5 or 7-month) and one 9-month period). After that, the main influencing variables were chosen among investigated time periods for each variable by using the method of principal component analysis (PCA). In continuation, the selected variables via PCA technique were used in the multivariate regression methods to create the best model of predicting wheat and barley yields based on each mentioned variable and combination of them. The performance of the established model was evaluated based on Ideal Point Error (IPE) criteria and the best predicting model of wheat and barley was selected for each region.
Results and Discussion: The results showed that applying PCA technique as a powerful statistical tool leads to decrease of the error and inflation of constructed models. This is done by reducing the volume of data and selecting influencing variables. Based on the PCA results by choosing only four components the 90 percent and greater than variation of crop yields are estimated and the first component includes time periods of spring and winter months. Investigation of the results of the best model at the given stations based on IPE criteria show that the constructed models based on variables of SPI index have more accuracy for predicting yields of wheat and barley at station of Bojnourd, at Mashhad station the created models based on a combination of variables and at Birjand station a model based on a combination of variables and a created model according to RDI variables was used that has more accuracy for predicting yields of wheat and barley, respectively. Comparing the estimated and actual values of wheat and barley yields indicate that the correlation coefficients of the models when applied to estimate the yield of wheat and barley at Bojnourd station resulted in 68 and 69 percent, at Mashhad station 89 and 86 percent and at Birjand station 66 and 74 percent, respectively.The performance evaluation graph shown in Fig. 1 can be used to illustrate model performance and to diagnose model bias.
Conclusion: According to the results, a relation between crop yields and combination of metrological variables and drought indices is more positive and stronger than only metrological variables combination. The results showed that the variables of temperature, precipitation and evapotranspiration are to be considered. Also, the evaluation model indicated that the RDI index is more suitable for predicting rain-fed wheat and barley yields.
H. Mir; Ahmad Gholamalizadeh Ahangar; A. Shabani
Abstract
Introduction: Phosphorus is important as an essential element in the production of agricultural products. On the other hand, its ability to induce essential micronutrient deficiency and its negative effects on the environment, have attracted more attention to this element. The knowledge of phosphorus ...
Read More
Introduction: Phosphorus is important as an essential element in the production of agricultural products. On the other hand, its ability to induce essential micronutrient deficiency and its negative effects on the environment, have attracted more attention to this element. The knowledge of phosphorus availability conditions in the soil and consequently the accurate management of fertilizer consumption has a key role in the environmental protection. The degree of phosphorus absorption in the soil depends on the environmental factors, soil characteristics and compositions, and phosphorus fertilizer which have been used. The amount of available phosphorus in the soil has relationship with some of the physical and chemical properties of the soil. Since, the soil characteristics are important factors in the reaction of phosphorus in the soil, the present study aimed to investigate and determine the most important soil characteristics affecting the availability of phosphorus using regression and artificial neural network techniques, in the soils of Sistan plain.
Materials and Methods: Soil sampling was done in 1.5×1.5 km intervals, from 0-30 cm depth, and 200 soil samples were taken. The amounts of available phosphorus and the soil properties including the percentages of clay , organic matter, calcium carbonate and the amount of pH were measured. Then, stepwise multivariate linear regression analysis was performed to determine linear relation between available phosphorus and the soil properties. In order to model and validate the regression model, respectively 80 and 20% of data were selected and entered into SPSS software. To train the neural network, multilayer perceptron (MLP) network was used by MATLAB 7.6 package. In this type of network, 70% of data is selected for training, 15% for validation and 15% for testing the model. Levenberg-Marquardt algorithm and hyperbolic tangent (as a transfer function) were used to train the network. The numbers of neurons in the hidden layer were calculated based on the trial and error method and finally the best structure was selected according to the highest R2 and the lowest RMSE value. Moreover, quantifying the importance of variables in the neural network was done through employing connection weight approach. In this method, the connection weights of input-hidden and hidden-output neurons were used to indicate the significance of variables.
Results and Discussion: The values of the coefficient of variation for the soil properties were in the range of 5.66 for pH (the lowest) and 69.90 for available phosphorus (the highest). The high variation of the available phosphorus could be due to the different amounts of phosphorus fertilizers consumption and their diverse rate of conversion to less soluble forms. The validation results of regression and neural network methods showed that the latter technique was more accurate compared with the multivariate linear regression method, in the estimation of available phosphorus, as multi-layer perceptron neural network with 4-6-1 layout predicts nearly 90% of available phosphorus variability using soil properties (percentage of clay, organic matter, calcium carbonate and the amount of pH); however, the obtained regression equation could explain only 43% of phosphorus variances. The reasons for this could be: 1) considering nonlinear relations between the variables in the artificial neural network method, and 2) less sensitivity of this method to the existence of error in input data, comparing with the regression method. The values of R2 and RMSE were 0.43 and 11.23, respectively for training the multivariate linear regression method and 0.91 and 4.28, respectively for training the artificial neural network method. From the investigated soil properties in the current study, the percentage of organic matter and clay were entered in the regression model, and the values of standardized regression coefficient (beta) showed that the first variable is more important to explain the available phosphorus variability. The results of quantifying the importance of variables by the connection weight method showed that pH had the greatest contribution in the variability of phosphorus in the study area. In the other words, the high values of pH were the most important limiting factor for the availability of phosphorus in Sistan soils.
Conclusion: Considering nonlinear and complicated relations between variables, the artificial neural network model is an effective tool to assess the effect of soil properties on the availability of phosphorus in the study area. The results of quantifying the importance of variables by using the connection weight method showed that pH had the greatest contribution in the variability of phosphorus in the study area. In fact, the existence of lime in the soils of the study area, arid climate and lack of precipitation have resulted in the accumulation of basic cations in the soil and consequently increased pH values. Furthermore, the observed average values of pH that are more than 8.5 demonstrated the risk of soil sodicity in the study area. Thus, the management of this area by cultivating tolerant plants could be resulted in increasing organic matter content, which along with using chemical amendments such as sulfur will decrease pH values and increase the availability of phosphorus in Sistan plain. Applying such practices and through it modifying soil characteristics, decreasing the consumption of phosphate fertilizers and preventing their hazardous environmental effects would be expected in long run.
