Modeling the relationship between iron concentration in citrus leaves and some soil properties using artificial neural network (case study of southern Kerman province)

Document Type : Research Paper

Authors

1 Faculty Members of Soil and Water Research Department, South Kerman Agricultural and Natural Resources Research and Education Center, AREEO, Jiroft, Iran.

2 Faculty Members of Soil and Water Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran

3 Faculty Members of Soil and Water Research Department, South Kerman Agricultural and Natural Resources Research and Education Center, AREEO, Jiroft, Iran

4 Soil and Water Research Department, South Kerman Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Jiroft, Iran

Abstract

This study was conducted to evaluate the relationship between leaf iron and some easily-available soil properties in citrus orchards in the southern region of Kerman province by artificial neural network modeling and stepwise regression. For this purpose, 40 orchards were selected from the study area and the physical and chemical properties of soil and iron in the plant leaves were measured. Using artificial neural network in different models with different data from soil properties as input and leaf iron as output, the ability of these models to predict leaf iron concentration was evaluated. The results showed artificial neural network with variables of organic carbon, pH, clay, phosphorus, TNV and electrical conductivity with explanation coefficient of 0.86 and 0.81 and root mean square error (RMSE) of 14.60 and 20.13 mg.kg-1 for data Training and testing were the best models in estimating leaf iron. Comparison of regression and neural network models in the test data showed that the neural network had a higher accuracy with an explanation coefficient of 0.81 than stepwise regression with an explanation coefficient of 0.2. The amount of RMSE in the neural network also improved and increased from 27.72 mg.kg-1 in the stepwise regression model to 20.13 mg.kg-1 in the neural network. Artificial neural networks have been able to predict the iron in plant leaves based on the easily-available properties of the soil, so that by choosing organic carbon as the input of the first model to the best model by selecting organic carbon, pH, clay, phosphorus, TNV and electrical conductivity, model accuracy increased.

Keywords

Main Subjects


Modeling the Relationship between Iron Concentration in Citrus Leaves and Some Soil Properties Using Artificial Neural Network (Case Study of Southern Kerman Province)

EXTENDED ABSTRACT

Introduction

Studying the relationships between the chemical and physical characteristics of a plant's growing environment and the uptake of required elements by the plant can lead to better knowledge and design of the growing environment in that plant. Therefore, statistical and mathematical tools such as linear regression, logistic regression, and their combined models can be used in this direction. In recent years, the use of the artificial neural network (ANN) in predicting and modeling the nonlinear relationships of various phenomena that have great complexity, and the usual linear models and statistical analyzes that are unable to explain the relationships has expanded. The purpose of this study was conducted to evaluate the relationship between leaf iron and some easily-available soil properties in citrus orchards in the southern region of Kerman province by artificial neural network modeling and stepwise regression.

Materials and methods

The studied area is the south of Kerman province and includes seven cities: Jiroft, Kohnouj, Anbarabad, Manojan, Rudbar Janub, Ghaleganj and Faryab. To conduct this research, 40 orchards were selected from the study area and the physical and chemical properties of soil and iron in the plant leaves were measured. To model the relationship between iron concentration in leaves and some soil characteristics, stepwise regression and artificial neural network methods were used. To model the artificial neural network, MATLAB software, multilayer perceptron neural network, and backpropagation learning algorithm were used. using artificial neural networks in different models with different data from soil properties as input and leaf iron as output, the ability of these models to predict leaf iron concentration was evaluated and compared with the stepwise regression model.

Results and Discussion

The results of the regression model showed that soil organic carbon with a coefficient of 116.79 was the most and the only effective factor in the estimation of leaf iron, and the rest of the independent variables in the model did not affect the estimation of leaf iron. Most of the soils of citrus orchards in the region had low organic matter. The modeling results showed that in the ANN 1 model, with the selection of organic carbon as the only model input and the number of 10 neurons in the middle layer, the value of the regression coefficients was 0.33 and 0.32 for the training and test data, which had a better performance than the same model in stepwise regression. In the ANN 2 model, by adding the pH variable as an input, the prediction accuracy (regression coefficient) increased and reached 0.50 and 0.47 for the training and test data. Further, by adding the number of input variables in the ANN 3, ANN 4, and ANN 5 models, the relative improvement of the regression coefficients and error in the training and test data was achieved. The best result in the estimation of leaf iron was obtained in the ANN 6 model. The artificial neural network with variables of organic carbon, pH, clay, phosphorus, TNV, and electrical conductivity with regression coefficients of 0.86 and 0.81 and root mean square error (RMSE) of 14.60 and 20.13 mg/kg for data Training and testing were the best models in estimating leaf iron. The results of the neural network showed that the most important soil characteristic affecting iron absorption and concentration in plant leaves was organic carbon, followed by pH, and after these two variables, the most important characteristics in order of importance were phosphorus, and electrical conductivity. Comparison of regression and neural network models in the test data showed that the neural network had a higher accuracy with a regression coefficient of 0.81 than stepwise regression with a regression coefficient of 0.2. The amount of RMSE in the neural network also improved and increased from 27.72 mg.kg-1 in the stepwise regression model to 20.13 mg.kg-1 in the neural network.

Conclusion

The results of modeling using two methods of regression and an artificial neural network showed that the iron in plant leaves was most closely related to the amount of organic matter and soil pH. Artificial neural networks have been able to predict the iron in plant leaves based on the easily-available properties of the soil so by choosing organic carbon as the input of the first model to the best model by selecting organic carbon, pH, clay, phosphorus, TNV, and electrical conductivity, model accuracy increased.

Abrougui, K., Gabsi, K., Mercatoris, B., Khemis, C., Amami, R., & Chehaibi, S. (2019). Prediction of organic potato yield using tillage systems and soil properties by artificial neural network (ANN) and multiple linear regressions (MLR). Soil and Tillage Research, 190, 202-208. https://doi.org/https://doi.org/10.1016/j.still.2019.01.011
Ahmad, N., Hussain, S., Ali, M. A., Minhas, A., Waheed, W., Danish, S., Fahad, S., Ghafoor, U., Baig, K. S., Sultan, H., Hussain, M. I., Ansari, M. J., Marfo, T. D., & Datta, R. (2022). Correlation of Soil Characteristics and Citrus Leaf Nutrients Contents in Current Scenario of Layyah District. Horticulturae, 8(1), 61. https://doi.org/https://doi.org/10.3390/horticulturae8010061
Ajili Lahiji, A., Mohammadi Torkashvand, A., Mehnatkesh, A., & Navidi, M. (2020). Determination of the Most Important Factors Affecting Yield of Olive (Olea europaea L. ) Orchards in the North of Iran. Journal Of Horticulture Science (Agricultural Sciences And Technology), 33(4 ), 743-755. https://doi.org/https://doi.org/10.1080/01904169109364237 (In Persian)
Allison, L., & Richards, L. (1954). Diagnosis and improvement of saline and alkali soils. Soil and Water Conservative Research Branch, Agricultural Research Service.
Alva, A., & Syvertsen, J. (1991). Irrigation water salinity affects soil nutrient distribution, root density, and leaf nutrient levels of citrus under drip fertigation. Journal of plant nutrition, 14(7), 715-727.
Basirat, M., Haghighatnia, H., & Mousavi, S. M. (2018). Evaluationand Determinationthe Nutritional Status of Valencia Orange Orchards in South of Fars Province. Water and Soil, 32(1), 143-154. https://doi.org/10.22067/jsw.v32i1.67597
Cheng, J., Ding, C., Li, X., Zhang, T., & Wang, X. (2016). Soil quality evaluation for navel orange production systems in central subtropical China. Soil and Tillage Research, 155, 225-232. https://doi.org/https://doi.org/10.1016/j.still.2015.08.015
Dayhoff, J. E., & DeLeo, J. M. (2001). Artificial neural networks: opening the black box. Cancer: Interdisciplinary International Journal of the American Cancer Society, 91(S8), 1615-1635. https://doi.org/https://doi.org/10.1002/1097-0142(20010415)91:8+%3C1615::AID-CNCR1175%3E3.0.CO;2-L
Dhaliwal, S. S., Naresh, R. K., Mandal, A., Singh, R., & Dhaliwal, M. K. (2019). Dynamics and transformations of micronutrients in agricultural soils as influenced by organic matter build-up: A review. Environmental and Sustainability Indicators, 1-2, 100007. https://doi.org/https://doi.org/10.1016/j.indic.2019.100007
Gonzalez-Fernandez, I., Iglesias-Otero, M., Esteki, M., Moldes, O., Mejuto, J., & Simal-Gandara, J. (2019). A critical review on the use of artificial neural networks in olive oil production, characterization and authentication. Critical reviews in food science and nutrition, 59(12), 1913-1926. https://doi.org/https://doi.org/10.1080/10408398.2018.1433628
Hosseinifard, S. J., Shirani, H., & Hashemipour, H. (2019). Modeling the relationship between cadmium and some soil physical and chemical properties in pistachio orchards using regression and artificial neural network [(In Persian)]. Environmental Sciences, 17(3), 177-188. https://doi.org/https://doi.org/10.29252/envs.17.3.177 (In Persian)
Jamshidi, S., Yadollahi, A., Ahmadi, H., Arab, M. M., & Eftekhari, M. (2016). Predicting In vitro Culture Medium Macro-Nutrients Composition for Pear Rootstocks Using Regression Analysis and Neural Network Models [Methods]. Frontiers in Plant Science, 7. https://doi.org/10.3389/fpls.2016.00274
Kalra, Y. (1997). Handbook of reference methods for plant analysis. CRC press.
Khalid, R., Mahmood, T., Bibi, R., Siddique, M. T., Alvi, S., & Naz, S. Y. (2012). Distribution and indexation of plant available nutrients of rainfed calcareous soils of Pakistan. Soil and Environment, 31(2), 146-151.
Li, Y., Han, M.-Q., Lin, F., Ten, Y., Lin, J., Zhu, D.-H., Guo, P., Weng, Y., & Chen, L.-S. (2015). Soil chemical properties,'Guanximiyou'pummelo leaf mineral nutrient status and fruit quality in the southern region of Fujian province, China. Journal of soil science and plant nutrition, 15(3), 615-628. https://doi.org/http://dx.doi.org/10.4067/S0718-95162015005000029
Mathan, K., & Amberger, A. (1977). Influence of iron on the uptake of phosphorus by maize. Plant and Soil, 46(2), 413-422. https://doi.org/https://doi.org/10.1007/BF00010097
Minasny, B., & McBratney, A. B. (2002). The neuro‐m method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal, 66(2), 352-361. https://doi.org/https://doi.org/10.2136/sssaj2002.3520
Mirsoleimani, A., Amin, H., & Najafi Ghiri, M. (2019). Investigating the Relationship of Soil Properties and Leaf Element Concentration with Qualitative Characteristics of the Washington Navel Orange Fruit in Darab Region, Fars province [(In Persian)] [Research]. Journal of Crop Production and Processing, 9(2), 157-171. https://doi.org/10.29252/jcpp.9.2.157 (In Persian)
Moradi, B., & Ebadi, H. (2011). Investigation of quantitative and qualitative characteristics of Thomson Navel orange on Citrumelo rootstock as affected by potassium and supplementary irrigation [(In Persian)]. Journal of Plant Production (Journal of Agricultural Sciences and Natural Resources), 18(3), 47-62. https://doi.org/https://dorl.net/dor/20.1001.1.23222050.1390.18.3.4.7 (In Persian)
Nelson, D. a., & Sommers, L. E. (1983). Total carbon, organic carbon, and organic matter. In Methods of soil analysis: Part 2 chemical and microbiological properties (Vol. 9, pp. 539-579).
Olsen, S. R. (1954). Estimation of available phosphorus in soils by extraction with sodium bicarbonate. US Department of Agriculture.
Prasad, V., & Gupta, S. D. (2008). Applications and potentials of artificial neural networks in plant tissue culture. In Plant tissue culture engineering (pp. 47-67). Springer.
Roustaei, F., Ayoubi, S., & Norouzi Masir, M. (2018). Comparison of artificial neural network and multiple linear regressions efficiency for predicting soil salinity in Yazd -Ardakan plain, central Iran. Desert Ecosystem Engineering Journal, 1(1), 11-20. https://doi.org/10.22052/jdee.2017.62315
Rowell, D. L. (2014). Soil Science: Methods & Applications (1st ed.). Routledge, University of Reading, London. https://doi.org/https://doi.org/10.4324/9781315844855
Sarhadi-Sardoui, J., Ronaghi, A., Maftoun, M., & Karimian, N. (2003). Growth and chemical composition of corn in three calcareous sandy soils of Iran as affected by applied phosphorus and manure. Journal of Agricultural Science 5, 77-84.
Sarhadi, J., heidari, s., & Sharif, M. (2020). The effect of organic, chemical fertilizer and superabsorbant on nutritional status of sure orange rootstock (Citrus aurantium) [(In Persian)]. Horticultural Plants Nutrition, 2(2), 198-212. https://doi.org/10.22070/hpn.2020.4840.1047 (In Persian)
Shirdeli, A., & Tavassoli, A. (2015). Predicting yield and water use efficiency in saffron using models of artificial neural network based on climate factors and water [(In Persian)]. Saffron agronomy and technology, 3(2), 121-131. https://doi.org/https://doi.org/10.22048/jsat.2015.10381 (In Persian)
Srivastava, A., & Singh, S. (2004). Leaf and soil nutrient guide in citrus–A review. Agricultural Reviews, 25(4), 235-251.
Srivastava, A., & Singh, S. (2005). Soil and plant nutritional constraints contributing to citrus decline in Marathwada region, India. Communications in soil science and plant analysis, 35(18), 2537-2550. https://doi.org/https://doi.org/10.1081/LCSS-200030359
Torkashvand, A. M., Ahmadipour, A., & Mousavi Khaneghah, A. (2020). Estimation of kiwifruit yield by leaf nutrients concentration and artificial neural network. The Journal of Agricultural Science, 158(3), 185-193. https://doi.org/10.1017/S002185962000043X
Wang, L., Qi, G., Fu, Q., & Liu, Y. (2006). Soybean Yield Forecast Application Based on HOPFIELD ANN Model. The Journal of American Science, 2(3), 85-89.
Wiseman, C., & Püttmann, W. (2005). Soil organic carbon and its sorptive preservation in central Germany. European Journal of Soil Science, 56(1), 65-76. https://doi.org/https://doi.org/10.1111/j.1351-0754.2004.00655.x