Assessment of Summe Savory (satureja hortensis L.) Biomass by Easily-Attainable Soil Parameters and Artificial Network

علوم باغبانی

Article 4, Volume 31, Issue 3, September 2017, Pages 448-456   

Document Type: Research Article

DOI: 10.22067/jhorts4.v31i3.33666

Authors

Hossein Sabourifard^{* 1}; Azim Ghaesmnezhad¹; Khodayar Hemmati¹; Aboutaleb Hezarjaribi¹; Mahmoodreza Bahrami²; Fahimeh Nosrati¹

¹Gorgan University of Agricultural Science and Natural Resources

²Ferdowsi University of Mashhad

Abstract

Introduction: One of the most important requirements in planning production and processing of medicinal plants in order to obtain high yield and high-quality is the initial assessment of the physical and chemical properties of soil, which reduces the production cost by avoiding the use of unnecessary soil analysis. Summer savory (Satureja hortensis L.) is one the most widely used medicinal plants that quality index of plant is related to the quantity and the constituent of its essential oil content. Understanding the relations between the quantity and quality of medicinal plants with the very physical and chemical properties of soil is very complex and the estimation of parameters changes of medicinal plants affect by soil quality characteristics is more difficult. Today, with the arrival of multivariable regression models and artificial lattice models in the research, many complex relationships found in nature is understandable. Hence the need for estimation the biomass yield of savory using fast, cheap and with acceptable accuracy is feeling.
Materials and Methods: The present study was performed at the Agricultural Research Station Neyshabur as pot experiment based on a completely randomized design with three replications. Around 53 soil samples were collected from different parts of Neyshabur city, and soil texture, organic matter, pH, salinity, phosphorus, potassium, nitrogen and carbon content were selected as the easily available parameters. Before planting the parameters were measured in laboratory. Approximately 90 days after planting seeds in pots containing soil samples, the sampling of plants was done based on the treatments. For drying, samples were placed for 24 hours in an oven at 40 °C. Finally, the relationship between the biomass yield and easily available soil parameters was determined using artificial neural network by Matlab7.9 software.
Results and Discussion: The results showed that soil variability, is a key element in the management of valuable information on soil properties within a field and valuable information on soil properties within a field nature puts at our disposal. In yield modeling with 10 parameters for 53 soil samples, the best makeup hidden layer with Levenberg-Marquardt algorithm training as a hidden layer, 58 neurons, logsig threshold function for hidden layer and Tansig for the output layer were selected. High values of R2 and low levels of RMSE mentioned the proximity of the forecast data with measurement data and high accuracy of the model in summer savory biomass yield estimation. To obtain the most sensitive parameters, the sensitivity analysis was calculated using no-sensitive coefficient. So that, if the coefficient of a sensitive parameter is more than 1.0, the mentioned parameter, is one of the critical parameters of model. Accordingly, the parameters of organic carbon, nitrogen, phosphorus, organic matter, potassium, pH, salinity, clay, silt and sand respectively were selected as the most sensitive parameters. The addition of input parameters increases the value of R2 and reduces the RMSE during training, validation and test stages. This represents an increasing in the accuracy of model in estimation of biomass yield via increasing the input parameters. Models 1(soil texture) and 2(carbon) are not enough strong for biomass yield estimation. With increasing the experiment from 1 to 2, the potency of the neural network model 3(soil texture + carbon) significantly increased. Thus with an overview, the model No. 3 suggested as an improved model because with the minimum number of imputes produced equal output comparing the models with more inputs.
Conclusions: Based on the obtained results, it seems that with the improvement of artificial neural network models and determining appropriate parameters, results to understanding the soil factors involved in the formation of savory plant biomass and better planning. Till leads to a cheaper and better product. Also, results showed that the artificial neural network has high accuracy in estimating the biomass plant Summer Savory. So that, the 80% of yield variability of the study area, presents by using the data of 10 readily available properties of the soil. Yield biomass of savory, largely depends on the soil texture, organic matter, carbon and the minerals of the soil. Since, this study is the first work to estimate the biomass of medicinal plants using artificial neural network, therefore recommended to use this method to estimate the yield and essential oil of other medicinal plants.

Keywords

Summer Savory; Artificial neural network; Easily accessible soil parameters

References

1- Alvarez, A. 2009. Predicting average regional yield and production of wheat in the Argentine Pampas by an artificial neural network approach. Eur J. Agron.30: 70-77.

2- Ayoubi S., Khormali F., and Sahrawat K. 2009. Relation of barley biomass and grain yields to soil properties within a field in the arid region: Use of factor analysis. Acta. Agr. Scand. 59(2):107-117.

3- Bremner J.S., and Mulvaney C.S. 1982. Nitrogen-total. In A. L. Page (Ed.), Methods of Soil Analysis, Part 2.American Society of Agronomy (pp. 595-624). Madison, Wisconsin.

4- Drummond S.T., Sudduth K.A., Joshi A., Birrell S.L., and Kitchen N.R. 2003, Statistical and Neural Methods for Site-specific Yield Prediction, Transactions of the American Society of Agricultural Engineering, 46(1):. 5-14.

5- Gee G.W., and Bauder J.W. 1986. Particle size analysis. P 383-411, In: Methods of soil analysis. Part 1. 2nd ed. Klute, A. (Ed). Agron. Monogr. 9.ASA. Madison. WI.

6- Hill M. 1998. Methods and guidelines for effective model calibration. U.S. Geological survey Water- Resources Investigations Rep. 98-4005.

7- Kaul M., Hill R.L., and Walthall C. 2005. Artificial neural networks for corn and soybean yield prediction. Agriculture Systems, 85:1-18.

8- Lobell D.B., Ortiz-Monasterio J.I., Addams C.L., and Asner G.P. 2002. Soil, climate, and management impacts on regional wheat productivity in Mexico from remote sensing. Agricultural and Forest Meteorology, 114: 31-43.

9- Menhaj M.B. 2001. Computational intelligence, fundamentals of neural networks. 2nd d., Amir Kabir University of Technology, Tehran: Iran. (in Persian (

10- Moazen zadeh R., Ghahraman B., Fathalian F., and Khoshnoodyazdi A.A.2009. Effect of type and number of input variables on moisture retention curve and saturated hydraulic conductivity prediction. J. Water and Soil. 23: 3. 57-70.(in Persian)

11- Norouzi M., 2009. Prediction of rainfed wheat yield using artificial neural network in Ardal district of Chaharmahal and Bakhtiari province. M.Sc. Thesis,Collage of iculture, Isfahan University of Technology, Isfahan, Iran, 112 p.(in Persian)

12- Omidbaigi R. 2005. Production and processing of medicinal plants Vol. 2 Astane Quds Publ. Tehran, 438p.(in Persian)

13- Rao V., and Rao H. 1996. C++ Neural networks and fuzzy logic, BPB, New Dehli, India, pp: 380-381.

14- Schaap M., and Leij F. 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil and Till Res. 47: 37-42.

15- Schaap M.G., and Bouten W. 1996. Modelling water retention curves of sandy soils using neural networks. Water Resou. Res. 32:3033-3040.

16- Smith R.C.G., Adams J., Stephens D.J. and Hick P.T. 1995. Forecasting wheat yield in a Mediterranean-type environment from the NOAA satellite. Australian Journal of Agricultural Research, 46(1): 113-125.

17- Walkley A., and Black I.A. 1934. An examination of the Degtjareff method for determining soil organic matter and a proposed modification of the chromic acid titration method. Soil Sci. 37: 29-39.

18- Wu F.Y., and Yen K. K. 1992. Application of neural network in regression analysis. Computers and Industrial Engineering. 23: 93-95.