Document Type : Original Article


1 Department of Biosystems Engineering University of Tabriz, Iran

2 Department of Biosystems Engineering, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

3 Department of Water Engineering, Faculty of Agriculture, Ferdowsi University of Mashhad

4 Department of Biosystems Engineering, Ferdowsi University of Mashhad, Mashhad, Iran


The aim of this study was to determine the probability of working days (PWD) for tillage operation using weather data with Multiple Linear Regression (MLR) and Radial Basis Function (RBF) artificial networks. In both models, seven variables were considered as input parameters, namely minimum, average and maximum temperature, relative humidity, rainfall, wind speed, and evaporation on a daily basis. The PWD was considered to be the output of the developed models. Performance criteria were RMSE, MAPE, and R2. Results showed that the R2-valuewas 0.78 and 0.99 for MLR and RBF models, respectively. Both models had acceptable performance, but the RBF model was more accurate than the MLR model. The RMSE and MAPE values for the RBF model were lower than those for the MLR model. Thus, the RBF model was selected as the suitable model for predicting PWD. Moreover, the results of these models were compared to the prior soil moisture model. It was indicated that the results of the studied models had a good agreement with the results of the soil moisture model. However, the RBF model had the highest R2 (99%). In conclusion, the developed RBF model could be used to predict the probability of working days in terms of agricultural management policies.

Graphical Abstract

Developing a Radial Basis Function Neural Networks to Predict the Working Days for Tillage Operation in Crop Production


  • The MLR and RBF techniques were used to determine the probability of working days of tillage operation.
  • Several scenarios were assessed to find the most effective factors to estimate PWD.
  • Results highlighted that the RBF model had the best performance.
  • The final model had six inputs including min., max and average air temperature, rainfall, wind speed, and evaporation.


Main Subjects

Ahaneku, I. E., & Onwualu, A. P. (2007). Predicting suitable field workdays for soil tillage in north central Nigeria. Nigerian Journal of Technology, 26(1), 81-90.
Allen, R.G., Pereira, L.S., Raes, D. and Smith, M. (1998). Crop Evapotranspiration-Guidelines for Computing Crop Water Requirements. FAO Irrigation and drainage paper 56. United Nations Food and Agriculture Organization, Rome.
Ardabili, S. F., Mahmoudi, A., & Gundoshmian, T. M. (2016). Modeling and simulation controlling system of HVAC using fuzzy and predictive (radial basis function, RBF) controllers. Journal of Building Engineering, 6, 301-308.
American Society of Agricultural Engineers (2000). Agricultural Machinery Management Data. ASAE D497.4 MAR99. 2950 Niles Rd., St. Joseph, MI 49085-9659, USA ph. 616-429-0300, fax 616-429-3852, ASAE-The Society for Engineering in Agricultural, Food, And Biological Systems.
Ataíde, L. T., Caramori, P. H. da Silva Ricce, W., Silva, D. A. B., & de Souza, J. R. P. (2012). The probability of potentially useful work days during the year in Londrina Probabilidade de dias potencialmente úteis de trabalho durante o ano em Londrina. Semina: Ciências Agrárias, Londrina 33(6), 2215-2226.
Babeir, A. S., Colvin, T. S., & Marley, S. J. (1986). Predicting field tractability with a simulation model. Transactions of the ASAE, 29(6), 1520-1525.
Baier, W. (1973). Estimation of field workdays in Canada from the versatile soil moisture budget. Canadian Agricultural Engineering, 15(2), 84-87.
Bietresato, M., Calcante, A., & Mazzetto, F. (2015). A neural network approach for indirectly estimating farm tractors engine performances. Fuel, 143, 144-154.
De Toro, A. & Hansson, P. A. (2004). Analysis of field machinery performance based on daily soil workability status using discrete event simulation or on average workday probability. Agricultural Systems, 79(1), 109-129.
Elhami, B., Khanali, M., & Akram, A. (2017). Combined application of artificial neural networks and life cycle assessment in lentil farming in Iran. Information Processing in Agriculture, 4(1), 18-32.
Fang, T., & Lahdelma, R. (2016). Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system. Applied Energy, 179, 544-552.
Hayhoe, H., & Baier, W. (1974). Markov chain model for sequences of field workdays. Canadian Journal of Soil Science, 54(2),137-148.
Hwang, S. (2007). Days available for harvesting switchgrass and the cost to deliver switchgrass to a biorefinery, unpublished dissertation, Oklahoma State University, USA.
Kamali, G., Behyar, M., & Minbashian, R. (2011). Determining the date of effective weeds spraying in sugarcane fields in Haft Tappeh considering the effect of meteorological parameters. Journal of Geography and Regional Development, 8(15), 247-265(In Persian).
Kosari-Moghaddam, A., Sadrnia, H., Aghel, H., & Bannayan, M. (2015). Predicting working days for secondary tillage and planting operation in fall. Journal of Agricultural Machinery, 6(2), 537-546 (In Persian).
Kosari-Moghaddam, A., Taheri-rad, A., Rostami, M. J. K., & Esmailpour-Troujeni, M. (2016). The comparison of available working days of rice harvesting at conventional and mechanized methods in Gorgan. The 10th national congress on biosystems engineering and mechanization. Ferdowsi University of Mashhad, Mashha, Iran (In Persian).
Maran, J. P., Manikandan, S., Thirugnanasambandham, K., Nivetha, C. V., & Dinesh, R. (2013). Box–Behnken design based statistical modeling for ultrasound-assisted extraction of corn silk polysaccharide. Carbohydrate Polymers, 92(1), 604-611.
Mirzazadeh, A., Abdollahpour, S., Mahmoudi, A., & Bukat, A. (2012). Intelligent modeling of material separation in combine harvester’s thresher by ANN. International Journal of Agriculture and Crop Sciences, 4(23), 1767-1777.
Nesheli, Y. M., Beheshti, B., & Shad, M. (2012). The effect of rainfall and relative humidity for determination of working days for harvesting paddy crop on Amol Region. The 6th National Conference on New Ideas in Agriculture. Agricultural Faculty Islamic Azad University, 1- 2 March, Khorasgan Branch, Iran (In Persian).
Omrani, A., Shiekhdavoodi, M. J., & Shomeili, M. (2011). Influence of meteorological parameters on suitable workdays and timeliness cost in sugarcane harvesting operation. Journal of Life Science and Biomedicine, 2(6), 274-277.
Pakravan, M., Kavoosi Kelashemi, M., Alipour, H. (2011). Forecasting Iran’s rice imports during 2009-2013. International Journal of Agricultural Management and Development, 1(1), 39-44.
Pishgar-Komleh, S. H., Keyhani, A., Mostofi-Sarkari, M. R., & Jafari, A. (2012). Application of response surface methodology for optimization of picker-husker harvesting losses in corn seed. Iranica Journal of Energy and Environment, 3(2), 134-142.
Rohani, A., Ranjbar, I., Abbaspour-Fard, M. H., Ajabshir, Y., & Valizadeh, M. (2010). Evaluation regression techniques in prediction of tractor repair and maintenance costs. Journal of Agricultural Engineering Research, 11(3), 87-96.
Rotz, C. A., & Harrigan, T. M. (2005). Predicting suitable days for field machinery operations in a whole farm simulation. Applied Engineering in Agriculture, 21(4), 563-571.
Rostami, S., Choobin, S., Hosseinzadeh, B., Esmaeili, Z., & Zareiforoush, H. (2017). Analysis and modeling of yield, CO2 emissions, and energy for basil production in Iran using artificial neural networks. International Journal of Agricultural Management and Development, 7(1), 47-58.
Saglam, C., & Tobi, I. (2011). Distribution of tractor available workdays over the southeastern Anatolia project (GAP) area. African Journal of Agricultural Research, 6(30), 6416-6424.
Savin, L., Matić-Kekić, S., Dedović, N., Simikić, M., & Tomić, M. (2014). Profit maximisation algorithm including the loss of yield due to uncertain weather events during harvest. Biosystems Engineering, 123, 56-67.
Selirio, I., & Brown, D. (1972). Estimation of spring workdays from climatological records. Canadian Agricultural Engineering, 14(2), 79-81.
Simalenga, T. E., & Have, H. (1992). Estimation of soil tillage workdays in a semi-arid area. Journal of Agricultural Engineering Research, 51, 81-89.
Soltanali, H., Nikkhah, A., & Rohani, A. (2017). Energy audit of Iranian kiwifruit production using intelligent systems. Energy, 139, 646-654.
Tatari, M., Koochekian, A. & Mahalati, M. N. (2009). Dryland wheat yield prediction using precipitation and edaphic data by applying of regression models. Iranian Journal of Field Crops Research, 7(2), 357-365.
Wen, X. L., Wang, H. T., & Wang, H. (2012). Prediction model of flow boiling heat transfer for R407C inside horizontal smooth tubes based on RBF neural network. Procedia Engineering, 31, 233-239.
Wiljes, H. d., & Zaat, J. C. (1968). The influence of climate upon the number of weather-working hours in combine harvesting in the Netherlands. Theoretical and Applied Climatology, 16(1), 105-114.
Witney, B. (1988). Choosing and Using Farm Machines. Edinburgh, Land Technology Ltd, pp: 412.
Witney, B., Oskoui, K. E., & Speirs, R. (1982). A simulation model for predicting soil moisture status. Soil and Tillage Research, 2(1), 67-80.