Models for feature selection and efficient crop yield prediction in the groundnut production

https://doi.org/10.17221/15/2021-RAECitation:

Krithika K.M., Maheswari N., Sivagami M. (2022): Models for feature selection and efficient crop yield prediction in the groundnut production. Res. Agr. Eng., 68: 131–141.

download PDF

Tamil Nadu ranks high in groundnut production in India. The yield prediction of the crop over Tamil Nadu will be highly useful in improving the efficiency of the production. This article aims to identify an efficient machine learning model to predict the groundnut crop yield and analyse the performance of the tested models. The study used the irrigation, rainfall, area and production data as factors for the groundnut crop yield across the districts of Tamil Nadu. This article identified the best set of features for training the models and studied various prediction models to evaluate the performance on the collected data. The trained and tested data were evaluated using various performance measures. The results of the study show that LASSO and ElasticNet provide the optimal results with the lowest RMSE and RRMSE values of 491.603 and 490.931 kg·ha–1, 20.68 and 20.66%, respectively. The models showed the lowest MAE and RMAE values as well (333.154 and 331.827 kg·ha–1 and 14.53%, 14.51%, respectively) when compared to other models. The identification of the right time to sow and area to irrigate through feature selection and the prediction of the yield will improve the yield of the groundnut crops. This helps farmers to make practical decisions and reap the benefits.

References:
Basso B., Cammarano D., Carfagna E. (2013): Review of crop yield forecasting methods and early warning systems. In: Proceedings of the First Meeting of the Scientific Advisory Committee of the Global Strategy to Improve Agricultural and Rural Statistics (FAO Headquarters), July 18–19, 2013, Rome, Italy: 18–19.
 
Casanova D., Goudriaan J., Bouma J., Epema G.F. (1999): Yield gap analysis in relation to soil properties in direct-seeded flooded rice. Geoderma, 91: 191–216. https://doi.org/10.1016/S0016-7061(99)00005-1
 
Das B., Nair B., Reddy V.K., Venkatesh P. (2018): Evaluation of multiple linear, neural network and penalised regression models for prediction of rice yield based on weather parameters for west coast of India. International Journal of Biometeorology, 62: 1809–1822. https://doi.org/10.1007/s00484-018-1583-6
 
Emamgholizadeh S., Parsaeian M., Baradaran M. (2015): Seed yield prediction of sesame using artificial neural network. European Journal of Agronomy, 68: 89–96. https://doi.org/10.1016/j.eja.2015.04.010
 
Gandhi N., Armstrong L.J., Petkar O., Tripathy A.K. (2016a): Rice crop yield prediction in India using support vector machines. In: 13th International Joint Conference on Computer Science and Software Engineering (JCSSE), July 13–15, 2016, Khon Kaen, Thailand: 1–5.
 
Gandhi N., Petkar O., Armstrong L.J. (2016b): Rice crop yield prediction using artificial neural networks. In: IEEE International Conference on Technological Innovations in ICT for Agriculture and Rural Development (TIAR), July 15–16, 2016, Chennai, India: 105–110.
 
Glen S. (2015): Variance inflation factor. Available at https://www.statisticshowto.com/variance-inflation- factor/ (accessed Feb 1, 2021).
 
Gonzalez-Sanchez A., Frausto-Solis J., Ojeda-Bustamante W. (2014): Attribute selection impact on linear and nonlinear regression models for crop yield prediction. The Scientific World Journal, 2014: 1–10. https://doi.org/10.1155/2014/509429
 
Government of Tamil Nadu (2017): Report No.1 of 2017  – Economic Sector Government of Tamil Nadu [Dataset]. Available at https://cag.gov.in/webroot/uploads/download_audit_report/2017/Report_No.1_of_2017_-_Economic_Sector_Government_of_Tamil_Nadu.pdf (accessed Feb 4, 2021).
 
Haghverdi A., Washington-Allen R.A., Leib B.G. (2018): Prediction of cotton lint yield from phenology of crop indices using artificial neural networks. Computers and Electronics in Agriculture, 152: 186–197. https://doi.org/10.1016/j.compag.2018.07.021
 
Jaikla R., Auephanwiriyakul S., Jintrawet A. (2008): A rice yield prediction using a support vector regression method. In: 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, May 14–17, 2008, Krabi, Thailand: 29–32.
 
Johnson M.D., Hsieh W.W., Cannon A.J., Davidson A., Bédard F. (2016): Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods. Agricultural and Forest Meteorology, 218: 74–84. https://doi.org/10.1016/j.agrformet.2015.11.003
 
Kaul M., Hill R.L., Walthall C. (2005): Artificial neural networks for corn and soybean yield prediction. Agricultural Systems, 85: 1–18. https://doi.org/10.1016/j.agsy.2004.07.009
 
Kouadio L., Deo R.C., Byrareddy V., Adamowski J.F., Mushtaq S. (2018): Artificial intelligence approach for the prediction of Robusta coffee yield using soil fertility properties. Computers and Electronics in Agriculture, 155: 324–338. https://doi.org/10.1016/j.compag.2018.10.014
 
Kumar K.S., Sreenivasulu G. (2017): Locally received NOAA based crop yield estimation using vegetation index and atmospheric parameters for Chittoor district. International Journal of Applied Engineering Research, 12: 9688–9696.
 
Maya Gopal P.S., Bhargavi R. (2019a): A novel approach for efficient crop yield prediction. Computers and Electronics in Agriculture, 165: 1–9. https://doi.org/10.1016/j.compag.2019.104968
 
Maya Gopal P.S., Bhargavi R. (2019b): Performance evaluation of best feature subsets for crop yield prediction using machine learning algorithms. Applied Artificial Intelligence, 33: 621–642. https://doi.org/10.1080/08839514.2019.1592343
 
Meena M., Singh P.K. (2013): Crop yield forecasting using neural networks. In: International Conference on Swarm, Evolutionary, and Memetic Computing, Dec 19–21, 2013, Chennai, India: 319–331.
 
Mupangwa W., Chipindu L., Nyagumbo I., Mkuhlani S., Sisito G. (2020): Evaluating machine learning algorithms for predicting maize yield under conservation agriculture in Eastern and Southern Africa. SN Applied Science, 2: 1–14. https://doi.org/10.1007/s42452-020-2711-6
 
Pallavi K., Pallavi P., Shrilatha S., Sushma, Sowmya S. (2021): Crop yield forecasting using data mining. Global Transitions Proceedings of International Conference on Computing Systems and Applications, 2: 402–407.
 
Ramesh D., Vardhan B.V. (2015): Analysis of crop yield prediction using data mining techniques. International Journal of Research in Engineering and Technology, 4: 470–473.
 
Safa M., Samarasinghe S. (2011): Determination and modelling of energy consumption in wheat production using neural networks: A case study in Canterbury province, New Zealand. Energy, 36: 5140–5147. https://doi.org/10.1016/j.energy.2011.06.016
 
Shah V., Shah P. (2018): Groundnut crop yield prediction using machine learning techniques. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 3: 1093–1097.
 
Sharif B., Makowski D., Plauborg F., Olesen J.E. (2017): Comparison of regression techniques to predict response of oilseed rape yield to variation in climatic conditions in Denmark. European Journal of Agronomy, 82: 11–20. https://doi.org/10.1016/j.eja.2016.09.015
 
Sirsat M.S., Mendes-Moreira J., Ferreira C., Cunha M. (2019): Machine learning predictive model of grapevine yield based on agro climatic patterns. Engineering in Agriculture, Environment and Food, 12: 443–450. https://doi.org/10.1016/j.eaef.2019.07.003
 
Wallach D., Goffinet B. (1989): Mean squared error of prediction as a criterion for evaluating and comparing system models. Ecological Modelling, 44: 299–306. https://doi.org/10.1016/0304-3800(89)90035-5
 
download PDF

© 2022 Czech Academy of Agricultural Sciences | Prohlášení o přístupnosti