Predicting coffee productivity using artificial neural networks
Keywords:
Coffee, Productivity, Artificial neural networksAbstract
Coffee is a leading commodity in Indonesia as a raw material for making food, beverages, and other processed products. The demand for coffee is competitive in the international market as a source of foreign exchange for the country. Uncertain production results greatly affect production costs and impact the economy of farmers. Therefore, it is necessary to make a prediction to determine the likelihood of the development of coffee productivity in the future. This research uses data on coffee production from farmers from 2014 to 2023. The algorithm used in this research is the backpropagation artificial neural network. The backpropagation algorithm is one of the artificial neural networks that uses a systematically working multilayer that is very strong and objective through developed network architecture models so that it can make good predictions. The network architecture model used is 4 input neurons, 2 hidden neurons, and 1 output neuron. The maximum epoch value used is 1000, and the learning rate ranges from 0.1 to 0.9. The training process resulted in the best weights with an MSE value of 0.007703 at a learning rate of 0.2. Based on this research, it is expected to provide benefits for farmers as a solution, reference, and evaluation material to improve coffee productivity and minimize the budget for land and plant processing production costs in the future, as well as provide information on future harvests.
References
[1] M. Iqbal Ulumando, "Prediction of Coffee Crop Production in NTT Region Using Backpropagation," JAPPRI: Journal of Agricultural & Agrotechnology Scientific Research Publications, Vol. 4, No. 2, pp. 28–45, 2022.
[2] A. A. Suryanto and A. Muqtadir, "Application of Linear Regression to Predict Rice Production Needs," Proceedings of the National Seminar on Research Results and Community Service III PGRI Ronggolawe University Tuban, Vol. 3, pp. 331–332, 2018.
[3] M. Adi DKK., "Application of Backpropagation Algorithm in Predicting Rice Crop Production by District/City in North Sumatera," semantics, Vol. 4, No. 1, pp. 77–86, 2018.
[4] A. Wanto, "Prediction of Indonesian Corn Productivity in 2019-2020 as an Effort to Anticipate Import Using Backpropagation Artificial Neural Networks," SINTECH Journal | 53 SINTECH JOURNAL, Vol. 1, No. 1, pp. 53–62, 2019, [Online]. Available: http://jurnal.stiki-indonesia.ac.id/index.php/sintechjournal
[5] W. R. A. Situmorang and M. Jannah, "Implementation of Artificial Neural Network Predicts Rice Yield in Pagar Jati Village by Backpropagation Method," JIKOMSI [Journal of Computer Science and Information Systems], Vol. 3, No. 3, pp. 167–175, 2021.
[6] C. Oktaviani and Afdal, "Prediction of Monthly Rainfall Using Neural Networks with Multiple Backpropagation Training Functions," Unand Journal of Physics, Vol. 2, No. 4, pp. 228–237, 2013.
[7] E. P. C. Edi Ismanto, "Neural Network Backpropagation Algorithm in Predicting the Availability of Food Commodities in Riau Province," Rabit: Journal of Technology and Information Systems Univrab, Vol. 2, No. 2, pp. 196–209, August 2017, doi: 10.36341/rabit. v2i2.152.
[8] M. F. Andrijasa and D. Mistianingsih, "Application of Neural Network to Predict the Number of Unemployed in East Kalimantan Province Using Backpropagation Learning Algorithm," Journal of Informatics Mulawarman, Vol. 5, No. 1, pp. 50–54, 2010.
[9] R. S. Suhartanto, C. Dewi, and L. Muflikhah, "Implementation of Backpropagation Neural Network to Diagnose Skin Diseases in Children," Journal of Information Technology Development and Computer Science, Vol. 1, No. 7, pp. 555–562, 2017, [brave]. Available: http://j-ptiik.ub.ac.id
[10] A. Trimulya, F. Agus Setyaningsih, and J. Computer Systems, "Implementation of Neural Networks Backpropagation Method to Predict Stock Prices," Journal of Coding, Untan Computer System, Vol. 03, No. 2, pp. 66–75, 2015.
[11] W. Santoso and P. Sukmasetya, "Journal of Media Informatics Budidarma Predicting Waste Volume at Banyuurip TPSA Using Backpropagation Neural Network Method," Journal Of Media Informatics Budidarma, Vol. 7, No. 1, pp. 464–472, 2023, doi: 10.30865/mib. v7i1.5499.
[12] H. I. Fathoni, B. Rahayudi, and D. E. Ratnawati, "Prediction of Vaname Shrimp Harvest using Backpropagation Neural Network Algorithm," Journal of Information Technology Development and Computer Science, Vol. 6, No. 8, pp. 3587–3595, 2022, [Online]. Available: http://j-ptiik.ub.ac.id
[13] M. Birky Auliya Akbar and A. Afif Supianto, "Optimization of Backpropagation Method Forecasting Using Genetic Algorithm on the Number of Train Passengers in Indonesia," Journal of Information Technology Development and Computer Science, Vol. 3, No. 3, pp. 2533–2541, 2019, [Online]. Available: http://j-ptiik.ub.ac.id.
[14] G. Ramadhona, B. Darma Setiawan, and F. A. Bachtiar, "Prediction of Rice Productivity Using Backpropagation Neural Network," Journal of Information Technology Development and Computer Science, Vol. 2, No. 12, pp. 6048–6057, 2018, [Online]. Available: http://j-ptiik.ub.ac.id
