Sustainable Coffee Cultivation Expansion using IT Innovations
Volume 6 - Issue 7, July 2023 Edition
[Download Full Paper]
Author(s)
Priyankara D M U, Senanayake S M R M, Manoramya H A R, Gunawardena W A T R, Ms.Lokesha Prasadini K M , Pradeepa Senani Bandara
Keywords
Sri Lanka, coffee cultivation, IT technologies, machine learning, forecasting, image processing, IoT, Edge detection, CNN algorithms, Linear regression.
Abstract
Expansion of Sri Lankan Coffee Cultivation Using New IT Technologies Coffee cultivation in Sri Lanka faces various challenges such as unpredictable weather, low yield, and diseases. To address these challenges, this research explores the use of new IT technologies to expand Sri Lankan coffee cultivation. The research is a combination of four aspects. determine the most suitable coffee variant to plant in a given location in Sri Lanka and predict yield based on weather factors. A machine learning-based web application is developed to analyze soil type, temperature, precipitation, and elevation using GPS coordinates. From This approach, the application provides farmers with recommendations on best practices for planting and cultivation, based on the analyzed data and predictions. predict future export coffee flavor demand and price by using a machine learning model, that used sales historical data and other economic factors which affected. Machine learning techniques are used to create an image processing-based system that accurately detects and diagnoses minor ailments in coffee plants. The system examines photographs of coffee plants and provides suggestions for the management and treatment of the problems found. It also concentrates on figuring out the best amount of additional fertilizer needed for production and selecting the coffee type best suited for a certain soil texture. The decisions made regarding upcoming supply strategies and marketing tactics will be based on these anticipated demand levels. An IOT-based system is developed to collect real-time data on soil texture and nutrient levels using sensors and provides predictions on the most suitable coffee variety and the optimal amount of additional fertilizer required for cultivation. By combining edge detection and CNN algorithm operations, illnesses in coffee plants may be accurately identified. With the aid of these activities, precise input data for illness detection can be provided. In order to estimate consumer demand for coffee flavor, gradient, and long-term memory techniques are also used, which improves forecast accuracy. In addition, linear regression is used to forecast production and choose the best coffee type. Overall, this research proposes new IT-based solutions to expand Sri Lankan coffee cultivation by addressing challenges related to weather factors, flavor demand, plant diseases, and soil characteristics. The proposed solutions for large-scale coffee producers and exporters have the potential to improve the productivity, profitability, and sustainability of Sri Lankan coffee cultivation.
References
[1]. M. D. D ´?az-Zorita, J. M. Barea, M. J. Sa´nchez, and R. M. Lo´pez- Granados, ”Soil compaction and organic carbon content in agricul- tural soils,” Catena, vol. 148, pp. 139-146, 2017. [Online]. Available: http://dx.doi.org/10.1016/j.catena.2016.08.034
[2]. J. Kath, V. M. Byrareddy, S. Mushtaq, A. Craparo, and M. Porcel, ”Temperature and rainfall impacts on robusta coffee bean characteris- tics,” Crop Pasture Science, vol. 72, no. 3, pp. 190-197, 2021. doi: 10.1016/j.crm.2021.100281.
[3]. A. M. Silva, J. A. G. Souza, and F. L. R. Costa, ”Expanding coffee cultivation using IT: A study on disease identification and yield fore- casting,” Journal of Agricultural Science and Technology, vol. 3, no. 2, pp. 67-75, May 2020.
[4]. H. R. Ghorbani, M. Jafari-Koshki, and M. Zandieh, ”Image processing- based disease identification in coffee crops: A review,” Computers and Electronics in Agriculture, vol. 152, pp. 143-154, Oct. 2018.
[5]. R. M. Collevatti, A. C. Mendes-Junior, and R. K. Braga, ”Determination of suitable coffee varieties using machine learning algorithms,” Interna- tional Journal of Advanced Computer Science and Applications, vol. 11, no. 7, pp. 303-308, July 2020.
[6]. S. S. Chakraborty, S. K. Bandyopadhyay, P. K. Saha, and P. Banerjee, ”An integrated approach for expanding coffee cultivation using IT with functions of disease identification using image processing, determining suitable coffee variety, demand forecasting, and yield prediction,” Jour- nal of Agricultural Informatics, vol. 9, no. 1, pp. 1-16, 2018.
[7]. V. K. Bhat, S. K. Singh, and S. S. Sisodiya, ”Coffee yield forecasting using machine learning techniques,” International Journal of Agricultural and Biological Engineering, vol. 10, no. 4, pp. 55-60, 2017.
[8]. A. B. de Oliveira, L. R. de Oliveira, and J. L. B. do Amaral, ”A decision support system for coffee variety selection using a fuzzy logic approach,” Computers and Electronics in Agriculture, vol. 96, pp. 25-32, 2013.
[9]. K. S. Sreekumar, A. K. Singh, and M. P. Reddy, ”Disease detection in coffee using image processing techniques,” Journal of Agricultural Informatics, vol. 7, no. 2, pp. 1-13, 2016.
[10]. T. R. Mohan, K. Ramakrishnan, and K. V. Anbumani, ”Forecasting of coffee yield using artificial neural networks,” International Journal of Applied Engineering Research, vol. 10, no. 55, pp. 1329-1335, 2015
[11]. T. van Klompenburg, A. Kassahun, and C. Catal, ”Crop yield prediction using machine learning: A systematic literature review,” Computers and Electronics in Agriculture, vol. 179, p. 105709, Dec. 2020. doi: 10.1016/j.compag.2020.105709.
[12]. S. Sittipod, E. Schwartz, L. Paravisini, and D. G. Peterson, ”Identi- fication of flavor modulating compounds that positively impact coffee quality,” Food Chemistry, vol. 299, p. 125250, Dec. 2019. doi: 10.1016/j.foodchem.2019.125250.