Research Article
BibTex RIS Cite

Makine Öğrenmesi Tabanlı Tüm Avrupa için Tarımsal Ekim Planlaması

Year 2021, Issue: 21, 697 - 707, 31.01.2021
https://doi.org/10.31590/ejosat.822785

Abstract

Tarımsal ürünlerin toprak bilgisine ve fiyat tahmin bilgilerine sınırlı erişimleri nedeniyle, çiftçiler mahsullerini bölgelerindeki ortak uygulamaya göre yetiştirmektedir. Bu, tarımda sürdürülebilirliğin devam ettirilememesine ve çiftçilerin üretimi ile tüketicinin talepleri arasında bir dengesizliğe yol açmaktadır. Yukarıda belirtilen sorunları ele almak için AgriTrade adlı BİT (ICT) tabanlı bir tarımsal ürün yetiştirme planlama politikası ve sistemi öneriyoruz. AgriTrade'in temel operasyonu, öncelikle çiftçileri bir mobil uygulama kullanarak interaktif bir şekilde ekim planlamasına katılmaya teşvik etmek, ikincisi, tedarik zincirinden toplanan verileri kullanarak çiftçilere yüksek hassasiyetli fiyat ve toprak bilgisi sağlamak için makine öğrenimi algoritmalarını kullanmaktır. AgriTrade'in fizibilitesini göstermek için, Avrupa'nın son 15 yıllık domates fiyatlarını ve AB'nin en büyük domates ihracatçılarından biri olan Türkiye'deki çiftçilerin domates yetiştiriciliği istatistiklerini toplayarak bir pilot kullanım örneği gerçekleştiriyoruz. AgriTrade, AB'nin tarihi domates fiyatlarına dayalı olarak gelecekteki domates fiyatlarını tahmin ediyor. Domatesi geleneksel yöntemle pazarlamayı ve tahmine dayalı pazarlamayı karşılaştırıyoruz: Geleneksel pazarlama yöntemi, ürünü yetiştirildiğinde hemen satmak iken, tahmine dayalı pazarlama, ürünü, ürünün fiyatlarının daha yüksek olduğu tahmin edilen ana kadar depolamaktır. Sonuçlar, Türkiye'deki çiftçilerin tahmine dayalı pazarlamayı uyguladıklarında, geleneksel yolla pazarlamaya kıyasla karlarını % 9,1 civarında önemli ölçüde artırabileceklerini gösteriyor.

References

  • Deichmann, U., Goyal, A., & Mishra, D. (2016). Will digital technologies transform agriculture in developing countries?. The World Bank.
  • Aker, J. & Fafchamps, M., (2015) Mobile phone coverage and producer markets: Evidence from West Africa. World Bank Economic Review 29 (2), 262-292.
  • Fafchamps, M. & Minten B. (2012) Impact of SMS-Based Agricultural Information on Indian Farmers, World Bank Economic Review, 26(3), 383-414.
  • Comcec Coordination Office, “Improving Agricultural Market Performance: Developing Agricultural Market Information Systems”, Comcec Coordination Office, February 2018
  • Trendov, N. M., Varas, S., & Zenf, M. (2019) Digital Technologies in Agriculture and Rural Areas: Status Report. Food and Agricultural Organization of the United Nations.
  • Pesce, M., Kirova, M., Soma, K., Bogaardt, M. J., Poppe, K., Thurston, C., ... & Urdu, D. (2019). Research for AGRI Committee—Impacts of the Digital Economy on the Food Chain and the CAP. European Parliament, Policy Department for Structural and Cohesion Policies: Brussels, Belgium, 80.
  • Giesler, S. (2018, March 22). Bioeconomy. Retrieved November 05, 2020, from https://www.biooekonomie-bw.de/en/articles/dossiers/digitisation-in-agriculture-from-precision-farming-to-farming-40
  • Antonopoulou, E., Karetsos, S. T., Maliappis, M., & Sideridis, A. B. (2010). Web and mobile technologies in a prototype DSS for major field crops. Computers and Electronics in Agriculture, 70(2), 292-301.
  • Tayyebi, A., Meehan, T. D., Dischler, J., Radloff, G., Ferris, M., & Gratton, C. (2016). SmartScape™: A web-based decision support system for assessing the tradeoffs among multiple ecosystem services under crop-change scenarios. Computers and Electronics in Agriculture, 121, 108-121.
  • Bacco, M., Barsocchi, P., Ferro, E., Gotta, A., & Ruggeri, M. (2019). The digitisation of agriculture: a survey of research activities on smart farming. Array, 3, 100009.
  • Alawode, O., Cline, T., Koigi, B., & Defait, V. (n.d.). Artificial intelligence: Matching food demand and supply. Retrieved November 05, 2020, from https://spore.cta.int/en/dossiers/article/artificial-intelligence-matching-food-demand-and-supply-sid082fb8395-30f5-44f8-96a0-96f11ede4ece
  • Wolfert, S., Ge, L., Verdouw, C., & Bogaardt, M. J. (2017). Big data in smart farming–a review. Agricultural Systems, 153, 69-80.
  • API-AGRO. (2019, April 17). Exploit the value of agricultural data - API-AGRO. Retrieved November 05, 2020, from https://api-agro.eu/en/
  • Seyedmohammadi, J., Sarmadian, F., Jafarzadeh, A. A., Ghorbani, M. A., & Shahbazi, F. (2018). Application of SAW, TOPSIS and fuzzy TOPSIS models in cultivation priority planning for maize, rapeseed and soybean crops. Geoderma, 310, 178-190.
  • David-Benz, H., Galtier, F., Egg, J., Lancon, F., & Meijerink, G. W. (2012). Market information systems. Using information to improve farmers’ market power and farmers organizations’ voice.
  • European Commission. (2020, June 10). EU prices for selected representative products. Retrieved November 05, 2020, from https://ec.europa.eu/info/food-farming-fisheries/farming/facts-and-figures/markets/prices/price-monitoring-sector/eu-prices-selected-representative-products
  • Canakci, M., & Akinci, I. (2004). Antalya bölgesi sera sebzeciliği işletmelerinde tarımsal altyapı ve mekanizasyon özellikleri. Akdeniz Üniversitesi Ziraat Fakültesi Dergisi, 17(1), 101-108.
  • Özkan, B., Akcaoz, H. V., & Karadeniz, C. F. (2001). Antalya ilinde serada sebze üretimine yer veren işletmelerin ekonomik analizi. Bahçe, 30(1).
  • The Ministry of Agriculture and Forestry of Turkey, & TAGEM, (2018, January), Tarım Ürünleri Piyasaları Domates retrieved 27.04.2020, https://arastirma.tarimorman.gov.tr/tepge
  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
  • Gers, F. A., Schraudolph, N. N., & Schmidhuber, J. (2002). Learning precise timing with LSTM recurrent networks. Journal of machine learning research, 3(Aug), 115-143.
  • Olah, C. (2015, August). Understanding LSTM Networks. Retrieved November 05, 2020, from https://colah.github.io/posts/2015-08-Understanding-LSTMs/

Cultivation Planning Across Europe using Machine Learning Techniques

Year 2021, Issue: 21, 697 - 707, 31.01.2021
https://doi.org/10.31590/ejosat.822785

Abstract

Due to their limited accessibility to the soil information and price prediction information of the agricultural products, farmers grow their crops based on the common practice in their regions. This leads to non-sustainability in agriculture and imbalance between farmers' production and customers' demand, respectively. To address the above-mentioned issues, we propose an ICT-based cultivation planning policy and system, named AgriTrade. The basic operation of AgriTrade lies in, first, incenting farmers to participate in the cultivation planning in an interactive manner using a mobile app, second, employing machine learning algorithms to provide high precision price and soil information for farmers using data collected from across the supply chain. To demonstrate the feasibility of AgriTrade, we carry out a pilot use case by collecting the last 15 years’ tomato prices of Europe and the statistics of tomato cultivation of farmers in Turkey, which is one of the biggest tomato exporters of the EU. AgriTrade forecasts the future tomato prices based on the historical tomato prices of the EU. We compare the traditional way marketing and forecast-based marketing of tomatoes: While the traditional way marketing is to immediately sell the product when it is grown, the forecast-based marketing is to store the product until the time the product's prices is higher based on the predicted prices and to sell it. The results show that when the farmers of Turkey apply the forecast-based marketing, they can remarkably increase their profits around 9.1% compared with the traditional way marketing.

References

  • Deichmann, U., Goyal, A., & Mishra, D. (2016). Will digital technologies transform agriculture in developing countries?. The World Bank.
  • Aker, J. & Fafchamps, M., (2015) Mobile phone coverage and producer markets: Evidence from West Africa. World Bank Economic Review 29 (2), 262-292.
  • Fafchamps, M. & Minten B. (2012) Impact of SMS-Based Agricultural Information on Indian Farmers, World Bank Economic Review, 26(3), 383-414.
  • Comcec Coordination Office, “Improving Agricultural Market Performance: Developing Agricultural Market Information Systems”, Comcec Coordination Office, February 2018
  • Trendov, N. M., Varas, S., & Zenf, M. (2019) Digital Technologies in Agriculture and Rural Areas: Status Report. Food and Agricultural Organization of the United Nations.
  • Pesce, M., Kirova, M., Soma, K., Bogaardt, M. J., Poppe, K., Thurston, C., ... & Urdu, D. (2019). Research for AGRI Committee—Impacts of the Digital Economy on the Food Chain and the CAP. European Parliament, Policy Department for Structural and Cohesion Policies: Brussels, Belgium, 80.
  • Giesler, S. (2018, March 22). Bioeconomy. Retrieved November 05, 2020, from https://www.biooekonomie-bw.de/en/articles/dossiers/digitisation-in-agriculture-from-precision-farming-to-farming-40
  • Antonopoulou, E., Karetsos, S. T., Maliappis, M., & Sideridis, A. B. (2010). Web and mobile technologies in a prototype DSS for major field crops. Computers and Electronics in Agriculture, 70(2), 292-301.
  • Tayyebi, A., Meehan, T. D., Dischler, J., Radloff, G., Ferris, M., & Gratton, C. (2016). SmartScape™: A web-based decision support system for assessing the tradeoffs among multiple ecosystem services under crop-change scenarios. Computers and Electronics in Agriculture, 121, 108-121.
  • Bacco, M., Barsocchi, P., Ferro, E., Gotta, A., & Ruggeri, M. (2019). The digitisation of agriculture: a survey of research activities on smart farming. Array, 3, 100009.
  • Alawode, O., Cline, T., Koigi, B., & Defait, V. (n.d.). Artificial intelligence: Matching food demand and supply. Retrieved November 05, 2020, from https://spore.cta.int/en/dossiers/article/artificial-intelligence-matching-food-demand-and-supply-sid082fb8395-30f5-44f8-96a0-96f11ede4ece
  • Wolfert, S., Ge, L., Verdouw, C., & Bogaardt, M. J. (2017). Big data in smart farming–a review. Agricultural Systems, 153, 69-80.
  • API-AGRO. (2019, April 17). Exploit the value of agricultural data - API-AGRO. Retrieved November 05, 2020, from https://api-agro.eu/en/
  • Seyedmohammadi, J., Sarmadian, F., Jafarzadeh, A. A., Ghorbani, M. A., & Shahbazi, F. (2018). Application of SAW, TOPSIS and fuzzy TOPSIS models in cultivation priority planning for maize, rapeseed and soybean crops. Geoderma, 310, 178-190.
  • David-Benz, H., Galtier, F., Egg, J., Lancon, F., & Meijerink, G. W. (2012). Market information systems. Using information to improve farmers’ market power and farmers organizations’ voice.
  • European Commission. (2020, June 10). EU prices for selected representative products. Retrieved November 05, 2020, from https://ec.europa.eu/info/food-farming-fisheries/farming/facts-and-figures/markets/prices/price-monitoring-sector/eu-prices-selected-representative-products
  • Canakci, M., & Akinci, I. (2004). Antalya bölgesi sera sebzeciliği işletmelerinde tarımsal altyapı ve mekanizasyon özellikleri. Akdeniz Üniversitesi Ziraat Fakültesi Dergisi, 17(1), 101-108.
  • Özkan, B., Akcaoz, H. V., & Karadeniz, C. F. (2001). Antalya ilinde serada sebze üretimine yer veren işletmelerin ekonomik analizi. Bahçe, 30(1).
  • The Ministry of Agriculture and Forestry of Turkey, & TAGEM, (2018, January), Tarım Ürünleri Piyasaları Domates retrieved 27.04.2020, https://arastirma.tarimorman.gov.tr/tepge
  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
  • Gers, F. A., Schraudolph, N. N., & Schmidhuber, J. (2002). Learning precise timing with LSTM recurrent networks. Journal of machine learning research, 3(Aug), 115-143.
  • Olah, C. (2015, August). Understanding LSTM Networks. Retrieved November 05, 2020, from https://colah.github.io/posts/2015-08-Understanding-LSTMs/
There are 22 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Kubilay Demir 0000-0001-5355-2472

Publication Date January 31, 2021
Published in Issue Year 2021 Issue: 21

Cite

APA Demir, K. (2021). Cultivation Planning Across Europe using Machine Learning Techniques. Avrupa Bilim Ve Teknoloji Dergisi(21), 697-707. https://doi.org/10.31590/ejosat.822785