Research Article
BibTex RIS Cite

AGRICULTURAL DATA ANALYSIS WITH DATA MINING METHODS: A SMART FARMING SYSTEM PROPOSAL

Year 2022, Volume: 10 Issue: 4, 1417 - 1429, 30.12.2022
https://doi.org/10.21923/jesd.1081814

Abstract

Food scarcity and population growth are among the biggest challenges facing sustainable development worldwide. However, the impact of climate change will cause uncertainties in agriculture, as in many other areas. Advanced technologies such as artificial intelligence (AI), Internet of Things (IoT), Geographic Information Systems (GIS) and mobile internet can provide realistic solutions to the challenges facing the world. Today, with the widespread use of sensor device, it has become widespread to obtain and examine data from agricultural areas. This study focuses on product forecasting with data analysis in smart agriculture systems. Machine learning models are created using soil data (ph value, nitrogen value, potassium value and phosphorus value) and climate data (temperature, rainfall and humidity) provided via Kaggle. The created models are compared according to accuracy, precision, recall, f-score and the running time of the algorithm. The model developed with the Random Forest algorithm gave the most optimum results with a running time of approximately 0.05 s and an accuracy of 99.5%. Then, the Random Forest algorithm was applied to the data provided by the Indian ministries and finally, the agricultural product map of India is created.

References

  • Annual Rainfall Map of India. (2021). Ocak 4, 2022 tarihinde https://www.mapsofindia.com/maps/india/annualrainfall.htm adresinden alındı.
  • Average Humidity for India in January. (tarih yok). Ocak 4, 2022 tarihinde https://www.currentresults.com/Weather/India/humidity-january.php adresinden alındı.
  • Balducci, F., Impedovo, D., & Pirlo, G. (2018). Machine Learning Applications on Agricultural Datasets for Smart Farm Enhancement. MDPI, machines, 6(38), 1-22.
  • CLIMATE-SMART AGRICULTURE. (2021, Nisan 5). Ocak 30, 2022 tarihinde https://www.worldbank.org/en/topic/climate-smart-agriculture adresinden alındı.
  • Ensemble methods. (2022). Ocak 4, 2022 tarihinde https://scikit-learn.org/stable/modules/ensemble.html#forest adresinden alındı.
  • Horng, G.-J., Liu, M.-X., & Chen, C.-C. (2019). The Smart Image Recognition Mechanism for Crop Harvesting System in Intelligent Agriculture. IEEE Sensors Journal, 1-16.
  • Idoje, G., Dagiuklas, T., & Iqbal, M. (2021). Survey for smart farming technologies: Challenges and issues. Computers & Electrical Engineering, 96, 1-14.
  • India - Current Temperature [°C]. (2021). Ocak 4, 2022 tarihinde https://www.weatheronline.in/weather/maps/current?LANG=in&DATE=1604127600&CONT=inin&LAND=II&KEY=II&SORT=2&UD=0&INT=06&TYP=temperatur&ART=karte&RUBRIK=akt&R=310&CEL=C&SI=kph adresinden alındı.
  • Ingle, A. (2020, Aralık 2020). Crop Recommendation Dataset. Ocak 4, 2022 tarihinde https://www.kaggle.com/atharvaingle/crop-recommendation-dataset?select=Crop_recommendation.csv adresinden alındı.
  • Li, W., Zheng, T., Yang, Z., Li, M., Sun, C., & Yang, X. (2021). Classification and detection of insects from field images using deep learning for smart pest management: A systematic review. Ecological Informatics , 66(101460), 1-18.
  • Mohamed, E. S., AA.Belal, Abd-Elmabod, S., El-Shirbeny, M. A., A.Gad, & Zahran, M. B. (2021). Smart farming for improving agricultural management. The Egyptian Journal of Remote Sensing and Space Science, 24(3), 971-981.
  • Muangprathuba, J., Boonnama, N., Kajornkasirata, S., Lekbangponga, N., Wanichsombata, A., & Nillaorb, P. (2018). IoT and agriculture data analysis for smart farm. Computers and Electronics in Agriculture, 467-474.
  • Nearest Neighbors. (2022). Ocak 4, 2022 tarihinde https://scikit-learn.org/stable/modules/neighbors.html#classification adresinden alındı.
  • Ok, A., Akar, Ö., & Gungor, O. (2011). Rastgele Orman Sınıflandırma Yöntemi Yardımıyla Tarım Alanlarındaki ürün Çeşitliliğinin Sınıflandırılması. TUFUAB 2011 VI. Teknik Sempozyumu, (s. 1-7). Antalya.
  • Pathak, A., AmazUddin, M., Abedin, M. J., Andersson, K., Mustafa, R., & Hossainc, M. S. (2019). IoT based Smart System to Support Agricultural Parameters: A Case Study. Procedia Computer Science, 155, 648-653.
  • Podder, A. K., Bukhari, A. A., Islam, S., Mia, S., Mohammed, M. A., Kumar, N. M., . . . Abdulkareem, K. H. (2021). IoT based smart agrotech system for verification of Urban farming parameters. Microprocessors and Microsystems, 82(104025), 1-10.
  • Ratnaparkhi, S., Khan, S., Arya, C., Khapre, S., Singh, P., Diwakar, M., & Shankar, A. (2020). Smart agriculture sensors in IOT: A review. Materials Today: Proceedings, 1-6.
  • Rodríguez, J. P., Montoya-Munoz, A. I., Rodriguez-Pabon, C., Hoyos, J., & Corrales, J. C. (2021). IoT-Agro: A smart farming system to Colombian coffee farms. Computers and Electronics in Agriculture, 190, 1-18.
  • Roukha, A., Fotea, F. N., Mahmoudia, S. A., & Mahmoudia, S. (2020). Big Data Processing Architecture for Smart Farming. The 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks. Madeira.
  • Soil Maps- Cycle I. (tarih yok). Ocak 4, 2022 tarihinde https://soilhealth.dac.gov.in/NewHomePage/SoilMap adresinden alındı.
  • South Asia Network on Dams, Rivers and People. (tarih yok). Ocak 4, 2022 tarihinde https://sandrp.in/category/rainfall/page/2/ adresinden alındı.
  • Sujatha, R., Chatterjee, J. M., Jhanjhi, N., & Brohi, S. N. (2021). Performance of deep learning vs machine learning in plant leaf disease detection . Microprocessors and Microsystems, 80, 1-11.
  • Tay, B., Hyun, J. K., & Oh, S. (2014). A Machine Learning Approach for Specification of Spinal Cord Injuries Using Fractional Anisotropy Values Obtained from Diffusion Tensor Images. Comput Math Methods Med.
  • Wang, P., Hafshejani, B. A., & Wang, D. (2021). An improved multilayer perceptron approach for detecting sugarcane yield production in IoT based smart agriculture. Microprocessors and Microsystems , 82(103822), 1-7.
  • XGBoost Documentation. (2022). Ocak 4, 2022 tarihinde https://xgboost.readthedocs.io/en/stable/ adresinden alındı.

VERİ MADENCİLİĞİ YÖNTEMLERİ İLE TARIMSAL VERİ ANALİZİ: BİR AKILLI TARIM SİSTEMİ ÖNERİSİ

Year 2022, Volume: 10 Issue: 4, 1417 - 1429, 30.12.2022
https://doi.org/10.21923/jesd.1081814

Abstract

Gıda kıtlığı ve nüfus artışı, dünya çapında sürdürülebilir kalkınmanın karşı karşıya olduğu en büyük zorluklardandır. Bununla beraber iklim değişikliğinin etkisi diğer birçok alanda olduğu gibi tarım alanında da belirsizliklere neden olacaktır. Yapay zekâ (AI), Nesnelerin İnterneti (IoT), Coğrafi Bilgi Sistemleri (CBS) ve mobil internet gibi gelişmiş teknolojiler, dünyanın karşı karşıya olduğu zorluklara gerçekçi çözümler sağlayabilmektedir. Günümüzde sensör cihazlarının yaygınlaşması ile tarım alanlarından veri elde etmek ve ham veriden bilgi üretmek yaygınlaşmıştır. Bu çalışma, Akıllı tarımda veri analizi ile ürün tahmini üzerine yoğunlaşmıştır. Kaggle üzerinden sağlanan toprak (ph, azot, potasyum ve fosfor değeri) ve iklim verileri (sıcaklık yağış ve nem) kullanılarak veri madenciliği algoritmaları ile farklı modeller oluşturulmuştur. Oluşturulan modeller doğruluk, kesinlik, duyarlılık, f-skor ve algoritmanın çalışma zamanına göre kıyaslanmıştır. Rastgele Orman algoritmasıyla geliştirilen model, çalışma süresi yaklaşık 0,05 s ve %99,5’lik doğruluk değeri ile en optimum sonuçları vermiştir. Daha sonra, Rastgele Orman algoritması Hindistan bakanlıklarınca sağlanan toprak verileri ve meteoroloji verilerine uygulanmış ve Hindistan’ın tarımsal ürün haritası oluşturulmuştur.

References

  • Annual Rainfall Map of India. (2021). Ocak 4, 2022 tarihinde https://www.mapsofindia.com/maps/india/annualrainfall.htm adresinden alındı.
  • Average Humidity for India in January. (tarih yok). Ocak 4, 2022 tarihinde https://www.currentresults.com/Weather/India/humidity-january.php adresinden alındı.
  • Balducci, F., Impedovo, D., & Pirlo, G. (2018). Machine Learning Applications on Agricultural Datasets for Smart Farm Enhancement. MDPI, machines, 6(38), 1-22.
  • CLIMATE-SMART AGRICULTURE. (2021, Nisan 5). Ocak 30, 2022 tarihinde https://www.worldbank.org/en/topic/climate-smart-agriculture adresinden alındı.
  • Ensemble methods. (2022). Ocak 4, 2022 tarihinde https://scikit-learn.org/stable/modules/ensemble.html#forest adresinden alındı.
  • Horng, G.-J., Liu, M.-X., & Chen, C.-C. (2019). The Smart Image Recognition Mechanism for Crop Harvesting System in Intelligent Agriculture. IEEE Sensors Journal, 1-16.
  • Idoje, G., Dagiuklas, T., & Iqbal, M. (2021). Survey for smart farming technologies: Challenges and issues. Computers & Electrical Engineering, 96, 1-14.
  • India - Current Temperature [°C]. (2021). Ocak 4, 2022 tarihinde https://www.weatheronline.in/weather/maps/current?LANG=in&DATE=1604127600&CONT=inin&LAND=II&KEY=II&SORT=2&UD=0&INT=06&TYP=temperatur&ART=karte&RUBRIK=akt&R=310&CEL=C&SI=kph adresinden alındı.
  • Ingle, A. (2020, Aralık 2020). Crop Recommendation Dataset. Ocak 4, 2022 tarihinde https://www.kaggle.com/atharvaingle/crop-recommendation-dataset?select=Crop_recommendation.csv adresinden alındı.
  • Li, W., Zheng, T., Yang, Z., Li, M., Sun, C., & Yang, X. (2021). Classification and detection of insects from field images using deep learning for smart pest management: A systematic review. Ecological Informatics , 66(101460), 1-18.
  • Mohamed, E. S., AA.Belal, Abd-Elmabod, S., El-Shirbeny, M. A., A.Gad, & Zahran, M. B. (2021). Smart farming for improving agricultural management. The Egyptian Journal of Remote Sensing and Space Science, 24(3), 971-981.
  • Muangprathuba, J., Boonnama, N., Kajornkasirata, S., Lekbangponga, N., Wanichsombata, A., & Nillaorb, P. (2018). IoT and agriculture data analysis for smart farm. Computers and Electronics in Agriculture, 467-474.
  • Nearest Neighbors. (2022). Ocak 4, 2022 tarihinde https://scikit-learn.org/stable/modules/neighbors.html#classification adresinden alındı.
  • Ok, A., Akar, Ö., & Gungor, O. (2011). Rastgele Orman Sınıflandırma Yöntemi Yardımıyla Tarım Alanlarındaki ürün Çeşitliliğinin Sınıflandırılması. TUFUAB 2011 VI. Teknik Sempozyumu, (s. 1-7). Antalya.
  • Pathak, A., AmazUddin, M., Abedin, M. J., Andersson, K., Mustafa, R., & Hossainc, M. S. (2019). IoT based Smart System to Support Agricultural Parameters: A Case Study. Procedia Computer Science, 155, 648-653.
  • Podder, A. K., Bukhari, A. A., Islam, S., Mia, S., Mohammed, M. A., Kumar, N. M., . . . Abdulkareem, K. H. (2021). IoT based smart agrotech system for verification of Urban farming parameters. Microprocessors and Microsystems, 82(104025), 1-10.
  • Ratnaparkhi, S., Khan, S., Arya, C., Khapre, S., Singh, P., Diwakar, M., & Shankar, A. (2020). Smart agriculture sensors in IOT: A review. Materials Today: Proceedings, 1-6.
  • Rodríguez, J. P., Montoya-Munoz, A. I., Rodriguez-Pabon, C., Hoyos, J., & Corrales, J. C. (2021). IoT-Agro: A smart farming system to Colombian coffee farms. Computers and Electronics in Agriculture, 190, 1-18.
  • Roukha, A., Fotea, F. N., Mahmoudia, S. A., & Mahmoudia, S. (2020). Big Data Processing Architecture for Smart Farming. The 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks. Madeira.
  • Soil Maps- Cycle I. (tarih yok). Ocak 4, 2022 tarihinde https://soilhealth.dac.gov.in/NewHomePage/SoilMap adresinden alındı.
  • South Asia Network on Dams, Rivers and People. (tarih yok). Ocak 4, 2022 tarihinde https://sandrp.in/category/rainfall/page/2/ adresinden alındı.
  • Sujatha, R., Chatterjee, J. M., Jhanjhi, N., & Brohi, S. N. (2021). Performance of deep learning vs machine learning in plant leaf disease detection . Microprocessors and Microsystems, 80, 1-11.
  • Tay, B., Hyun, J. K., & Oh, S. (2014). A Machine Learning Approach for Specification of Spinal Cord Injuries Using Fractional Anisotropy Values Obtained from Diffusion Tensor Images. Comput Math Methods Med.
  • Wang, P., Hafshejani, B. A., & Wang, D. (2021). An improved multilayer perceptron approach for detecting sugarcane yield production in IoT based smart agriculture. Microprocessors and Microsystems , 82(103822), 1-7.
  • XGBoost Documentation. (2022). Ocak 4, 2022 tarihinde https://xgboost.readthedocs.io/en/stable/ adresinden alındı.
There are 25 citations in total.

Details

Primary Language Turkish
Subjects Computer Software
Journal Section Research Articles
Authors

Burak Özer 0000-0003-2615-9389

Sümeyra Kuş 0000-0002-5288-769X

Oktay Yıldız 0000-0001-9155-7426

Publication Date December 30, 2022
Submission Date March 4, 2022
Acceptance Date April 27, 2022
Published in Issue Year 2022 Volume: 10 Issue: 4

Cite

APA Özer, B., Kuş, S., & Yıldız, O. (2022). VERİ MADENCİLİĞİ YÖNTEMLERİ İLE TARIMSAL VERİ ANALİZİ: BİR AKILLI TARIM SİSTEMİ ÖNERİSİ. Mühendislik Bilimleri Ve Tasarım Dergisi, 10(4), 1417-1429. https://doi.org/10.21923/jesd.1081814