Development of a Forecasting and Warning System on the Ecological Life-Cycle of Sunn Pest

2018-10-24
Balaban, Ismail
Acun, Fatih
Arpalı, Onur Yiğit
Murat, Furkan
We provide a machine learning solution that replaces the traditional methods for deciding the pesticide application time of Sunn Pest. We correlate climate datawith phases of Sunn Pest in its life-cycle and decide whether the fields should be sprayed. Our solution includes two groups of prediction models. The first group contains decision trees that predict migration time of Sunn Pest from winter quarters to wheat fields. The second group contains random forest models that predict the nymphal stage percentages of Sunn Pest which is a criterion for pesticide application. We trained our models on four years of climate data which was collected from Kırşehir and Aksaray. The experiments show that our promised solution make correct predictions with high accuracies.
International Conference & Exhibition on Digital Transformation & Smart Systems
Citation Formats
I. Balaban, F. Acun, O. Y. Arpalı, and F. Murat, “Development of a Forecasting and Warning System on the Ecological Life-Cycle of Sunn Pest,” presented at the International Conference & Exhibition on Digital Transformation & Smart Systems, Ankara, Türkiye, 2018, Accessed: 00, 2024. [Online]. Available: https://hdl.handle.net/11511/108672.