Apple Pest Analysis

Abstract—Prediction depicts the way the things will happen in the future, but not always based on experience or knowledge. Prediction is helpful in various fields and it brings out together the past and current data as a basis to develop reasonable expectations about the future. The main objective of this work is to predict the occurrence of a risk factor in apple caused by apple scab in Himalayan regions. Firstly, we obtained the readings of necessary environmental parameters like temperature, Humidity and leaf wetness duration, which affects the growth of disease and pests by interfacing sensors with Raspberry Pi board and calculation of the infection index of the disease of apple. As a prediction model, the Beta regression model was used

Due to pests and disease attack on the crops, farmers have to face major economic loss every year. To control the pest and disease, there are many chemical pesticides that are used by farmers in their field. Widespread use of these agro-chemicals has resulted in damaged Agra-echo system, scoring low on product quality and effect on human health. So there is a need of pest management, which is a method to control the pest in an effective manner and reducing our dependence on pesticides. The use of pesticides can be reduced with the help of forecasting of diseases and pest infection. Infection rate and disease severity are highly dependent on environmental parameters like temperature, humidity, leaf wetness duration, rainfall, etc. Using correlation of these parameters with the infection rate, a mathematical prediction model can be devised to estimate the future value of infection. It predicts risk or no risk for the particular infection to occur on that particular crop [1]. Advance information about severity of risk help to alert the farmers to manage the quality and quantity of spray of pesticides for particular pest and disease. For this work, apple scab has been considered which is infected by Venturia Inaequalis.
A.Plant Disease Forecasting
Plant disease forecasting is a management system used to predict the occurrence or change in severity of plant diseases.

The parameter q describes how steeply Y increases with increasing T up to the optimum; the parameter r describes how steeply Y decreases as T increases past the optimum. The above equation can be linearized to: log(Y) = log(p) + q log(t) + r log(1 – t) + s