Termination of Irrigation time of chili pepper by computer method

The problem of water scarcity is one of the most important agricultural problems in Iran, therefore proper and timely use of water resources is essential. One of the strategies for optimal use of water in agriculture is irrigation planning of agricultural products. Irrigation planning means specifying the irrigation time and amount of water needed at each irrigation time during the plant growth period. In this study, in order to determine the irrigation time, the color change index of pepper leaf due to the decrease in soil moisture was used. So far, some studies have been carried out to determine some of the agronomic parameters of the fruit and leaf color changes using digital image processing, but no evidence is available for the relationship between leaf color and soil moisture subject to this thesis. Therefore, it can be assumed that this research is the first research in this field.

In order to investigate the effect of water stress on leaf color of chili pepper, plastic pots and dimaz chili peppers were used. The measured parameters included plant leaf color and soil moisture. Leaves were photographed daily and finally leaf color analysis was performed using Photoshop and BAL color scheme. The experiment was conducted in a completely randomized design with five treatments including 10, 30 and 50% water stress, complete irrigation and no irrigation treatment in four replications for irrigation planning. (No irrigation treatment was considered as control treatment). Water stress was applied to the treatments for 52 days during plant growth period from transplanting (three weeks after transplanting) until harvest.

The LAB color system with a correlation coefficient higher than 94% can be used as an efficient system for investigating leaf color changes and determining irrigation time. One of the advantages of this method is its high computational volume and high accuracy of results. Increasing the accuracy of this method and examining its feasibility requires further research, and its simplicity and low cost can be a good justification for continuing its use. Certainly, by developing research on the proposed system, including the use of laboratory equipment and more accurate numerical methods, acceptable results can be obtained in estimating the exact irrigation time. On the other hand, three tree models QUEST, C5 and CHAID, which are decision tree algorithms, were used to predict soil moisture classes. The results showed that the C5 tree model had higher accuracy than other models and the accuracy of prediction of soil moisture classes by this model for the lab system was 86%.

The findings showed that as a result of soil moisture changes, there is a change in the natural reflection of the leaf color of the plant, and the lower the soil moisture, the darker the leaf color becomes and these changes affect the elements of the lab color system.