Estimation of moisture content in cucurbitaceae seedlings using hyperspectral imagery

Background: This research was conducted to develop moisture content model and estimate its performance in cucurbitaceae seedlings, such as cucumber and water melon, using hyperspectral imagery. Methods: Using a hyperspectral image acquisition system, reflectance of leaf area of cucumber (n=45) and watermelon (n=45) seedlings was calculated after providing water stress. Then, moisture content in each seedling was measured by using a dry oven. Finally, the moisture content estimation models were developed by PLS-Regression analysis with reflectance data and moisture content data. Results: After developing the estimation models, the cucumber model predicts that performance is significant as 0.73 of R2, 1.45% of RMSE, and 1.58% of RE. The watermelon model predicts that performance is acceptable as 0.66 of R2, 1.06% of RMSE, and 1.14% of RE. The model performed slightly better after removing one sample from cucumber seedlings as outlier and unnecessary. Hence, the performance of new model for cucumber seedlings (n=44) showed 0.79 of R2, 1.10% of RMSE, and 1.20% of RE. The model performance combined with all samples (n=89) showed 0.67 of R2, 1.26% of RMSE, and 1.36% of RE. Discussion: The model of cucumber showed better performance than the model of water melon. This is because variables of cucumber are consisted of widely distributed variation, and it affected the performance. Further, accuracy and precision of the cucumber model were increased when an insignificant sample was eliminated from the dataset. Finally, it is considered that both models can be significantly used to estimate moisture content, as gradients of trend line are almost same and intersected. Conclusion: It is considered that the accuracy and precision of the estimating models possibly can be improved, if the models are constructed by using variables with widely distributed variation. The improved models will be utilized as the basis for developing low-priced sensors