An Automated Crop Growth Detection Method Using Satellite Imagery Data

This study develops an automated crop growth detection APP, with the functionality to access the cadastral data for the target field, that was to be used for a satellite-imagery-based field survey. A total of 735 ground-truth records of the cabbage cultivation areas in Yunlin were collected via the implemented APP in order to train a deep learning model to make accurate predictions of the growth stages of the cabbage from 0 to 70 days. A regression analysis was performed by the gradient boosting decision tree (GBDT) technique. The model was trained on multitemporal multispectral satellite images, which were retrieved from the ground-truth data. The experimental results show that the mean average error of the predictions is 8.17 days, and that 75% of the predictions have errors less than 11 days. Moreover, the GBDT algorithm was also adopted for the classification analysis. After planting, the cabbage growth stages can be divided into the cupping, early heading, and mature stages. For each stage, the prediction capture rate is 0.73, 0.51, and 0.74, respectively. If the days of growth of the cabbages are partitioned into two groups, the prediction capture rate for 0–40 days is 0.83, and that for 40–70 days is 0.76. Therefore, by applying appropriate data mining techniques, together with multitemporal multispectral satellite images, the proposed method can predict the growth stages of the cabbage automatically, which can assist the governmental agriculture department to make cabbage yield predictions when creating precautionary measures to deal with the imbalance between production and sales when needed.