Drought Prediction in Tea Plantations Based on an Internet of Things System and a LASSO-COX-NOMOGRAM

This study aimed to assess the early-warning capabilities of climate change indicators for short-term drought in tea plantations and to elucidate the underlying climatic mechanisms. Meteorological data collected via IoT devices were analyzed using the Limma algorithm and univariate Cox regression to identify climate variables with differential change patterns linked to varying drought intensities. On this basis, a nomogram method based on LASSO and Cox was constructed to explore the impact mechanism of climate change on drought conditions in tea plantations. The modeling factors were screened by LASSO regression, the basis of the model was established by 5-Folder Cross Validation and Cox multivariate analysis, the prediction model was constructed by Nomogram, and the visual prediction system was built by Shiny and DynNOM. The prediction model achieved AUC values of 0.776, 0.762, and 0.777 for soil moisture content changes exceeding \u22125%, 0%, and 5%, respectively, in the training set. In the validation set, corresponding AUC values were 0.742, 0.799, and 0.710. The calibration curves closely matched the ideal reference lines, and the external validation demonstrated an accuracy of 78.57%. The developed drought prediction system enables accurate forecasting of short-term, localized drought variations in tea plantations. It offers high precision with low computational demand, thereby providing a foundation for improving the yield and quality of Yunnan tea.