2 results about "Allium chinense" patented technology

This invention relates to the field of ecological restoration, and discloses a method and system for soil health restoration and nutrient cycling regulation of degraded *Allium chinense* populations in karst alpine regions. The method includes the following steps: performing structured initial sampling in the target restoration area to obtain an initial training dataset; constructing a master surrogate model for predicting *Allium chinense* population density and a constrained surrogate model for predicting the feasibility of restoration schemes; optimizing the master surrogate model using a sampling function to select candidate restoration formulas; implementing the candidate restoration formulas in the field and observing the actual population density response, incorporating the new data pairs into the initial training dataset to update the master surrogate model; using the constrained surrogate model combined with a feasibility constraint function to evaluate the economic feasibility of the candidate restoration formulas under given competing plant conditions; integrating the new data to retrain the master surrogate model and / or the constrained surrogate model and updating the recommended restoration formulas. This method provides quantitative support for restoration decisions while reducing the number of field experiment rounds.

This invention discloses a method and system for classifying and spatially warning about the degradation status of *Allium chinense* populations in alpine grasslands, relating to the field of ecological environment monitoring technology. The method includes: acquiring degradation feature vectors of *Allium chinense* at each spatial grid point; obtaining the local spectral matrix of each spatial grid point based on its feature vectors and spatial neighborhood information using a robust covariance estimation method; constructing and solving a unified optimization problem based on the local spectral matrix, outputting the optimal load matrix for each spatial grid point through distributed iterative optimization; calculating the degradation intensity index based on the optimal load matrix and the local spectral matrix; identifying the dominant degradation variable based on the row-wise comprehensive load of the optimal load matrix; determining the degradation type of each spatial grid point through a configurable rule engine; performing spatial segmentation and connectivity analysis on the degradation intensity index; and outputting a spatial warning layer. This achieves continuous spatial assessment and classification of the degradation status of large-scale *Allium chinense* populations.