Visualization and Synthesis of LCCC Space Based on RF-SVM Optimization

The comprehensive carrying capacity of land is a key indicator for judging the sustainable development of nature and economy. Conducting comprehensive studies on this land capacity can provide the government with valuable information for decision-making. To divide and utilize land in a more reasonable and scientific manner, this study constructed an evaluation model based on the Random Forest and Support Vector Machine algorithms. The objective is to establish a more precise evaluation model and conduct a more comprehensive evaluation of the indicators. Based on the experimental results, it can be concluded that the carrying capacity of all five systems increased between 2014 and 2022. System Dexhibited the fastest increase in carrying capacity, with a growth rate of 58.43%, while system R recorded a growth rate of 46.29%. The difference in data before and after spatial processing in a certain region was analyzed: the average error of the five regions was relatively small, indicating that the processed values can accurately express spatial visualization information. The accuracy of Random forest support vector machine evaluation model is higher than that of support vector machine, which verifies the optimization effect of Random forest algorithm on support vector machine. In the comparative experiment of four models, each error evaluation parameter from the constructed evaluation module was superior to those from other models. These results illustrate the superior applicability of the proposed research model in terms of comprehensive land bearing capacity. The study optimized the evaluation model for comprehensive carrying capacity of land. This model proposes countermeasures and suggestions for the assessment of land carrying capacity and provides decision-making references for the protection and development of land resources.