研究目的
Investigating the application of the PSO-SVR algorithm for the inversion of water quality parameters in Longquan Lake based on GF-1 remote sensing images to improve the accuracy and efficiency of water quality monitoring.
研究成果
The PSO-SVR model demonstrates superior accuracy in inverting suspended solids and Chlorophyll a concentrations in Longquan Lake compared to traditional linear regression models, with significant reductions in relative error and mean square error. This approach offers a promising tool for efficient and accurate water quality monitoring.
研究不足
The study is limited by the dependency on the accuracy of GF-1 remote sensing images and the availability of field-measured data. The PSO-SVR model's performance may vary with different water bodies or under varying environmental conditions.
1：Experimental Design and Method Selection:
The study employs the PSO-SVR algorithm for water quality parameter inversion, utilizing GF-1 remote sensing images and field-measured data.
2：Sample Selection and Data Sources:
Water samples from 30 sites in Longquan Lake were collected and analyzed for suspended solids and Chlorophyll a concentrations.
3：List of Experimental Equipment and Materials:
GF-1 remote sensing images, field-measured water spectrum data, and laboratory analysis tools.
4：Experimental Procedures and Operational Workflow:
The process includes mask extraction of water area using NDWI, SVR model training and testing, and PSO optimization of SVR parameters.
5：Data Analysis Methods:
The accuracy of the PSO-SVR model is compared with linear regression models using mean square error and relative error metrics.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
