With the development and utilization of lakes by people, the problem of eutrophication in lakes has also intensified. By evaluating the nutritional status of lakes, people can understand the water quality of lakes, analyze the causes of eutrophication, grasp the laws of lake environment, and provide basic data for the rational development and utilization of lake resources. Traditional sampling and analysis methods are time-consuming, costly, and easily affected by environmental interference. Hyperspectral technology can quickly and comprehensively obtain water quality parameters of lake, and is widely used for evaluation of lake eutrophication. In previous studies, the data sources were mostly ground data or low spatial resolution hyperspectral data, which could not reflect the detailed changes in water quality parameters. The relationship between water quality parameters and spectra is complex and variable, and the simple linear model is difficult to accurately quantify the content of water quality parameters. The single indicator is not suitable for evaluation of lake eutrophication, and the comprehensive evaluation indicator needs to be established. For this purpose, the evaluation method for lake eutrophication using aerial hyperspectral image is built.The evaluation of lake eutrophicationn had been carried out using aerial hyperspectral image with a spatial resolution of 0.5 m and combined with ground measurement data. Firstly, the collected data was preprocessed to obtain reflectance data and five water quality parameters including Chlorophyll-a, Total Phosphorus, Total Nitrogen, Secchi Depth, and Permanganate Index. The correlation analysis was conducted on the preprocessed data and water quality parameters, and the first-order derivatives with higher correlations were selected for relevant features using Competitive Adaptive Reweighted Sampling (CARS). Then, the water quality parameter inversion model has been constructed using the Least Squares Support Vector Regression (LSSVR) algorithm based on Quantum Particle Swarm Optimization(QPSO). The model accuracy has been evaluated using the coefficient of determination(R²) and Root Mean Squard Error(RMSE), and the comparative analysis was conducted. Finally, the comprehensive nutritional status index has been calculated and compared with the measured values, and the eutrophication of lake in the research area has been evaluated using aerial hyperspectral image.Five different inversion models were compared, and the water quality parameter inversion model constructed based on first-order differential transformation has the highest accuracy with R² > 0.8(Tab.3), and inversion values are close to the measured values(Fig.4). The results of the comprehensive nutrient index are accurate, with MRE = 0.91% and RMSE = 0.50 when compared to measured values(Fig.4). The evaluation results for lake eutrophication in the study area have a high spatial resolution, accurately and detailed reflecting the distribution of nutrient status in the lake (Fig.5). The research area is in a state of mild eutrophication, which is consistent with the content of the water environment quality report of Yangzhou City. The method achieves high-precision and rapid evaluation of lake eutrophication. Due to limitations in flight conditions and project support, data collection was conducted only within the lake area of Gaoyou City and did not fully cover the entire Gaoyou Lake region. The results cannot represent the eutrophication level of the entire Gaoyou Lake.An evaluation method for lake eutrophication based on aerial hyperspectral data is proposed. This method uses aerial hyperspectral data with a spatial resolution of 0.5 m, which details the variations in water quality parameters and accurately depicts the spatial distribution of eutrophication in lake. An optimized machine learning algorithm was employed to construct the water quality parameter inversion model, fully extracting relevant information to improve the accuracy of the inversion results. This method can quickly and accurately evaluate of lake eutrophication, but is subject to limitations such as sample collection and spatiotemporal distribution, and its applicability to other complex lake remains to be further studied. The data collection process may be affected by environmental factors such as weather and lighting, leading to poor data quality and reducing the accuracy of the inversion results. Comparative experiments under different climate and lighting conditions can be further conducted to verify its accuracy.