School of Science, Anhui Agricultural University, Hefei, 230036, China.
School of Resources and Environmental Engineering, Anhui University, Hefei, 230601, China.
Environ Sci Pollut Res Int. 2022 Jan;29(3):4401-4413. doi: 10.1007/s11356-021-16004-9. Epub 2021 Aug 18.
Water transparency is a key indicator of water quality as it reflects the turbidity and eutrophication in lakes and reservoirs. To carry out remote sensing monitoring of water transparency rapidly and intelligently, deep learning technology was used to construct a new retrieval model, namely, point-centered regression convolutional neural network (PSRCNN) suitable for Sentinel 2 and Landsat 8 images. The impact of input feature variables on the accuracy of the inversion model was examined, and the performance of an optimized PSRCNN model was also assessed. This model was applied to remote sensing images of three shallow lakes in the eastern China plain acquired in summer. The PSRCNN model, constructed using five identical bands from Landsat 8 and Sentinel 2 images and 20 band combinations as the input variables, the input window size of 5 × 5 pixels, proves a good predictive ability, with a verification accuracy of R = 0.85, the root mean squared error (RMSE) = 13.0 cm, and the relative predictive deviation (RPD) = 2.58. After the sensitive spectral analysis of water transparency, the band combinations that had correlation coefficients higher than 0.6 were selected as the new input feature variables to construct an optimized PSRCNN model (PSRCNN) for water transparency. The PSRCNN model has an excellent predictive ability, with a verification accuracy of R = 0.89, RMSE = 11.48 cm, and RPD =3.0. It outperforms the commonly retrieval models (band ratios, random forest, support vector machine, etc.), with higher accuracy and robustness. Spatial variations in water transparency of three lakes from the retrieval results by PSRCNN model are consistent with the field observations.
水透明度是水质的一个关键指标，因为它反映了湖泊和水库的浑浊度和富营养化程度。为了快速、智能地进行水透明度的遥感监测，利用深度学习技术构建了一种新的反演模型，即适用于 Sentinel-2 和 Landsat-8 图像的点中心回归卷积神经网络（PSRCNN）。检验了输入特征变量对反演模型精度的影响，并评估了优化后的 PSRCNN 模型的性能。将该模型应用于夏季获取的中国东部平原三个浅水湖泊的遥感图像。使用 Landsat-8 和 Sentinel-2 图像的五个相同波段和 20 个波段组合作为输入变量，输入窗口大小为 5×5 像素，构建的 PSRCNN 模型具有良好的预测能力，验证精度 R=0.85，均方根误差（RMSE）=13.0cm，相对预测偏差（RPD）=2.58。对水透明度进行敏感光谱分析后，选择相关系数高于 0.6 的波段组合作为新的输入特征变量，构建了用于水透明度的优化 PSRCNN 模型（PSRCNN）。PSRCNN 模型具有优异的预测能力，验证精度 R=0.89，RMSE=11.48cm，RPD=3.0。它优于常用的反演模型（波段比、随机森林、支持向量机等），具有更高的精度和鲁棒性。从 PSRCNN 模型的反演结果来看，三个湖泊的水透明度空间变化与实地观测结果一致。
