Guangdong Provincial Key Laboratory of Water Quality Improvement and Ecological Restoration for Watersheds, School of Ecology, Environment and Resources, Guangdong University of Technology, Guangzhou, 510006, China.
State Environmental Protection Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing, 100012, China.
Environ Sci Pollut Res Int. 2023 Jul;30(35):83628-83642. doi: 10.1007/s11356-023-28344-9. Epub 2023 Jun 22.
Cyanobacterial blooms in lakes fueled by increasing eutrophication have garnered global attention, and high-precision remote sensing retrieval of chlorophyll-a (Chla) is essential for monitoring eutrophication. Previous studies have focused on the spectral features extracted from remote sensing images and their relationship with chlorophyll-a concentrations in water bodies, ignoring the texture features in remote sensing images which is beneficial to improve interpreting accuracy. This study explores the texture features in remote-sensing images. It proposes a retrieval method for estimating lake Chla concentration by combining spectral and texture features of remote sensing images. Remote sensing images from Landsat 5 TM and 8 OLI were used to extract spectral bands combination. The gray-level co-occurrence matrix (GLCM) of remote sensing images was used to obtain a total of 8 texture features; then, three texture indices were calculated using texture features. Finally, a random forest regression was used to establish a retrieval model of in situ Chla concentration from texture and spectral index. Results showed that texture features are significantly correlated with lake Chla concentration, and they can reflect the temporal and spatial distribution change of Chla. The retrieval model combining spectral and texture indices performs better (MAE = 15.22 μg·L, bias = 9.69%, MAPE = 47.09%) than the model without texture features (MAE = 15.76 μg·L, bias = 13.58%, MAPE = 49.44%). The proposed model performance varies in different Chla concentration ranges and is excellent in predicting higher concentrations. This study evaluates the potential of incorporating texture features of remote sensing images in lake water quality estimation and provides a novel remote sensing method to better estimate lake Chla concentration.
湖泊富营养化引发的蓝藻水华已引起全球关注，精确的叶绿素 a（Chla）遥感反演对于监测富营养化至关重要。以往的研究主要集中在从遥感图像中提取的光谱特征及其与水体 Chla 浓度的关系上，忽略了遥感图像中的纹理特征，而这些特征有利于提高解释精度。本研究探讨了遥感图像中的纹理特征。提出了一种结合遥感图像光谱和纹理特征估算湖泊 Chla 浓度的反演方法。利用 Landsat 5 TM 和 8 OLI 遥感图像提取光谱波段组合。利用遥感图像的灰度共生矩阵（GLCM）获取共 8 个纹理特征；然后，利用纹理特征计算 3 个纹理指数。最后，采用随机森林回归建立基于纹理和光谱指数的原位 Chla 浓度反演模型。结果表明，纹理特征与湖泊 Chla 浓度显著相关，能够反映 Chla 的时空分布变化。结合光谱和纹理指数的反演模型表现更好（MAE=15.22μg·L，偏差=9.69%，MAPE=47.09%），优于不包含纹理特征的模型（MAE=15.76μg·L，偏差=13.58%，MAPE=49.44%）。所提出的模型在不同 Chla 浓度范围内的性能不同，在预测较高浓度时表现出色。本研究评估了将遥感图像纹理特征纳入湖泊水质估算的潜力，为更好地估算湖泊 Chla 浓度提供了一种新的遥感方法。
