School of Environmental Engineering, University of Seoul, Dongdaemun-gu, Seoul 02504, Republic of Korea.
Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USA.
Sci Total Environ. 2024 Feb 20;912:169540. doi: 10.1016/j.scitotenv.2023.169540. Epub 2023 Dec 23.
Recent advances in remote sensing techniques provide a new horizon for monitoring the spatiotemporal variations of harmful algal blooms (HABs) using hyperspectral data in inland water. In this study, a hierarchical concatenated variational autoencoder (HCVAE) is proposed as an efficient and accurate deep learning (DL) based bio-optical model. To demonstrate its usefulness in retrieving algal pigments, the HCVAE is applied to bloom-prone regions in Daecheong Lake, South Korea. By abstracting the similarity between highly related features using layer-wise clique-based latent-feature extraction, HCVAE reduces the computational loads in deriving outputs while preventing performance degradation. Graph-based clique-detection uses information theory-based criteria to group the related reflectance spectra. Consequently, six latent features were extracted from 79 spectral bands to consist of a multilevel hierarchy of HCVAE that can simultaneously estimate concentrations of chlorophyll-a (Chl-a) and phycocyanin (PC). Despite the parsimonious model architecture, the Chl-a and PC concentrations estimated by HCVAE closely agree with the measured concentrations, with test R values of 0.76 and 0.82, respectively. In addition, spatial distribution maps of algal pigments obtained from HCVAE using drone-borne reflectance successfully capture the blooming spots. Based on its multilevel hierarchical architecture, HCVAE can provide the importance of latent features along with their individual wavelengths using Shapley additive explanations. The most important latent features covered the spectral regions associated with both Chl-a and PC. The lightweight neural network DNN, which uses only the spectral bands of highest importance in latent-feature extraction, performed comparably to HCVAE. The study results demonstrate the utility of the multilevel hierarchical architecture as a comprehensive assessment model for near-real-time drone-borne sensing of HABs. Moreover, HCVAE is applicable to a wide range of environmental big data, as it can handle numerous sets of features.
近年来，遥感技术的进步为利用内陆水体高光谱数据监测有害藻华（HAB）的时空变化提供了新的契机。本研究提出了一种分层连接变分自动编码器（HCVAE），作为一种高效、准确的基于深度学习（DL）的生物光学模型。为了证明其在反演藻色素中的有效性，将 HCVAE 应用于韩国大青湖水华频发区。通过使用基于层的团状潜在特征提取方法来抽象高度相关特征之间的相似性，HCVAE 在降低导出输出的计算负载的同时，防止了性能下降。基于图的团状检测使用基于信息理论的标准来对相关反射光谱进行分组。因此，从 79 个光谱波段中提取了 6 个潜在特征，组成了 HCVAE 的多层次层次结构，该层次结构可以同时估计叶绿素-a（Chl-a）和藻蓝蛋白（PC）的浓度。尽管模型结构简约，但 HCVAE 估计的 Chl-a 和 PC 浓度与实测浓度密切吻合，测试 R 值分别为 0.76 和 0.82。此外，使用无人机搭载的反射率从 HCVAE 获得的藻色素空间分布图成功捕获了水华点。基于其多层次的架构，HCVAE 可以使用 Shapley 加法解释来提供潜在特征及其各自波长的重要性。最重要的潜在特征涵盖了与 Chl-a 和 PC 都相关的光谱区域。仅使用潜在特征提取中最重要的光谱波段的轻量级神经网络 DNN 与 HCVAE 性能相当。研究结果表明，多层次架构作为一种综合的无人机搭载实时 HAB 监测评估模型具有实用性。此外，HCVAE 适用于广泛的环境大数据，因为它可以处理多组特征。
