Palola Pirta, Theenathayalan Varunan, Schröder Cornelius, Martinez-Vicente Victor, Collin Antoine, Wright Rosalie, Ward Melissa, Thomson Eleanor, Lopez-Garcia Patricia, Hochberg Eric J, Malhi Yadvinder, Wedding Lisa M
School of Geography and the Environment, University of Oxford, Oxford, UK.
Plymouth Marine Laboratory, Plymouth, UK.
R Soc Open Sci. 2025 May 7;12(5):241471. doi: 10.1098/rsos.241471. eCollection 2025.
Human activities are altering coral reef ecosystems worldwide. Optical remote sensing via satellites and drones can offer novel insights into where and how coral reefs are changing. However, interpretation of the observed optical signal (remote-sensing reflectance) is an ill-posed inverse problem, as there may be multiple different combinations of water constituents, depth and benthic reflectance that result in a similar optical signal. Here, we apply a new approach, simulation-based inference, for addressing the inverse problem in marine remote sensing. The simulation-based inference algorithm combines physics-based analytical modelling with approximate Bayesian inference and machine learning. The input to the algorithm is remote-sensing reflectance, and the output is the likely range (posterior probability density) of phytoplankton and suspended minerals concentrations, coloured dissolved organic matter absorption, wind speed and depth. We compare inference models trained with simulated hyperspectral or multispectral reflectance spectra characterized by different signal-to-noise ratios. We apply the inference model to radiometric data ( = 4) and multispectral drone imagery collected on the Tetiaroa atoll (South Pacific). We show that water constituent concentrations can be estimated from hyperspectral and multispectral remote-sensing reflectance in optically shallow environments, assuming a single benthic cover. Future developments should consider spectral mixing of multiple benthic cover types.
人类活动正在改变全球范围内的珊瑚礁生态系统。通过卫星和无人机进行的光学遥感能够为珊瑚礁在何处以及如何发生变化提供全新的见解。然而，对观测到的光学信号（遥感反射率）进行解释是一个不适定的反问题，因为水成分、深度和底栖反射率可能存在多种不同组合，却会导致相似的光学信号。在此，我们应用一种新方法——基于模拟的推理，来解决海洋遥感中的反问题。基于模拟的推理算法将基于物理的分析建模与近似贝叶斯推理及机器学习相结合。该算法的输入是遥感反射率，输出是浮游植物和悬浮矿物质浓度、有色溶解有机物吸收、风速和深度的可能范围（后验概率密度）。我们比较了用具有不同信噪比的模拟高光谱或多光谱反射光谱训练的推理模型。我们将推理模型应用于在泰蒂亚罗阿环礁（南太平洋）收集的辐射数据（ = 4）和多光谱无人机图像。我们表明，在假设单一底栖覆盖的情况下，在光学浅水环境中可以从高光谱和多光谱遥感反射率估算出水成分浓度。未来的发展应考虑多种底栖覆盖类型的光谱混合。
