SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks
SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks
复制标题
DOI：
10.1109/tgrs.2021.3128280
复制
发表时间：
2022-01-01
影响因子：
8.2
通讯作者：
Muller, Jan-Peter
中科院分区：
文献类型：
--
作者：
Francis, Alistair;Mrziglod, John;Muller, Jan-Peter
我们引入了一种新的神经网络架构-传感器独立性光谱编码器（SEnSeI）-通过该架构，可以使用多个多光谱仪器（每个仪器具有不同的光谱波段组合）来训练广义深度学习模型。我们专注于云掩蔽的问题，使用几个预先存在的数据集，和一个新的，免费提供的数据集哨兵-2。我们的模型被证明在其训练的卫星（Sentinel-2和Landsat 8）上实现了最先进的性能，并且能够外推到训练期间没有看到的传感器，例如Landsat 7，PeruSat-1和Sentinel-3海洋和陆地表面温度辐射计（SLSTR）。模型的性能提高时，多颗卫星被用于培训，接近，或超过专门的，单传感器模型的性能。这项工作的动机是，遥感界可以获得各种传感器采集的数据。这不可避免地导致为不同的传感器分别进行标记工作，这限制了深度学习模型的性能，因为它们需要大量的训练集才能实现最佳性能。传感器独立性可以使深度学习模型能够同时利用多个数据集进行训练，提高性能，并使其具有更广泛的适用性。这可能导致深度学习方法更频繁地用于机载应用和地面段数据处理，这通常需要模型在发射时或之后不久就准备好。
We introduce a novel neural network architecture-spectral encoder for sensor independence (SEnSeI)-by which several multispectral instruments, each with different combinations of spectral bands, can be used to train a generalized deep learning model. We focus on the problem of cloud masking, using several preexisting datasets, and a new, freely available dataset for Sentinel-2. Our model is shown to achieve state-of-the-art performance on the satellites on which it was trained (Sentinel-2 and Landsat 8) and is able to extrapolate to sensors that it has not seen during training, such as Landsat 7, PeruSat-1, and Sentinel-3 Sea and Land Surface Temperature Radiometer (SLSTR). Model performance is shown to improve when multiple satellites are used in training, approaching, or surpassing the performance of specialized, single-sensor models. This work is motivated by the fact that the remote sensing community has access to data taken with a huge variety of sensors. This has inevitably led to labeling efforts being undertaken separately for different sensors, which limits the performance of deep learning models, given their need for huge training sets to perform optimally. Sensor independence can enable deep learning models to utilize multiple datasets for training simultaneously, boosting performance, and making them much more widely applicable. This may lead to deep learning approaches being used more frequently for onboard applications and in ground segment data processing, which generally requires models to be ready at launch or soon afterward.