Estévez José, Vicent Jorge, Rivera-Caicedo Juan Pablo, Morcillo-Pallarés Pablo, Vuolo Francesco, Sabater Neus, Camps-Valls Gustau, Moreno José, Verrelst Jochem
Image Processing Laboratory (IPL), Parc Científic, Universitat de Valencia, 46980 Paterna, Valencia, Spain.
Magellium, Toulouse, France.
ISPRS J Photogramm Remote Sens. 2020 Sep;167:289-304. doi: 10.1016/j.isprsjprs.2020.07.004.
Retrieval of vegetation properties from satellite and airborne optical data usually takes place after atmospheric correction, yet it is also possible to develop retrieval algorithms directly from top-of-atmosphere (TOA) radiance data. One of the key vegetation variables that can be retrieved from at-sensor TOA radiance data is leaf area index (LAI) if algorithms account for variability in atmosphere. We demonstrate the feasibility of LAI retrieval from Sentinel-2 (S2) TOA radiance data (L1C product) in a hybrid machine learning framework. To achieve this, the coupled leaf-canopy-atmosphere radiative transfer models PROSAIL-6SV were used to simulate a look-up table (LUT) of TOA radiance data and associated input variables. This LUT was then used to train the Bayesian machine learning algorithms Gaussian processes regression (GPR) and variational heteroscedastic GPR (VHGPR). PROSAIL simulations were also used to train GPR and VHGPR models for LAI retrieval from S2 images at bottom-of-atmosphere (BOA) level (L2A product) for comparison purposes. The BOA and TOA LAI products were consistently validated against a field dataset with GPR ( of 0.78) and with VHGPR ( of 0.80) and for both cases a slightly lower RMSE for the TOA LAI product (about 10% reduction). Because of delivering superior accuracies and lower uncertainties, the VHGPR models were further applied for LAI mapping using S2 acquisitions over the agricultural sites Marchfeld (Austria) and Barrax (Spain). The models led to consistent LAI maps at BOA and TOA scale. The LAI maps were also compared against LAI maps as generated by the SNAP toolbox, which is based on a neural network (NN). Maps were again consistent, however the SNAP NN model tends to overestimate over dense vegetation cover. Overall, this study demonstrated that hybrid LAI retrieval algorithms can be developed from TOA radiance data given a cloud-free sky, thus without the need of atmospheric correction. To the benefit of the community, the development of such hybrid models for the retrieval vegetation properties from BOA or TOA images has been streamlined in the freely downloadable ALG-ARTMO software framework.
从卫星和航空光学数据中反演植被属性通常是在大气校正之后进行的，但也可以直接从大气层顶（TOA）辐射数据开发反演算法。如果算法考虑到大气的变异性，那么可以从传感器处的TOA辐射数据中反演的关键植被变量之一就是叶面积指数（LAI）。我们在混合机器学习框架中展示了从哨兵-2（S2）的TOA辐射数据（L1C产品）反演LAI的可行性。为了实现这一点，使用耦合的叶-冠层-大气辐射传输模型PROSAIL-6SV来模拟TOA辐射数据及相关输入变量的查找表（LUT）。然后使用这个LUT来训练贝叶斯机器学习算法高斯过程回归（GPR）和变分异方差GPR（VHGPR）。为了进行比较，还使用PROSAIL模拟来训练用于从大气底层（BOA）水平的S2图像（L2A产品）反演LAI的GPR和VHGPR模型。通过GPR（R²为0.78）和VHGPR（R²为0.80）将BOA和TOA的LAI产品与野外数据集进行了一致性验证，并且在这两种情况下，TOA的LAI产品的均方根误差（RMSE）略低（降低了约10%）。由于具有更高的精度和更低的不确定性，VHGPR模型被进一步应用于使用奥地利马尔希费尔德和西班牙巴拉克的农业站点上的S2数据进行LAI制图。这些模型在BOA和TOA尺度上生成了一致的LAI地图。还将这些LAI地图与基于神经网络（NN）的SNAP工具箱生成的LAI地图进行了比较。地图再次保持一致，然而SNAP的NN模型往往会高估茂密植被覆盖区域的LAI。总体而言，这项研究表明，在晴空条件下，可以从TOA辐射数据开发混合LAI反演算法，因此无需进行大气校正。为了方便大家，在可免费下载的ALG-ARTMO软件框架中简化了用于从BOA或TOA图像反演植被属性的此类混合模型的开发。
