Gaussian Processes Regression for Biophysical Parameter Retrieval from Imaging Spectroscopy Data: Opportunities for Sentinel-2 and -3
نویسندگان
چکیده
ESA’s upcoming satellites Sentinel-2 (S2) and Sentinel3 (S3) aim to ensure continuity for Landsat, Spot and MERIS observations by providing multispectral and hyperspectral images of high temporal resolution. S2 and S3 will deliver near real-time operational products with a high accuracy for land monitoring, but therefore robust and accurate retrieval methods are needed. Machine learning algorithms may be powerful candidates for the estimation of biophysical parameters because of their ability to adaptive, nonlinear regression. We have compared the efficacy of four state-of-theart machine learning algorithms given various S2 and S3 band settings and 3 important biophysical parameters: leaf chlorophyll content (Chl), green leaf area index (LAI) and fractional vegetation cover (FVC). Tested Sentinel configurations were: S2-10m (4 bands), S2-20m (8 bands), S2-60m (10 bands) and S3-300m (19 bands), and tested methods were: support vector regression (SVR), kernel ridge regression (KRR), neural networks (NN) and the novel Gaussian processes regression (GPR). GPR was the only method that reached the by GMES defined precision of 10% in the estimation of Chl. Also, although validated with RMSE accuracy around 20%, GPR yielded optimal LAI estimates at highest S2 spatial resolution of 10 m with only 4 bands. GPR did not only outperform the other retrieval methods for the majority of tested configurations, but also provided additional confidences of the estimates, which gives it a key advantage over the other methods.
منابع مشابه
Volumetric soil moisture estimation using Sentinel 1 and 2 satellite images
Surface soil moisture is an important variable that plays a crucial role in the management of water and soil resources. Estimating this parameter is one of the important applications of remote sensing. One of the remote sensing techniques for precise estimation of this parameter is data-driven models. In this study, volumetric soil moisture content was estimated using data-driven models, suppor...
متن کاملSpectral band selection for vegetation properties retrieval using Gaussian processes regression
With current and upcoming imaging spectrometers, automated band analysis techniques are needed to enable efficient identification of most informative bands to facilitate optimized processing of spectral data into estimates of biophysical variables. This paper introduces an automated spectral band analysis tool (BAT) based on Gaussian processes regression (GPR) for the spectral analysis of veget...
متن کاملPerformance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data
Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatia...
متن کاملDetection of Glioblastoma Multiforme Tumor in Magnetic Resonance Spectroscopy Based on Support Vector Machine
Introduction: The brain tumor is an abnormal growth of tissue in the brain, which is one of the most important challenges in neurology. Brain tumors have different types. Some brain tumors are benign and some brain tumors are cancerous and malignant. Glioblastoma Multiforme (GBM) is the most common and deadliest malignant brain tumor in adults. The average survival rate for peo...
متن کاملDynamic lymphoscintigraphy in breast cancer patients: feasibility and added value
Introduction: Lymphoscintigraphy is imaging of the lymphatic system and has been integrated into the sentinel node mapping procedures. Lymphoscintigraphy usually encompasses early or delayed static images. However, immediate dynamic imaging of the lymphatic basins and tumors has also been used as an adjunct lymphoscintigraphy imaging. The aim of this study was ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011