Vicarious calibration approaches using in situ measurements saw first use in the early 1980s and have since improved to keep pace with the evolution of the radiometric requirements of the sensors that are being calibrated. The advantage of in situ measurements for vicarious calibration is that they can be carried out with traceable and quantifiable accuracy, making them ideal for interconsistency studies of on-orbit sensors. The recent development of automated sites to collect the in situ data has led to an increase in the available number of datasets for sensor calibration. The current work describes the Radiometric Calibration Network (RadCalNet) that is an effort to provide automated surface and atmosphere in situ data as part of a network including multiple sites for the purpose of optical imager radiometric calibration in the visible to shortwave infrared spectral range. The key goals of RadCalNet are to standardize protocols for collecting data, process to top-of-atmosphere reflectance, and provide uncertainty budgets for automated sites traceable to the international system of units. RadCalNet is the result of efforts by the RadCalNet Working Group under the umbrella of the Committee on Earth Observation Satellites (CEOS) Working Group on Calibration and Validation (WGCV) and the Infrared Visible Optical Sensors (IVOS). Four radiometric calibration instrumented sites located in the USA, France, China, and Namibia are presented here that were used as initial sites for prototyping and demonstrating RadCalNet. All four sites rely on collection of data for assessing the surface reflectance as well as atmospheric data over that site. The data are converted to top-of-atmosphere reflectance within RadCalNet and provided through a web portal to allow users to either radiometrically calibrate or verify the calibration of their sensors of interest. Top-of-atmosphere reflectance data with associated uncertainties are available at 10 nm intervals over the 400 nm to 1000 nm spectral range at 30 min intervals for a nadir-viewing geometry. An example is shown demonstrating how top-of-atmosphere data from RadCalNet can be used to determine the interconsistency between two sensors.

Atmospheric radiative transfer models (RTMs) simulate the light propagation in the Earth’s atmosphere. With the evolution of RTMs, their increase in complexity makes them impractical in routine processing such as atmospheric correction. To overcome their computational burden, standard practice is to interpolate a multidimensional lookup table (LUT) of prestored simulations. However, accurate interpolation relies on large LUTs, which still implies large computation times for their generation and interpolation. In recent years, emulation has been proposed as an alternative to LUT interpolation. Emulation approximates the RTM outputs by a statistical regression model trained with a low number of RTM runs. However, a concern is whether the emulator reaches sufficient accuracy for atmospheric correction. Therefore, we have performed a systematic assessment of key aspects that impact the precision of emulating MODTRAN: 1) regression algorithm; 2) training database size; 3) dimensionality reduction (DR) method and a number of components; and 4) spectral resolution. The Gaussian processes regression (GPR) was found the most accurate emulator. The principal component analysis remains a robust DR method and nearly 20 components reach sufficient precision. Based on a database of 1000 samples covering a broad range of atmospheric conditions, GPR emulators can reconstruct the simulated spectral data with relative errors below 1% for the 95th percentile. These emulators reduce the processing time from days to minutes, preserving sufficient accuracy for atmospheric correction and providing model uncertainties and derivatives. We provide a set of guidelines and tools to design and generate accurate emulators for satellite data processing applications.

The combination of machine learning models with physical models is a recent research path to learn robust data representations. In this paper, we introduce p$^3$VAE, a generative model that integrates a physical model which deterministically models some of the true underlying factors of variation in the data. To fully leverage our hybrid design, we enhance an existing semi-supervised optimization technique and introduce a new inference scheme that comes along meaningful uncertainty estimates. We apply p$^3$VAE to the pixel-wise classification of airborne hyperspectral images. Our experiments on simulated and real data demonstrate the benefits of our hybrid model against conventional machine learning models in terms of extrapolation capabilities and interpretability. In particular, we show that p$^3$VAE naturally has high disentanglement capabilities. Our code and data have been made publicly available at https://github.com/Romain3Ch216/p3VAE.

Vegetation canopy water (VCW) plays one connecting role in the coupling of terrestrial carbon-water cycles, and together with soil moisture, identifying the main changes of the terrestrial ecosystem. With regard to the remote sensing technologies, microwave-based VOD (vegetation optical depth) has been widely used as the VCW proxy. The feature of coarse resolution especially for microwave passive as well as mixing of vegetation water and biomass together would limit its more precise application. In spite of some efforts for the hyperspectral thermal and Global Navigation Satellite Systems (GNSS) limited in regional areas, as well as optical indices and initial efforts for AVHRR and SNAP from optical remote sensing, there are still no global operational and mature VCW product in the science community.To bridge the research gap, this study proposed the unified VCW retrieval algorithm for optical satellites, by improving the methodology developed with some first attempts (e.g., machine learning trained on PROSAIL radiative transfer model simulations). The improvements were implemented by comprehensively parametrizing the VCW related variables (i.e., leaf traits and soil background) in PROSAIL model, based on the largest open integrated global plants (TRY) and soil spectral (OSSL) databases, respectively. In PROSAIL, VCW is expressed as the product of green/leaf area per horizontal ground area (LAI, cm2/cm2) and leaf water content per green area (Cw, g/cm2). In the proposed algorithm, we bridge the quantitative relationship between VCW (LAI *Cw) and simulated TOC reflectance using the machine learning model.The algorithm was assessed for Landsat8 and Sentinel-2, using the ground measurements distributed over diverse climate and biome types worldwide. The results indicate that the developed VCW exhibits satisfactory performance, with R of 0.731 and unbiased RMSE (ubRMSE) of 0.055 g/cm2. Moreover, the proposed VCW achieves reasonable spatial patterns and seasonal changes over diverse vegetation types. The developed VCW product in this study is expected to provide new insights for monitoring global or regional vegetation water variations from optical satellites. With the strength of high spatial resolution compared to the microwave ones in the remote sensing community, the developed VCW would further facilitate the better hydro-ecological applications, especially for the terrestrial carbon-water couplings through vegetation, drought monitoring etc.