NASA’s Earth Surface Mineral Dust Source Investigation (EMIT) mission seeks to use spaceborne imaging spectroscopy (hyperspectral imaging) to map the mineralogy of arid dust source regions. Here we apply recent developments in Joint Characterization (JC) and the spectral Mixture Residual (MR) to explore the information content of data from this novel mission. Specifically, for a mosaic of 20 spectrally diverse scenes, we find: (1) a generalized three-endmember (Substrate, Vegetation, Dark; SVD) spectral mixture model is capable of capturing the preponderance (99% in three dimensions) of spectral variance with low misfit (99% pixels with <3.7% RMSE); (2) manifold learning (UMAP) is capable of identifying spatially coherent, physically interpretable clustering relationships in the spectral feature space; (3) UMAP yields results that are at least as informative when applied to the MR as when applied to raw reflectance; (4) SVD fraction information usefully contextualizes UMAP clustering relationships, and vice-versa (JC); and (5) when EMIT data are convolved to spectral response functions of multispectral instruments (Sentinel-2, Landsat 8/9, Planet SuperDove), SVD fractions correlate strongly across sensors, but UMAP clustering relationships for the EMIT hyperspectral feature space are far more informative than for simulated multispectral sensors. Implications are discussed for both the utility of EMIT data in the near-term and for the potential of high signal-to-noise (SNR) spaceborne imaging spectroscopy more generally, to transform the future of optical remote sensing in the years and decades to come.
Most applications of multispectral imaging are explicitly or implicitly dependent on the dimensionality and topology of the spectral mixing space. Mixing space characterization refers to the identification of salient properties of the set of pixel reflectance spectra comprising an image (or compilation of images). The underlying premise is that this set of spectra may be described as a low dimensional manifold embedded in a high dimensional vector space. Traditional mixing space characterization uses the linear dimensionality reduction offered by Principal Component Analysis to find projections of pixel spectra onto orthogonal linear subspaces, prioritized by variance. Here, we consider the potential for recent advances in nonlinear dimensionality reduction (specifically, manifold learning) to contribute additional useful information for multispectral mixing space characterization. We integrate linear and nonlinear methods through a novel approach called Joint Characterization (JC). JC is comprised of two components. First, spectral mixture analysis (SMA) linearly projects the high-dimensional reflectance vectors onto a 2D subspace comprising the primary mixing continuum of substrates, vegetation, and dark features (e.g., shadow and water). Second, manifold learning nonlinearly maps the high-dimensional reflectance vectors into a low-D embedding space while preserving manifold topology. The SMA output is physically interpretable in terms of material abundances. The manifold learning output is not generally physically interpretable, but more faithfully preserves high dimensional connectivity and clustering within the mixing space. Used together, the strengths of SMA may compensate for the limitations of manifold learning, and vice versa. Here, we illustrate JC through application to thematic compilations of 90 Sentinel-2 reflectance images selected from a diverse set of biomes and land cover categories. Specifically, we use globally standardized Substrate, Vegetation, and Dark (S, V, D) endmembers (EMs) for SMA, and Uniform Manifold Approximation and Projection (UMAP) for manifold learning. The value of each (SVD and UMAP) model is illustrated, both separately and jointly. JC is shown to successfully characterize both continuous gradations (spectral mixing trends) and discrete clusters (land cover class distinctions) within the spectral mixing space of each land cover category. These features are not clearly identifiable from SVD fractions alone, and not physically interpretable from UMAP alone. Implications are discussed for the design of models which can reliably extract and explainably use high-dimensional spectral information in spatially mixed pixels—a principal challenge in optical remote sensing.
more » « less- Award ID(s):
- 2226649
- PAR ID:
- 10497006
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 14
- Issue:
- 22
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 5688
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
more » « less
The Dynamic World product is a discrete land cover classification of Sentinel 2 reflectance imagery that is global in extent, retrospective to 2015, and updated continuously in near real time. The classifier is trained on a stratified random sample of 20,000 hand-labeled 5 × 5 km Sentinel 2 tiles spanning 14 biomes globally. Since the training data are based on visual interpretation of image composites by both expert and non-expert annotators, without explicit spectral properties specified in the class definitions, the spectral characteristics of the classes are not obvious. The objective of this study is to quantify the physical distinctions among the land cover classes by characterizing the spectral properties of the range of reflectance present within each of the Dynamic World classes over a variety of landscapes. This is achieved by comparing both the eight-class probability feature space (excluding snow) and the maximum probability class assignment (label) distributions to continuous land cover fraction estimates derived from a globally standardized spectral mixture model. Standardized substrate, vegetation, and dark (SVD) endmembers are used to unmix nine Sentinel 2 reflectance tiles from nine spectral diversity hotspots for comparison between the SVD land cover fraction continua and the Dynamic World class probability continua and class assignments. The variance partition for the class probability feature spaces indicates that eight of these nine hotspots are effectively five-dimensional to 95% of variance. Class probability feature spaces of the hotspots all show a tetrahedral form with probability continua spanning multiple classes. Comparison of SVD land cover fraction distributions with maximum probability class assignments (labels) and probability feature space distributions reveal a clear distinction between (1) physically and spectrally heterogeneous biomes characterized by continuous gradations in vegetation density, substrate albedo, and structural shadow fractions, and (2) more homogeneous biomes characterized by closed canopy vegetation (forest) or negligible vegetation cover (e.g., desert, water). Due to the ubiquity of spectrally heterogeneous biomes worldwide, the class probability feature space adds considerable value to the Dynamic World maximum probability class labels by offering users the opportunity to depict inherently gradational heterogeneous landscapes otherwise not generally offered with other discrete thematic classifications.
-
null (Ed.)Alaska has witnessed a significant increase in wildfire events in recent decades that have been linked to drier and warmer summers. Forest fuel maps play a vital role in wildfire management and risk assessment. Freely available multispectral datasets are widely used for land use and land cover mapping, but they have limited utility for fuel mapping due to their coarse spectral resolution. Hyperspectral datasets have a high spectral resolution, ideal for detailed fuel mapping, but they are limited and expensive to acquire. This study simulates hyperspectral data from Sentinel-2 multispectral data using the spectral response function of the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) sensor, and normalized ground spectra of gravel, birch, and spruce. We used the Uniform Pattern Decomposition Method (UPDM) for spectral unmixing, which is a sensor-independent method, where each pixel is expressed as the linear sum of standard reference spectra. The simulated hyperspectral data have spectral characteristics of AVIRIS-NG and the reflectance properties of Sentinel-2 data. We validated the simulated spectra by visually and statistically comparing it with real AVIRIS-NG data. We observed a high correlation between the spectra of tree classes collected from AVIRIS-NG and simulated hyperspectral data. Upon performing species level classification, we achieved a classification accuracy of 89% for the simulated hyperspectral data, which is better than the accuracy of Sentinel-2 data (77.8%). We generated a fuel map from the simulated hyperspectral image using the Random Forest classifier. Our study demonstrated that low-cost and high-quality hyperspectral data can be generated from Sentinel-2 data using UPDM for improved land cover and vegetation mapping in the boreal forest.more » « less
-
more » « less
A geologic map is both a visual depiction of the lithologies and structures occurring at the Earth’s surface and a representation of a conceptual model for the geologic history in a region. The work needed to capture such multifaced information in an accurate geologic map is time consuming. Remote sensing can complement traditional primary field observations, geochemistry, chronometry, and subsurface geophysical data in providing useful information to assist with the geologic mapping process. Two novel sources of remote sensing data are particularly relevant for geologic mapping applications: decameter-resolution imaging spectroscopy (spectroscopic imaging) and meter-resolution multispectral shortwave infrared (SWIR) imaging. Decameter spectroscopic imagery can capture important mineral absorptions but is frequently unable to spatially resolve important geologic features. Meter-resolution multispectral SWIR images are better able to resolve fine spatial features but offer reduced spectral information. Such disparate but complementary datasets can be challenging to integrate into the geologic mapping process. Here, we conduct a comparative analysis of spatial and spectral scaling for two such datasets: one Airborne Visible/Infrared Imaging Spectrometer—Classic (AVIRIS-classic) flightline, and one WorldView-3 (WV3) scene, for a geologically complex landscape in Anza-Borrego Desert State Park, California. To do so, we use a two-stage framework that synthesizes recent advances in the spectral mixture residual and joint characterization. The mixture residual uses the wavelength-explicit misfit of a linear spectral mixture model to capture low variance spectral signals. Joint characterization utilizes nonlinear dimensionality reduction (manifold learning) to visualize spectral feature space topology and identify clusters of statistically similar spectra. For this study area, the spectral mixture residual clearly reveals greater spectral dimensionality in AVIRIS than WorldView (99% of variance in 39 versus 5 residual dimensions). Additionally, joint characterization shows more complex spectral feature space topology for AVIRIS than WorldView, revealing information useful to the geologic mapping process in the form of mineralogical variability both within and among mapped geologic units. These results illustrate the potential of recent and planned imaging spectroscopy missions to complement high-resolution multispectral imagery—along with field and lab observations—in planning, collecting, and interpreting the results from geologic field work.
-
more » « less
Abstract In reduced-order modeling, complex systems that exhibit high state-space dimensionality are described and evolved using a small number of parameters. These parameters can be obtained in a data-driven way, where a high-dimensional dataset is projected onto a lower-dimensional basis. A complex system is then restricted to states on a low-dimensional manifold where it can be efficiently modeled. While this approach brings computational benefits, obtaining a good quality of the manifold topology becomes a crucial aspect when models, such as nonlinear regression, are built on top of the manifold. Here, we present a quantitative metric for characterizing manifold topologies. Our metric pays attention to non-uniqueness and spatial gradients in physical quantities of interest, and can be applied to manifolds of arbitrary dimensionality. Using the metric as a cost function in optimization algorithms, we show that optimized low-dimensional projections can be found. We delineate a few applications of the cost function to datasets representing argon plasma, reacting flows and atmospheric pollutant dispersion. We demonstrate how the cost function can assess various dimensionality reduction and manifold learning techniques as well as data preprocessing strategies in their capacity to yield quality low-dimensional projections. We show that improved manifold topologies can facilitate building nonlinear regression models.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs14225688
