skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Performance Assessment of Four Data-Driven Machine Learning Models: A Case to Generate Sentinel-2 Albedo at 10 Meters
High-resolution albedo has the advantage of a higher spatial scale from tens to hundreds of meters, which can fill the gaps of albedo applications from the global scale to the regional scale and can solve problems related to land use change and ecosystems. The Sentinel-2 satellite provides high-resolution observations in the visible-to-NIR bands, giving possibilities to generate a high-resolution surface albedo at 10 m. This study attempted to evaluate the performance of the four data-driven machine learning algorithms (i.e., random forest (RF), artificial neural network (ANN), k-nearest neighbor (KNN), and XGBoost (XGBT)) for the generation of a Sentinel-2 albedo over flat and rugged terrain. First, we used the RossThick-LiSparseR model and the 3D discrete anisotropic radiative transfer (DART) model to build the narrowband surface reflectance and broadband surface albedo, which acted as the training and testing datasets over flat and rugged terrain. Second, we used the training and testing datasets to drive the four machine learning models, and evaluated the performance of these machine learning models for the generation of Sentinel-2 albedo. Finally, we used the four machine learning models to generate a Sentinel-2 albedo and compared them with in situ albedos to show the models’ application potentials. The results show that these machine learning models have great performance in estimating Sentinel-2 albedos at a 10 m spatial scale. The comparison with in situ albedos shows that the random forest model outperformed the others in estimating a high-resolution surface albedo based on Sentinel-2 datasets over the flat and rugged terrain, with an RMSE smaller than 0.0308 and R2 larger than 0.9472.  more » « less
Award ID(s):
1655499
PAR ID:
10508544
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Remote Sensing
Volume:
15
Issue:
10
ISSN:
2072-4292
Page Range / eLocation ID:
2684
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, Frontiers in Earth Science)
    null (Ed.)
    Coastal mangrove forests provide important ecosystem goods and services, including carbon sequestration, biodiversity conservation, and hazard mitigation. However, they are being destroyed at an alarming rate by human activities. To characterize mangrove forest changes, evaluate their impacts, and support relevant protection and restoration decision making, accurate and up-to-date mangrove extent mapping at large spatial scales is essential. Available large-scale mangrove extent data products use a single machine learning method commonly with 30 m Landsat imagery, and significant inconsistencies remain among these data products. With huge amounts of satellite data involved and the heterogeneity of land surface characteristics across large geographic areas, finding the most suitable method for large-scale high-resolution mangrove mapping is a challenge. The objective of this study is to evaluate the performance of a machine learning ensemble for mangrove forest mapping at 20 m spatial resolution across West Africa using Sentinel-2 (optical) and Sentinel-1 (radar) imagery. The machine learning ensemble integrates three commonly used machine learning methods in land cover and land use mapping, including Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network (NN). The cloud-based big geospatial data processing platform Google Earth Engine (GEE) was used for pre-processing Sentinel-2 and Sentinel-1 data. Extensive validation has demonstrated that the machine learning ensemble can generate mangrove extent maps at high accuracies for all study regions in West Africa (92%–99% Producer’s Accuracy, 98%–100% User’s Accuracy, 95%–99% Overall Accuracy). This is the first-time that mangrove extent has been mapped at a 20 m spatial resolution across West Africa. The machine learning ensemble has the potential to be applied to other regions of the world and is therefore capable of producing high-resolution mangrove extent maps at global scales periodically. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Remote Sensing)
    null (Ed.)
    Surface albedo is a fundamental radiative parameter as it controls the Earth’s energy budget and directly affects the Earth’s climate. Satellite observations have long been used to capture the temporal and spatial variations of surface albedo because of their continuous global coverage. However, space-based albedo products are often affected by errors in the atmospheric correction, multi-angular bi-directional reflectance distribution function (BRDF) modelling, as well as spectral conversions. To validate space-based albedo products, an in situ tower albedometer is often used to provide continuous “ground truth” measurements of surface albedo over an extended area. Since space-based albedo and tower-measured albedo are produced at different spatial scales, they can be directly compared only for specific homogeneous land surfaces. However, most land surfaces are inherently heterogeneous with surface properties that vary over a wide range of spatial scales. In this work, tower-measured albedo products, including both directional hemispherical reflectance (DHR) and bi-hemispherical reflectance (BHR), are upscaled to coarse satellite spatial resolutions using a new method. This strategy uses high-resolution satellite derived surface albedos to fill the gaps between the albedometer’s field-of-view (FoV) and coarse satellite scales. The high-resolution surface albedo is generated from a combination of surface reflectance retrieved from high-resolution Earth Observation (HR-EO) data and moderate resolution imaging spectroradiometer (MODIS) BRDF climatology over a larger area. We implemented a recently developed atmospheric correction method, the Sensor Invariant Atmospheric Correction (SIAC), to retrieve surface reflectance from HR-EO (e.g., Sentinel-2 and Landsat-8) top-of-atmosphere (TOA) reflectance measurements. This SIAC processing provides an estimated uncertainty for the retrieved surface spectral reflectance at the HR-EO pixel level and shows excellent agreement with the standard Landsat 8 Surface Reflectance Code (LaSRC) in retrieving Landsat-8 surface reflectance. Atmospheric correction of Sentinel-2 data is vastly improved by SIAC when compared against the use of in situ AErosol RObotic NETwork (AERONET) data. Based on this, we can trace the uncertainty of tower-measured albedo during its propagation through high-resolution EO measurements up to coarse satellite scales. These upscaled albedo products can then be compared with space-based albedo products over heterogeneous land surfaces. In this study, both tower-measured albedo and upscaled albedo products are examined at Ground Based Observation for Validation (GbOV) stations (https://land.copernicus.eu/global/gbov/), and used to compare with satellite observations, including Copernicus Global Land Service (CGLS) based on ProbaV and VEGETATION 2 data, MODIS and multi-angle imaging spectroradiometer (MISR). 
    more » « less
  3. ; ; ; (, Remote Sensing)
    Surface albedo is of crucial interest in land–climate interaction studies, since it is a key parameter that affects the Earth’s radiation budget. The temporal and spatial variation of surface albedo can be retrieved from conventional satellite observations after a series of processes, including atmospheric correction to surface spectral bi-directional reflectance factor (BRF), bi-directional reflectance distribution function (BRDF) modelling using these BRFs, and, where required, narrow-to-broadband albedo conversions. This processing chain introduces errors that can be accumulated and then affect the accuracy of the retrieved albedo products. In this study, the albedo products derived from the multi-angle imaging spectroradiometer (MISR), moderate resolution imaging spectroradiometer (MODIS) and the Copernicus Global Land Service (CGLS), based on the VEGETATION and now the PROBA-V sensors, are compared with albedometer and upscaled in situ measurements from 19 tower sites from the FLUXNET network, surface radiation budget network (SURFRAD) and Baseline Surface Radiation Network (BSRN) networks. The MISR sensor onboard the Terra satellite has 9 cameras at different view angles, which allows a near-simultaneous retrieval of surface albedo. Using a 16-day retrieval algorithm, the MODIS generates the daily albedo products (MCD43A) at a 500-m resolution. The CGLS albedo products are derived from the VEGETATION and PROBA-V, and updated every 10 days using a weighted 30-day window. We describe a newly developed method to derive the two types of albedo, which are directional hemispherical reflectance (DHR) and bi-hemispherical reflectance (BHR), directly from three tower-measured variables of shortwave radiation: downwelling, upwelling and diffuse shortwave radiation. In the validation process, the MISR, MODIS and CGLS-derived albedos (DHR and BHR) are first compared with tower measured albedos, using pixel-to-point analysis, between 2012 to 2016. The tower measured point albedos are then upscaled to coarse-resolution albedos, based on atmospherically corrected BRFs from high-resolution Earth observation (HR-EO) data, alongside MODIS BRDF climatology from a larger area. Then a pixel-to-pixel comparison is performed between DHR and BHR retrieved from coarse-resolution satellite observations and DHR and BHR upscaled from accurate tower measurements. The experimental results are presented on exploring the parameter space associated with land cover type, heterogeneous vs. homogeneous and instantaneous vs. time composite retrievals of surface albedo. 
    more » « less
  4. ; ; ; (, Remote Sensing)
    null (Ed.)
    Leaf area index (LAI) is an important biophysical indicator of forest health that is linearly related to productivity, serving as a key criterion for potential nutrient management. A single equation was produced to model surface reflectance values captured from the Sentinel-2 Multispectral Instrument (MSI) with a robust dataset of field observations of loblolly pine (Pinus taeda L.) LAI collected with a LAI-2200C plant canopy analyzer. Support vector machine (SVM)-supervised classification was used to improve the model fit by removing plots saturated with aberrant radiometric signatures that would not be captured in the association between Sentinel-2 and LAI-2200C. The resulting equation, LAI = 0.310SR − 0.098 (where SR = the simple ratio between near-infrared (NIR) and red bands), displayed good performance ( R 2 = 0.81, RMSE = 0.36) at estimating the LAI for loblolly pine within the analyzed region at a 10 m spatial resolution. Our model incorporated a high number of validation plots (n = 292) spanning from southern Virginia to northern Florida across a range of soil textures (sandy to clayey), drainage classes (well drained to very poorly drained), and site characteristics common to pine forest plantations in the southeastern United States. The training dataset included plot-level treatment metrics—silviculture intensity, genetics, and density—on which sensitivity analysis was performed to inform model fit behavior. Plot density, particularly when there were ≤618 trees per hectare, was shown to impact model performance, causing LAI estimates to be overpredicted (to a maximum of X i + 0.16). Silviculture intensity (competition control and fertilization rates) and genetics did not markedly impact the relationship between SR and LAI. Results indicate that Sentinel-2’s improved spatial resolution and temporal revisit interval provide new opportunities for managers to detect within-stand variance and improve accuracy for LAI estimation over current industry standard models. 
    more » « less
  5. ; ; ; ; ; (, Remote Sensing)
    Melt and supraglacial lakes are precursors to ice shelf collapse and subsequent accelerated ice sheet mass loss. We used data from the Landsat 8 and Sentinel-2 satellites to develop a threshold-based method for detection of lakes found on the Antarctic ice shelves, calculate their depths and thus their volumes. To achieve this, we focus on four key areas: the Amery, Roi Baudouin, Nivlisen, and Riiser-Larsen ice shelves, which are all characterized by extensive surface meltwater features. To validate our products, we compare our results against those obtained by an independent method based on a supervised classification scheme (e.g., Random Forest algorithm). Additional verification is provided by manual inspection of results for nearly 1000 Landsat 8 and Sentinel-2 images. Our dual-sensor approach will enable constructing high-resolution time series of lake volumes. Therefore, to ensure interoperability between the two datasets, we evaluate depths from contemporaneous Landsat 8 and Sentinel-2 image pairs. Our assessments point to a high degree of correspondence, producing an average R2 value of 0.85, no bias, and an average RMSE of 0.2 m. We demonstrate our method’s ability to characterize lake evolution by presenting first evidence of drainage events outside of the Antarctic Peninsula on the Amery Ice shelf. The methods presented here pave the way to upscaling throughout the Landsat 8 and Sentinel-2 observational record across Antarctica to produce a first-ever continental dataset of supraglacial lake volumes. Such a dataset will improve our understanding of the influence of surface hydrology on ice shelf stability, and thus, future projections of Antarctica’s contribution to sea level rise. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email