- NSF-PAR ID:
- 10284831
- Date Published:
- Journal Name:
- Atmospheric Measurement Techniques
- Volume:
- 13
- Issue:
- 10
- ISSN:
- 1867-8548
- Page Range / eLocation ID:
- 5459 to 5480
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
null (Ed.)Abstract. We trained two Random Forest (RF) machine learning models for cloud mask andcloud thermodynamic-phase detection using spectral observations from Visible InfraredImaging Radiometer Suite (VIIRS)on board Suomi National Polar-orbiting Partnership (SNPP). Observations from Cloud-Aerosol Lidarwith Orthogonal Polarization (CALIOP) were carefully selected toprovide reference labels. The two RF models were trained for all-day anddaytime-only conditions using a 4-year collocated VIIRS and CALIOP dataset from2013 to 2016. Due to the orbit difference, the collocated CALIOP and SNPPVIIRS training samples cover a broad-viewing zenith angle range, which is agreat benefit to overall model performance. The all-day model uses three VIIRSinfrared (IR) bands (8.6, 11, and 12 µm), and the daytime model uses fiveNear-IR (NIR) and Shortwave-IR (SWIR) bands (0.86, 1.24, 1.38, 1.64, and 2.25 µm) together with the three IR bands to detect clear, liquid water, and icecloud pixels. Up to seven surface types, i.e., ocean water, forest, cropland,grassland, snow and ice, barren desert, and shrubland, were consideredseparately to enhance performance for both models. Detection of cloudypixels and thermodynamic phase with the two RF models was compared againstcollocated CALIOP products from 2017. It is shown that, when using a conservativescreening process that excludes the most challenging cloudy pixels forpassive remote sensing, the two RF models have high accuracy rates incomparison to the CALIOP reference for both cloud detection andthermodynamic phase. Other existing SNPP VIIRS and Aqua MODIS cloud mask andphase products are also evaluated, with results showing that the two RFmodels and the MODIS MYD06 optical property phase product are the top threealgorithms with respect to lidar observations during the daytime. During thenighttime, the RF all-day model works best for both cloud detection andphase, particularly for pixels over snow and ice surfaces. The present RFmodels can be extended to other similar passive instruments if trainingsamples can be collected from CALIOP or other lidars. However, the qualityof reference labels and potential sampling issues that may impact modelperformance would need further attention.more » « less
-
null (Ed.)Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed five different machine-learning (ML) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicate that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81%, 89%, and 85% over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML algorithms to NOAA’s Aerosol Detection Product (ADP), which is a product that classifies dust, smoke, and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule.more » « less
-
Satellite remote sensing of aerosol optical depth (AOD) is essential for detection, characterization, and forecasting of wildfire smoke. In this work, we evaluate the AOD (550 nm) retrievals during the extreme wildfire events over the western U.S. in September 2020. Three products are analyzed, including the Moderate-resolution Imaging Spectroradiometers (MODIS) Multi-Angle Implementation of Atmospheric Correction (MAIAC) product collections C6.0 and C6.1, and the NOAA-20 Visible Infrared Imaging Radiometer (VIIRS) AOD from the NOAA Enterprise Processing System (EPS) algorithm. Compared with the Aerosol Robotic Network (AERONET) data, all three products show strong linear correlations with MAIAC C6.1 and VIIRS presenting overall low bias (<0.06). The accuracy of MAIAC C6.1 is found to be substantially improved with respect to MAIAC C6.0 that drastically underestimated AOD over thick smoke, which validates the effectiveness of updates made in MAIAC C6.1 in terms of an improved representation of smoke aerosol optical properties. VIIRS AOD exhibits comparable uncertainty with MAIAC C6.1 with a slight tendency of increased positive bias over the AERONET AOD range of 0.5–3.0. Averaging coincident retrievals from MAIAC C6.1 and VIIRS provides a lower root mean square error and higher correlation than for the individual products, motivating the benefit of blending these datasets. MAIAC C6.1 and VIIRS are further compared to provide insights on their retrieval strategy. When gridded at 0.1° resolution, MAIAC C6.1 and VIIRS provide similar monthly AOD distribution patterns and the latter exhibits a slightly higher domain average. On daily scale, over thick plumes near fire sources, MAIAC C6.1 reports more valid retrievals where VIIRS tends to have retrievals designated as low or medium quality, which tends to be due to internal quality checks. Over transported smoke near scattered clouds, VIIRS provides better retrieval coverage than MAIAC C6.1 owing to its higher spatial resolution, pixel-level processing, and less strict cloud masking. These results can be used as a guide for applications of satellite AOD retrievals during wildfire events and provide insights on future improvement of retrieval algorithms under heavy smoke conditions.more » « less
-
The use of multispectral geostationary satellites to study aquatic ecosystems improves the temporal frequency of observations and mitigates cloud obstruction, but no operational capability presently exists for the coastal and inland waters of the United States. The Advanced Baseline Imager (ABI) on the current iteration of the Geostationary Operational Environmental Satellites, termed the
Series (GOES-R), however, provides sub-hourly imagery and the opportunity to overcome this deficit and to leverage a large repository of existing GOES-R aquatic observations. The fulfillment of this opportunity is assessed herein using a spectrally simplified, two-channel aquatic algorithm consistent with ABI wave bands to estimate the diffuse attenuation coefficient for photosynthetically available radiation, . First, an in situ ABI dataset was synthesized using a globally representative dataset of above- and in-water radiometric data products. Values ofwere estimated by fitting the ratio of the shortest and longest visible wave bands from the in situ ABI dataset to coincident,in situ data products. The algorithm was evaluated based on an iterative cross-validation analysis in which 80% of the dataset was randomly partitioned for fitting and the remaining 20% was used for validation. The iteration producing the median coefficient of determination ( ) value (0.88) resulted in a root mean square difference of , or 8.5% of the range in the validation dataset. Second, coincident mid-day images of central and southern California from ABI and from the Moderate Resolution Imaging Spectroradiometer (MODIS) were compared using Google Earth Engine (GEE). GEE default ABI reflectance values were adjusted based on a near infrared signal. Matchups between the ABI and MODIS imagery indicated similar spatial variability ( ) between ABI adjusted blue-to-red reflectance ratio values and MODIS default diffuse attenuation coefficient for spectral downward irradiance at 490 nm, , values. This work demonstrates that if an operational capability to provide ABI aquatic data products was realized, the spectral configuration of ABI would potentially support a sub-hourly, visible aquatic data product that is applicable to water-mass tracing and physical oceanography research. -
Domain adaptation techniques using deep neural networks have been mainly used to solve the distribution shift problem in homogeneous domains where data usually share similar feature spaces and have the same dimensionalities. Nevertheless, real world applications often deal with heterogeneous domains that come from completely different feature spaces with different dimensionalities. In our remote sensing application, two remote sensing datasets collected by an active sensor and a passive one are heterogeneous. In particular, CALIOP actively measures each atmospheric column. In this study, 25 measured variables/features that are sensitive to cloud phase are used and they are fully labeled. VIIRS is an imaging radiometer, which collects radiometric measurements of the surface and atmosphere in the visible and infrared bands. Recent studies have shown that passive sensors may have difficulties in prediction cloud/aerosol types in complicated atmospheres (e.g., overlapping cloud and aerosol layers, cloud over snow/ice surface, etc.). To overcome the challenge of the cloud property retrieval in passive sensor, we develop a novel VAE based approach to learn domain invariant representation that capture the spatial pattern from multiple satellite remote sensing data (VDAM), to build a domain invariant cloud property retrieval method to accurately classify different cloud types (labels) in the passive sensing dataset. We further exploit the weight based alignment method on the label space to learn a powerful domain adaptation technique that is pertinent to the remote sensing application. Experiments demonstrate our method outperforms other state-of-the-art machine learning methods and achieves higher accuracy in cloud property retrieval in the passive satellite dataset.more » « less