Fast and Effective Techniques for LWIR Radiative Transfer Modeling: A Dimension-Reduction Approach

Westing, Nicholas; Borghetti, Brett J.; Gross, Kevin C.

doi:10.3390/rs11161866

Cited by 5 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training the DAC algorithm requires a library of worldwide atmospheric measurements, forward modeled with MOD-TRAN, forming a training set of diverse TUD vectors. Additionally, a low-dimensional representation of these TUD vectors is used to reduce model fitting complexity [17]. Next, the TUD vector dimension reduction process is reviewed and how this method fuses with DAC is explained.…”

Section: Methodsmentioning

confidence: 99%

Learning Set Representations for LWIR In-Scene Atmospheric Compensation

Westing

Gross²,

Borghetti

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Atmospheric compensation of long-wave infrared (LWIR) hyperspectral imagery is investigated in this article using set representations learned by a neural network. This approach relies on synthetic at-sensor radiance data derived from collected radiosondes and a diverse database of measured emissivity spectra sampled at a range of surface temperatures. The network loss function relies on LWIR radiative transfer equations to update model parameters. Atmospheric predictions are made on a set of diverse pixels extracted from the scene, without knowledge of blackbody pixels or pixel temperatures. The network architecture utilizes permutation-invariant layers to predict a set representation, similar to the work performed in point cloud classification. When applied to collected hyperspectral image data, this method shows comparable performance to Fast Line-of-Sight Atmospheric Analysis of Hypercubes-Infrared (FLAASH-IR), using an automated pixel selection approach. Additionally, inference time is significantly reduced compared to FLAASH-IR with predictions made on average in 0.24 s on a 128 pixel by 5000 pixel data cube using a mobile graphics card. This computational speed-up on a low-power platform results in an autonomous atmospheric compensation method effective for real-time, onboard use, while only requiring a diversity of materials in the scene.

show abstract

Section: Methodsmentioning

confidence: 99%

Learning Set Representations for LWIR In-Scene Atmospheric Compensation

Westing

Gross²,

Borghetti

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…While L KL enforces a prior distribution on the latent components, atmospheric state and TUD vector reconstruction error must also be minimized to provide a useful model. Similar to previous work [4], [26], the TUD vector reconstruction error is minimized using…”

Section: A Multimodal Generative Modelsmentioning

confidence: 99%

Multimodal Representation Learning and Set Attention for LWIR In-Scene Atmospheric Compensation

Westing

Gross

Borghetti

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

A multimodal generative modeling approach combined with permutation-invariant set attention is investigated in this paper to support long-wave infrared (LWIR) in-scene atmospheric compensation. The generative model can produce realistic atmospheric state vectors (T, H2O, O3) and their corresponding transmittance, upwelling radiance, and downwelling radiance (TUD) vectors by sampling a low-dimensional space. Variational loss, LWIR radiative transfer loss and atmospheric state loss constrain the low-dimensional space, resulting in lower reconstruction error compared to standard mean-squared error approaches. A permutation-invariant network predicts the generative model low-dimensional components from in-scene data, allowing for simultaneous estimates of the atmospheric state and TUD vector. Forward modeling the predicted atmospheric state vector results in a second atmospheric compensation estimate. Results are reported for collected LWIR data and compared against Fast Line-of-Sight Atmospheric Analysis of Hypercubes -Infrared (FLAASH-IR), demonstrating commensurate performance when applied to a target detection scenario. Additionally, an approximate 8 times reduction in detection time is realized using this neural network-based algorithm compared to FLAASH-IR. Accelerating the target detection pipeline while providing multiple atmospheric estimates is necessary for many real-world, time sensitive tasks.

show abstract

“…Using simple, statistical, nonlinear approximation instead of a complicated physical-based model in ANNs renders a more computationally efficient method to achieve a similar job to that of the physical-based model without significant accuracy loss [13][14][15][16][17][18]. These advantages have attracted an increasing number of remote sensing scientists to explore the possible replacement of the radiative transfer (RT) forward model or inversion with the ANN model in recent years [19][20][21][22][23][24][25][26]. Given the complicated nature of the RT model and its input, emulating a full RT model using only one ANN architecture is currently impossible.…”

Section: Introductionmentioning

confidence: 99%

“…Each study of ANN emulation generally focuses on one specific purpose and limit in some spectrum range, such as visible, long-IR, short-IR, or micro waves. Some ANN emulators have been combined with additional statistics analysis, such as principal component analysis, to reduce the dimensionality of the input features [26].…”

Section: Introductionmentioning

confidence: 99%

“…Overall, 278 features were prepared as FCDN_CRTM input, and CRTM Version 2.3.0 was used to generate BT references. Note that some researchers[26] have suggested reducing the dimensionality for input features using principle component analysis (PCA) or other methods to simplify the model and speed up the model training; however, in our case, we kept all 91-layer data as model inputs to include extensive and detailed atmosphere states without any energy loss.Table 1lists all input features and output BTs in the FCDN_CRTM. Summary of input features and output brightness temperatures (BTs) in the fully connected "deep" neural network algorithm with the Community Radiative Transfer Model (FCDN_CRTM).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Applying Deep Learning to Clear-Sky Radiance Simulation for VIIRS with Community Radiative Transfer Model—Part 2: Model Architecture and Assessment

Liang

Liu

2020

Remote Sensing

View full text Add to dashboard Cite

A fully connected “deep” neural network algorithm with the Community Radiative Transfer Model (FCDN_CRTM) is proposed to explore the efficiency and accuracy of reproducing the Visible Infrared Imaging Radiometer Suite (VIIRS) radiances in five thermal emission M (TEB/M) bands. The model was trained and tested in the nighttime global ocean clear-sky domain, in which the VIIRS observation minus CRTM (O-M) biases have been well validated in recent years. The atmosphere profile from the European Centre for Medium-Range Weather Forecasts (ECMWF) and sea surface temperature (SST) from the Canadian Meteorology Centre (CMC) were used as FCDN_CRTM input, and the CRTM-simulated brightness temperatures (BTs) were defined as labels. Six dispersion days’ data from 2019 to 2020 were selected to train the FCDN_CRTM, and the clear-sky pixels were identified by an enhanced FCDN clear-sky mask (FCDN_CSM) model, which was demonstrated in Part 1. The trained model was then employed to predict CRTM BTs, which were further validated with the CRTM BTs and the VIIRS sensor data record (SDR) for both efficiency and accuracy. With iterative refinement of the model design and careful treatment of the input data, the agreement between the FCDN_CRTM and the CRTM was generally good, including the satellite zenith angle and column water vapor dependencies. The mean biases of the FCDN_CRTM minus CRTM (F-C) were typically ~0.01 K for all five bands, and the high accuracy persisted during the whole analysis period. Moreover, the standard deviations (STDs) were generally less than 0.1 K and were consistent for approximately half a year, before they significantly degraded. The validation with VIIRS SDR data revealed that both the predicted mean biases and the STD of the VIIRS observation minus FCDN_CRTM (V-F) were comparable with the VIIRS minus direct CRTM simulation (V-C). Meanwhile, both V-F and V-C exhibited consistent global geophysical and statistical distribution, as well as stable long-term performance. Furthermore, the FCDN_CRTM processing time was more than 40 times faster than CRTM simulation. The highly efficient, accurate, and stable performances indicate that the FCDN_CRTM is a potential solution for global and real-time monitoring of sensor observation minus model simulation, particularly for high-resolution sensors.

show abstract

Fast and Effective Techniques for LWIR Radiative Transfer Modeling: A Dimension-Reduction Approach

Cited by 5 publications

References 21 publications

Learning Set Representations for LWIR In-Scene Atmospheric Compensation

Learning Set Representations for LWIR In-Scene Atmospheric Compensation

Multimodal Representation Learning and Set Attention for LWIR In-Scene Atmospheric Compensation

Applying Deep Learning to Clear-Sky Radiance Simulation for VIIRS with Community Radiative Transfer Model—Part 2: Model Architecture and Assessment

Contact Info

Product

Resources

About