---
title: Extended VIIRS-like Artificial Nighttime Light (EVAL)
url: https://www.emergentmind.com/topics/extended-viirs-like-artificial-nighttime-light-eval
type: topic
---

# Extended VIIRS-like Artificial Nighttime Light (EVAL)

to=arxiv_search ็ตทรู 大奖彩票站  天天中彩票中大奖  大发快三彩票json
{"query":"Extended VIIRS-like Artificial Nighttime Light EVAL nighttime light VIIRS-like arXiv", "max_results": 10}
to=arxiv_search ՞նչ  重庆时时彩彩ೆjson
{"query":"nighttime light VIIRS-like reconstruction arXiv DMSP VIIRS EVAL", "max_results": 10}
to=arxiv_search 开号网址  彩神争霸可以json
{"query":"Translating multispectral imagery to nighttime imagery via conditional generative adversarial networks arXiv", "max_results": 5}
Extended VIIRS-like Artificial Nighttime Light (EVAL) denotes a set of related nighttime-remote-sensing constructs that seek to extend, reconstruct, calibrate, or enrich VIIRS-style observations beyond the native Suomi-NPP VIIRS record. In the cited literature, the term covers several distinct but connected objectives: translating Landsat 8 multispectral imagery to VIIRS-style nighttime radiance with a conditional GAN; proposing a roadmap for synthetic “VIIRS-style” annual composites from historical Landsat archives; reconstructing a China-wide 1986–2024 product with a two-stage deep architecture; calibrating DMSP-OLS into VIIRS-like format with unpaired cross-domain translation; generating visible multispectral nighttime products from calibrated ISS DSLR imagery; and defining a composite metric that combines orbital and human-vision sensitivities [2001.05848] [2508.00590] [2603.16385] [2108.07050] [2409.13111].

## 1. Conceptual scope and motivation

Nighttime satellite imagery has been applied in a wide range of fields, but its further application is hindered by limited understanding of how observed light intensity is formed and by uncertainty over whether it can be simulated [2001.05848]. A central motivation for EVAL is temporal extension: the NPP-VIIRS sensor provides high-quality NTL observations, yet its temporal coverage begins in 2012, which restricts long-term time-series studies that extend to earlier periods [2508.00590]. A second motivation is sensor incompatibility. DMSP-OLS and SNPP-VIIRS nighttime-light data are both widely used for monitoring urbanization, but discontinuities in calibration, spatial resolution, and saturation behavior hinder long-term fusion and interannual analysis [2306.02794] [2603.16385].

A third motivation is spectral incompleteness. VIIRS/DNB is panchromatic, and DMSP/OLS and SNPP/VIIRS-DNB are panchromatic and multispectral in the infrared but not at visible wavelengths, whereas ISS DSLR imagery can provide visible multispectral data across the world, albeit with substantial processing requirements [2108.07050]. Related work on colorizing panchromatic VIIRS/DNB into RGB proxies makes the same point in a different form: panchromatic radiance masks spectral signatures associated with lighting technologies and land-use types, limiting urban, health, and ecological analyses [2008.09303].

The literature therefore uses EVAL in more than one technical sense. Sometimes it denotes a raster reconstruction of VIIRS-like radiance from older sensors; sometimes it denotes a multispectral or RGB augmentation of panchromatic NTL; sometimes it denotes a physically calibrated ground-illumination product; and sometimes it denotes a composite metric designed to track both orbital radiance and human-vision radiance as lamp spectra evolve [2510.02977] [2409.13111]. This suggests that EVAL is best understood as a methodological family rather than a single universally standardized product.

## 2. Conditional translation from multispectral imagery to VIIRS-style radiance

A foundational precursor to later EVAL work is Huang et al.’s use of a modified pix2pix conditional GAN to translate Landsat 8 multispectral imagery to nighttime imagery [2001.05848]. The training data were gridded Landsat 8 and VIIRS image pairs over CONUS for 2016. Landsat 8 Collection-1 Tier 1 surface-reflectance Bands 4, 3, 2, and 5 were obtained via Google Earth Engine; each scene was atmospherically corrected, orthorectified, cloud-masked, median-composited per pixel, and resampled to 100 m. The VIIRS NPP-VJ1 DNB annual stable-light composite for 2016 was downloaded from NOAA/NCEI; stray light, lightning, lunar and cloud contamination were removed, transient lights and non-lights were screened, and radiance values were capped at 300 nW cm$^{-2}$ sr$^{-1}$. Both datasets were reprojected to a common WGS84 100 m grid, tiled into $0.625^\circ \times 0.625^\circ$ grids, and converted into aligned $256 \times 256$ patches [2001.05848].

The network used a U-Net generator and a $70 \times 70$ PatchGAN discriminator. The generator comprised seven convolutional encoder blocks, one 512-filter bottleneck convolution, and seven deconvolutional decoder blocks with skip-connections. Input channels were configured as RGB only, RGB + IR, or RGB + IR + SM, where the “social media” channel was derived from geotagged tweets from July to December 2016, aggregated into $\sim 450$ m cells, log-transformed, low-pass filtered with a $3 \times 3$ kernel, resampled to 100 m, and normalized to $[-1,1]$. The discriminator used five convolutional blocks with LeakyReLU $(\alpha = 0.2)$ and a final Sigmoid patch-probability map. The objective combined the adversarial loss and an $L_1$ reconstruction penalty with $\lambda = 100$:
$$
L_{GAN}(G,D)=E_{x,y}[\log D(x,y)] + E_x[\log(1-D(x,G(x)))]
$$
$$
L_{L1}(G)=E_{x,y}[\|y-G(x)\|_1]
$$
$$
G^*=\arg\min_G \max_D \{L_{GAN}(G,D)+\lambda L_{L1}(G)\}
$$
Training used 1000 screened CONUS grids, selected by total VIIRS radiance $> 8000$ nW cm$^{-2}$ sr$^{-1}$, with 800 for training and 200 for validation. Hyperparameters followed the original pix2pix setup: batch size 1, Adam with $\mathrm{lr}=0.0002$, $\beta_1=0.5$, $\beta_2=0.999$, and 200 epochs, with the first 100 at constant learning rate and the next 100 linearly decayed to zero [2001.05848].

The quantitative results established the practical viability of multispectral-to-nighttime translation.

| Scenario | Deu / Dma | $R_{ncc}$ |
|---|---:|---:|
| RGB | 31.431 / 41.947 | 0.492 |
| RGB + IR | 24.872 / 31.826 | 0.647 |
| RGB + IR + SM | 19.214 / 23.234 | 0.821 |

Visual comparison showed that RGB-only input failed to reproduce urban brightness, RGB + IR captured built-up areas but missed intensity cores, and RGB + IR + SM most closely matched VIIRS ground truth, including shadows, urban cores, and noise suppression [2001.05848]. In the EVAL context, Huang et al. explicitly proposed training on the overlapping Landsat 8/VIIRS era and applying the generator to historical Landsat 4/5/7 surface reflectance since 1984 to create synthetic “VIIRS-style” annual composites back to 1984. They also identified multi-sensor calibration, light desaturation, and temporal gap filling as downstream uses [2001.05848].

## 3. Reconstruction frameworks for long time series

Subsequent EVAL-oriented work moved from proof-of-concept translation to systematic time-series reconstruction. In the China EVAL product, the reconstruction task is decomposed into a two-stage process: a construction stage and a refinement stage [2508.00590]. The construction stage uses a U-Net encoder-decoder with a ResNet-50 encoder, a Structure Residual Fusion module, and a Multi-Scale Aggregator with dilated convolutions at rates $\{1,4,9\}$. It is optimized with mean squared error on log-transformed VIIRS radiance,
$$
\mathcal{L}_{\mathrm{MSE}}=\frac{1}{n}\sum_{i=1}^n (y_i-\hat y_i)^2,\quad y_i=\ln(\mathrm{VIIRS}_i),
$$
while the refinement stage uses a Dual Feature Refiner guided by high-resolution impervious surface masks and Cross-Resolution Local Attention, producing a residual correction so that
$$
\hat Y=\hat Y_{\mathrm{HFD}}+R_{\mathrm{DFR}}.
$$
The refinement loss is $L_1$ on log-space prediction. Inputs include Harmonized Global NTL DMSP-OLS, PANDA-China NTL, NPP-VIIRS annual composites, Landsat surface reflectance, GAIA annual impervious masks, and socioeconomic data. Preprocessing includes annual 10th-percentile Landsat compositing, OLI to TM/ETM+ harmonization via Roy et al. (2016) coefficients, resampling to 250 m, log-transforming VIIRS targets during training, per-band min–max normalization to $[0,1]$, and sampling 20,000 patches of $512 \times 512$ pixels with an 80/10/10 train/val/test split by province [2508.00590].

A different paradigm appears in the CUT-based unpaired cross-domain calibration of DMSP to VIIRS [2603.16385]. Here the objective is not paired Landsat-to-VIIRS translation but DMSP-to-VIIRS transformation using 2012–2013 overlap. DMSP annual composites from 1992–2013 are upsampled from 30″ to 15″ by bilinear interpolation, log-transformed, clipped at the 0.1%–99.9% percentiles, normalized to uint8, tiled into non-overlapping $256 \times 256$ patches, and filtered to exclude patches with less than 30% land, centered at $|\mathrm{lat}|>60^\circ$, or radiometrically dark or uniform. The generator is a ResNet-style image-to-image network with 9 residual blocks; the discriminator is a $70 \times 70$ PatchGAN; and the defining component is PatchNCE contrastive learning over generator features extracted from layers $l \in \{0,4,8,12,16\}$, with $P=256$ spatial samples per layer and temperature $\tau = 0.07$. The total objective is
$$
\mathcal L_{\rm total}=\lambda_{\rm GAN}\,\mathcal L_{\rm GAN}+\lambda_{\rm NCE}\,\mathcal L_{\rm NCE},
$$
with $\lambda_{\rm GAN}=1.0$ and $\lambda_{\rm NCE}=1.0$ [2603.16385].

Singh et al.’s NDUI+ work addresses inter-sensor normalization from a different direction: learning a nonlinear mapping from raw VIIRS DNB radiance to DMSP-OLS–style radiance using 2012 overlap, then fusing the calibrated VIIRS output with Landsat 7 NDVI into a 30 m annual urban index from 1999 to the present [2306.02794]. The globe is divided into $5^\circ \times 5^\circ$ blocks, a separate model is trained for each block, and the Swin Transformer is chosen after benchmarking 17 super-resolution and sensor-fusion networks in the UT-CDS suite. The loss combines MSE with a small gradient penalty for smoothness, with $\lambda \approx 10^{-4}$. Although NDUI+ is not itself a radiance-only EVAL product, it exemplifies the same core design pattern: one-shot overlap transfer, regional tuning, and multi-source harmonization of DMSP and VIIRS into a longer, higher-resolution annual series [2306.02794].

## 4. Validation, quantitative performance, and temporal consistency

Quantitative evaluation is central to EVAL because the target variables differ across formulations: radiance, RGB proxies, urban indices, skyglow, and ground illuminance. In the China EVAL dataset, pixel-scale evaluation on the 2012 test set in log-space compared EVAL with LongNTL and SVNL, using $R^2$, RMSE, PSNR, and UIQI [2508.00590].

| Product | Pixel-level results (2012) | Aggregate or correlation result |
|---|---|---|
| LongNTL | $R^2=0.596$, RMSE $=1.448$, PSNR $=43.50$, UIQI $=0.680$ | GDP corr. $=0.8622$, Population corr. $=0.8846$ |
| SVNL | $R^2=0.686$, RMSE $=1.278$, PSNR $=44.59$, UIQI $=0.773$ | GDP corr. $=0.8997$, Population corr. $=0.9271$ |
| EVAL | $R^2=0.809$, RMSE $=0.997$, PSNR $=46.75$, UIQI $=0.897$ | GDP corr. $=0.9681$, Population corr. $=0.9402$ |

The same work reported that EVAL boosts $R^2$ from 0.686 to 0.809 and lowers RMSE from 1.278 to 0.997 relative to SVNL; at the city aggregate scale across 2,891 counties in China for 2012, EVAL reached $R^2=0.975$ with RMSE $= 1{,}394.4$ W/cm$^2\cdot$sr, and trend comparison showed that EVAL avoided the jump seen in other VIIRS-like products at the 2012 transition [2508.00590].

The CUT-based DMSP-to-VIIRS calibration also reported strong held-out consistency. On the 15% test patches, Pearson $r=0.93$, Spearman $\rho=0.91$, $R^2=0.87$, concordance correlation coefficient $=0.89$, RMSE $=8.91$, MAE $=5.64$, and SSIM $=0.79$; relative to linear regression, histogram matching, and CycleGAN, CUT had the highest reported $R^2$ and Spearman $\rho$, and lower training time than CycleGAN. Error stratification showed high accuracy with $R^2>0.88$ in background and rural areas, degrading to $R^2=0.68$ in highly saturated urban cores [2603.16385].

For NDUI+, model selection was based on PSNR and SSIM on held-out 2012 patches, with the Swin Transformer yielding $\mathrm{SSIM} \approx 0.92$ versus 0.85 for the next-best model. Independent validation over Austin in 2020 showed $R^2=0.78$ and MAE $\approx 0.12$ in normalized units against Sentinel-2 Dynamic World built-up probability, while comparison with Ghosh et al. (2021) over Las Vegas indicated that the new dataset recovered the post-2016 radiance rebound [2306.02794]. Taken together, these studies indicate that “VIIRS-like” quality is typically assessed through some combination of pixelwise fidelity, structural similarity, aggregate temporal continuity, and correlation with socioeconomic or urban-form variables.

## 5. Spectral, photometric, and illuminance-oriented extensions

One branch of EVAL research departs from radiance reconstruction and instead extends VIIRS-like products into the visible spectral domain. The calibration of DSLR images from the International Space Station is a multi-stage process: Decodification, Linearity correction, Flat field/Vignetting, Spectral characterization of the channels, Astrometric calibration/georeferencing, Photometric calibration (stars)/Radiometric correction, and Transmittance correction [2108.07050]. RAW NEF files are converted with DCRAW into 16-bit linear counts for the four Bayer subchannels; high-DN nonlinearity is corrected with an empirical function $C_{\mathrm{lin}}(\mathrm{ISO},DN_{\mathrm{raw}})$; flat-field gains are derived from uniform lambertian targets; spectral response functions are linked to Johnson photometry through synthesized DSLR magnitudes; georeferencing uses Astrometry.net followed by ground control points; and radiometric scaling is derived from star-field regression. The worked Madrid example reported a final green-band map ranging from 0 to 300 nW·sr$^{-1}$·cm$^{-2}$, per-pixel uncertainty of approximately 5% from star-fit residuals and 2–3% from the atmospheric model, and georeferencing RMSE of approximately 4 pixels, corresponding to 0.4 km at nadir [2108.07050]. The same workflow proposes storing each band as georeferenced 16-bit GeoTIFF or NetCDF, followed by mosaicking and temporal compositing into a time series compatible with VIIRS DNB at 0.5 km resolution [2108.07050].

A second spectral extension is panchromatic-to-RGB colorization of VIIRS/DNB [2008.09303]. In that framework, each pixel is represented by a predictor vector consisting of panchromatic radiance, two neighborhood-difference terms, and two HBASE built-up statistics, and separate models are trained for $R$, $G$, and $B$. The candidate methods are multiple linear regression, Nadaraya–Watson kernel regression, random forest regression with $T=32$, and the elastic-map manifold method on a $12 \times 12$ grid with bending penalty tuned over $\{10^{-5},10^{-4},\dots,1\}$. Training data came from eight metropolitan areas—Atlanta, Beijing, Haifa, Khabarovsk, London, Naples, Nashville, and Tianjin—using georeferenced ISS photographs and leave-one-city-out evaluation. Random forest and kernel regression achieved the highest training-set correlations and lowest WMSE, linear regression generalized best on unseen cities with test Pearson $r$ in the range 0.75–0.85, and elastic-map models had the highest consistency between train and test metrics [2008.09303]. In EVAL terms, this line of work treats the VIIRS-like product as a spectrally enriched proxy rather than a direct replacement for DNB radiance.

A third extension defines EVAL as a composite metric that explicitly mixes orbital and human-vision sensitivities as lighting technology changes [2409.13111]. Using lamp-type spectral libraries $\Phi_{\lambda,k}$, total lumen flux per unit area $N(t)$, lamp fractions $\gamma_k(t)$, the VIIRS DNB response, and human luminous-efficiency functions, the proposed metric is
$$
\mathrm{EVAL}(t)=N(t)\sum_{k=1}^K \gamma_k(t)\bigl[w_D H_{D,k}+w_V H_{V,\alpha,k}\bigr].
$$
Its rate of change inherits both the growth of total lumens and the evolution of lamp mixture. In the VIIRS-vs-Globe-at-Night application, the paper argues that the reported divergence between approximately 2.2%/yr in VIIRS-DNB radiance and approximately 9.6%/yr in GAN-derived artificial radiance could be explained by spectral changes alone under some adaptation conditions, whereas photopic reconciliation would require GAN-specific light sources not captured by VIIRS-DNB [2409.13111]. Here EVAL is not a raster reconstruction but a spectrally corrected time-series functional.

A fourth extension is Otus 3, which transforms VIIRS-based radiance into physically interpretable maps of ground illuminance and skyglow [2510.02977]. Using Black Marble monthly and yearly composites, angular-dependence products, halo removal, and calibration against 139 Ninox sky-brightness sites across metropolitan France, the model infers ground luminous emittance, direct artificial illuminance, and artificial skyglow illuminance under clear-sky and low-cloud scenarios. The key inversion uses a Garstang-type emission model,
$$
\mathrm{RAD}(\theta)=k\cdot \mathrm{GLE}\cdot [2G(1-F)\cos\theta + 0.554F\theta^4]/(2\pi),
$$
from which direct artificial illuminance follows as $\mathrm{ADI}=\mathrm{GLE}(1-F)$, while diffuse skyglow illuminance is obtained by convolving the GLE map with scattering kernels. The resulting France maps showed a 23% reduction in middle-of-night artificial ground illuminance between 2013–2018 and 2019–2024 [2510.02977]. In this usage, EVAL denotes a calibrated photometric product, not merely a VIIRS-like radiance field.

## 6. Limitations, misconceptions, and open directions

A common misconception is to treat EVAL as a single standardized dataset. The literature instead assigns the label to several distinct constructs: radiance reconstruction from Landsat or DMSP, visible multispectral calibration from ISS imagery, RGB colorization of panchromatic VIIRS, urban-index fusion products, illuminance maps, and a spectral composite metric [2001.05848] [2108.07050] [2008.09303] [2510.02977] [2409.13111]. A plausible implication is that comparisons among EVAL studies require attention to the target variable itself: top-of-atmosphere radiance, log-transformed VIIRS proxy, RGB channel intensity, NDUI scalar, zenith luminance, or ground illuminance.

Method-specific limitations are explicit. Huang et al.’s cGAN was trained on CONUS, so global application requires regional retraining or domain adaptation; it used annual composites only; and the social-media auxiliary channel may under-represent certain areas because of Twitter skew [2001.05848]. In NDUI+, there is no extension before 1999, the output is a single scalar urban–vegetation index rather than subclass labels, the VIIRS-to-DMSP mapping is assumed stationary after 2012, and the 2015 non-urban mask reused for earlier years may over-mask rapidly urbanizing areas [2306.02794]. In the CUT-based calibration, performance degrades in highly saturated urban cores, despite strong global metrics [2603.16385]. In the France illuminance framework, direct illuminance uncertainty is approximately 49%, the minimum detectable ADI is approximately 25 mlux, and single-value aerosol and emission-law classes ignore local heterogeneity [2510.02977].

Open directions are also stated directly in the source material. The Landsat-to-VIIRS roadmap proposes alternative auxiliary sources such as OpenStreetMap and mobile-phone data, as well as recurrent cGANs and atmospheric emissions data [2001.05848]. The ISS calibration workflow points toward multispectral, epoch-tagged EVAL products extending visible artificial-light records back two decades and complementing panchromatic VIIRS DNB [2108.07050]. The Otus 3 study recommends integrating SDGSAT-1 higher-resolution multispectral nighttime data, expanding Ninox measurements to ground lux, and dynamically ingesting local AOD and cloud statistics [2510.02977]. Across these variants, the unifying research program is not a single algorithmic template but a persistent attempt to reconcile temporal depth, sensor continuity, spectral fidelity, and physical interpretability in nighttime-light remote sensing.

Source: https://www.emergentmind.com/topics/extended-viirs-like-artificial-nighttime-light-eval