Mr. Zhongzheng Hu Profile

Zhongzheng Hu

at CRESDA

SPIE Involvement:

Author

Publications (2)

Proceedings Article | 5 November 2020 Paper

Preliminary study on the multispectral measurement simulations of polarized scanning atmospheric corrector image

Weizhen Hou, Yanqing Xie, Zhengqiang Li, Hongji Yang, Zhongzheng Hu, Chaoyu Song, Jun Lin, Honglian Huang, Xuefeng Lei, Bangyu Ge, Yan Ma

Proceedings Volume 11566, 115660E (2020) https://doi.org/10.1117/12.2577500

KEYWORDS: Polarization, Satellites, Atmospheric modeling, Aerosols, Satellite imaging, Radiative transfer

Read Abstract +

Environment-2 (HJ-2) A/B satellites will be launched in 2020, which are expected to work as the successors of Environment-1 (HJ-1) satellites in Chinese Environment and Disaster Monitoring and Prediction Satellite Constellation. A new space-borne instrument called Polarized Scanning Atmospheric Corrector (PSAC) also will be onboard HJ-2 satellites, aiming to provide the atmospheric properties for synchronous atmospheric correction of the main sensors, such as the charge-coupled device cameras onboard the same satellite. PSAC is a cross-track scanning polarimeter with polarized channels from near-ultraviolet to shortwave infrared, centered in 410, 443, 555, 670, 865, 910, 1380, 1610 and 2250 nm. In order to test the performance of inversion algorithms and software modules, synthetic data simulated by the vector radiative transfer is indispensable. In this paper, the regional simulation of PSAC multispectral measurements are preliminarily studied, and the Unified Linearized Vector Radiative Transfer Model (UNL-VRTM) has been used as the forward model. For the observation geometries, the viewing zenith angles are calculated by the linear interpolation over the cross-track scanning angle range from west to east, while the viewing azimuth angle are simulated by following the azimuth angle distribution of other corresponding satellite. By taking the vegetated surface type as an example, the multispectral Lambertian surface reflectance and wavelength-independent BPDF model are used in the forward simulation, and different aerosol optical depth with fine-dominated and coarse-dominated aerosols are considered. In this way, the multispectral measurements can be obtained by the forward simulations over a regional grid with the predefined latitude and longitude, and further analysis are carried out based on the synthetic data. Thus, this study can provide key support to the testbed of inversion algorithms and software modules before and after the satellite launch.

SPIE Journal Paper | 8 September 2020 Open Access

Global chlorophyll-a concentration estimation from moderate resolution imaging spectroradiometer using convolutional neural networks

Bowen Yu, Linlin Xu, Jun-huan Peng, Zhongzheng Hu, Alexander Wong

JARS, Vol. 14, Issue 03, 034520, (September 2020) https://doi.org/10.1117/12.10.1117/1.JRS.14.034520

KEYWORDS: MODIS, Data modeling, Image resolution, Satellites, Remote sensing, Convolution, Convolutional neural networks, Neurons, Machine learning, Statistical modeling

Read Abstract +

The accurate estimation of global chlorophyll-a (Chla) concentration from the large remote sensing data in a timely manner is crucial for supporting various applications. Moderate resolution imaging spectroradiometer (MODIS) is one of the most widely used earth observation data sources, which has the characteristics of global coverage, high spectral resolution, and short revisit period. So the estimation of global Chla concentration from MODIS imagery in a fast and accurate manner is significant. Nevertheless, the estimation of Chla concentration from MODIS using traditional machine learning approaches is challenging due to their limited modeling capability to capture the complex relationship between MODIS spatial–spectral observations and the Chla concentration, and also their low computational efficiency to address large MODIS data in a timely manner. We, therefore, explore the potential of deep convolutional neural networks (CNNs) for Chla concentration estimation from MODIS imagery. The Ocean Color Climate Change Initiative (OC-CCI) Chla concentration image is used as ground truth because it is a well-recognized Chla concentration product that is produced by assimilating different satellite data through a complex data processing steps. A total of 12 monthly OC-CCI global Chla concentration maps and the associated MODIS images are used to investigate the CNN approach using a cross-validation approach. The classical machine learning approach, i.e., the supported vector regression (SVR), is used to compare with the proposed CNN approach. Comparing with the SVR, the CNN performs better with the mean log root-mean-square error and R2 of being 0.129 and 0.901, respectively, indicating that using the MODIS images alone, the CNN approach can achieve results that is close to the OC-CCI Chla concentration images. These results demonstrate that CNNs may provide Chla concentration images that are reliable, stable and timely, and as such CNN constitutes a useful technique for operational Chla concentration estimation from large MODIS data.

DOWNLOAD PAPER

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years