The observed radiation data from the second-generation Hyperspectral Infrared Atmospheric Sounder (HIRAS-II) on the Fengyun-3E (FY-3E) satellite contain useful vertical atmosphere information which can distinguish and retrieve vertical profiles of atmospheric gas components including ozone (O₃), carbon monoxide (CO), and methane (CH₄). This paper utilizes FY-3E/HIRAS-II observational data to optimize each gas channel using the improved Optimal Sensitivity Profile method (OSP) channel algorithm and establishes a typical convolutional neural network model (CNN) and a representative U-shaped network model (UNET) with deep features and shallow feature links to perform atmospheric profile retrieval calculations of O3, CO, and CH₄. We chose the clear sky data of the Indian and its southern seas in December 2021 and January 2022, with reanalysis data from European Center for Medium-Range Weather Forecasts Reanalysis v5 (ERA5) and European Center for Medium-Range Weather Forecasts Atmospheric Composition Reanalysis v4 (EAC4) serving as the reference values. The retrieval outcomes were then compared against advanced numerical forecast models including the Whole Atmosphere Community Climate Model (WACCM), Global Forecast System (GFS), and satellite products from an Atmospheric Infrared Sounder (AIRS) and Infrared Atmospheric Sounding Interferometer (IASI). Experimental results show that the generalization ability and retrieval accuracy of CNN are slightly higher compared with UNET. For O₃ profile retrieval, the mean percentage error (MPE) of the whole layers for CNN and UNET data in relation to ERA5 data was less than 8%, while the root-mean-square error (RMSE) was below 1.5 × 10⁻⁷ kg/kg; for CH₄ profile retrieval, the MPE of the whole layers for CNN and UNET data in relation to EAC4 data was less than 0.7%, while the RMSE was below 1.5 × 10⁻⁸ kg/kg. The retrieval of O₃ and CH₄ are resulted in a significant improvement compared to the forecast data and satellite products in most pressure levels; for CO profile retrieval, the MPE of the whole layers for CNN and UNET data in relation to EAC4 data was less than 11%, while the RMSE was below 4 × 10⁻⁸ kg/kg. The error of the CO retrieval results was higher than that of the forecast data at the pressure level of 200~500 hPa and lower than that of similar satellite products with most pressure levels. The experiments indicated that the neural network method effectively determines the atmospheric gas profiles using infrared hyperspectral data, exhibiting a positive performance in accuracy and retrieval speed.

Fengyun-3E (FY-3E)/Hyperspectral Infrared Atmospheric Sounder-II (HIRAS-II) is an extension Fengyun-3D (FY-3D)/HIRAS-I. It is crucial to fully explore and analyze the detection capabilities of these two instruments for atmospheric gas composition. Based on the observed spectral data from the infrared hyperspectral detection instruments FY-3D/HIRAS-I and FY-3E/HIRAS-II, simulated radiance data and Jacobian matrices are obtained using the Rapid Radiative Transfer Model RTTOV (Radiative Transfer for TOVS (TIROS Operational Vertical Sounder)). By perturbing temperature (T), surface temperature (T_surf), water vapor (H₂O), ozone (O₃), carbon dioxide (CO₂), methane (CH₄), carbon monoxide (CO), and nitrous oxide (N₂O), the brightness temperature differences before and after the perturbations are calculated to analyze the sensitivity of temperature and various atmospheric gas components. The Improved Optimal Sensitivity Profile (OSP) algorithm is used to select the channels for atmospheric gas retrieval. The observation error covariance and background error covariance matrices are calculated, and then the information capacity is calculated, specifically the degrees of freedom for signal(DFS) and the entropy reduction (ER). Based on this, a comparative analysis is conducted on the information capacity of atmospheric water vapor and ozone components contained in the hyperspectral detection data from HIRAS-I and HIRAS-II instruments, respectively, to explore the retrieval capabilities of the two instruments for atmospheric gas components. We selected clear-sky data from the African oceanic region and the Chinese Yangtze River Delta terrestrial region for quantitative analysis of the information capacity of HIRAS-I and HIRAS-II. The results show that FY-3D/HIRAS-I and FY-3E/HIRAS-II exhibit different sensitivities to atmospheric gas components. In different experimental regions, temperature and water vapor show the most dramatic sensitivity changes, followed by ozone, methane, and nitrous oxide, while carbon monoxide and carbon dioxide exhibit the lowest variability. Regarding channel selection, HIRAS-II identifies more gas channels compared to HIRAS-I. The experiments concluded that HIRAS-II has a significantly higher information capacity than HIRAS-I, and the information capacity of atmospheric gas components varies across different experimental regions. Water vapor and ozone exhibit the highest information capacity, followed by nitrous oxide and methane, while carbon monoxide and carbon dioxide demonstrate the lowest capacity. The H₂O ER (DFS) contained in FY-3E/HIRAS-II is 1.51 (0.35) higher than that in FY-3D/HIRAS-I, the O₃ ER (DFS) in FY-3E/HIRAS-II is 1.51 (0.36) higher than that in FY-3D/HIRAS-I, while the N₂O ER (DFS) in FY-3E/HIRAS-II is 0.17 (0.19) higher and the CH₄ ER (DFS) is 0.07 (0.04) higher than that in FY-3D/HIRAS-I.

Hyperspectral infrared atmospheric sounding data, characterized by their high vertical resolution, play a crucial role in capturing three-dimensional atmospheric spatial information. The hyperspectral infrared atmospheric detectors HIRAS/HIRAS-II, mounted on the FY3D/EF satellite, have established an initial global coverage network for atmospheric sounding. The collaborative observation approach involving multiple satellites will improve both the coverage and responsiveness of data acquisition, thereby enhancing the overall quality and reliability of the data. In response to the increasing number of channels, the rapid growth of data volume, and the specific requirements of multi-satellite joint observation applications with infrared hyperspectral sounding data, this paper introduces an efficient storage and indexing method for infrared hyperspectral sounding data within a distributed architecture for the first time. The proposed approach, built on the Kubernetes cloud platform, utilizes the Google S2 discrete grid spatial indexing algorithm to establish a grid-based hierarchical model for unified metadata-embedded documents. Additionally, it optimizes the rowkey design using the BPDS model, thereby enabling the distributed storage of data in HBase. The experimental results demonstrate that the query efficiency of the Google S2 grid-based embedded document model is superior to that of the traditional flat model, achieving a query time that is only 35.6% of the latter for a dataset of 5 million records. Additionally, this method exhibits better data distribution characteristics within the global grid compared to the H3 algorithm. Leveraging the BPDS model, the HBase distributed storage system adeptly balances the node load and counteracts the detrimental effects caused by the accumulation of time-series remote sensing images. This architecture significantly enhances both storage and query efficiency, thus laying a robust foundation for forthcoming distributed computing.

Conventional neural retrieval models commonly use a single spectral representation to predict all pressure levels, limiting their ability to capture altitude-dependent information. We propose a Pressure-Conditioned Cross-Attention Network (PC-CAN) for temperature-profile retrieval from Atmospheric Infrared Sounder (AIRS) Level 1C radiances. A three-stage one-dimensional residual encoder and adaptive tokenizer convert each 2645-channel spectrum into 64 spectral tokens with 64 features each. Continuous log-pressure encoding generates queries for 37 standard levels, and four-head cross-attention constructs level-specific features for a shared regression head. A screened regional dataset of 319,194 AIRS matches with the fifth-generation European Centre for Medium-Range Weather Forecasts reanalysis (ERA5) was constructed over 15–55° N and 70–140° E using Moderate Resolution Imaging Spectroradiometer (MODIS) cloud masks, summer observations, and date-independent partitions. On 84,618 test samples, PC-CAN achieved an RMSE of 1.3277 K, a bias of 0.1358 K, and a Pearson correlation coefficient of 0.9990 over 100–900 hPa, with an RMSE of 1.3935 K across all 37 pressure levels. Its 100–900 hPa RMSE was 16.66%, 18.90%, and 17.94% lower than those of a multilayer perceptron, a one-dimensional convolutional neural network, and an optimized spectral self-attention model, respectively. On an external set of 208 strictly collocated AIRS–Integrated Global Radiosonde Archive (IGRA) profiles from 70 stations, PC-CAN obtained an RMSE of 2.039 K, compared with 2.185–2.223 K for the three baselines; station-clustered paired bootstrap intervals supported the overall improvements. These results demonstrate improved agreement with ERA5 and radiosonde observations for clear-sky summer observations over East Asia and adjacent regions; they do not establish global, year-round, or cloudy-sky generalization.