The timely and accurate prediction of winter wheat yields is of importance in maintaining food security. However, existing deep-learning methods used for crop yield prediction are limited. While most methods utilize recurrent neural networks (RNNs) to interpret crop time series data, they struggle to learn geographical spatial information from input data and often prove challenging to interpret with prior knowledge. In this study, hyperspectral images were used as the input to a BS-Nets network for band selection, and a graph-based RNN framework GT-long-short-term memory (LSTM) [two channels based LSTM-graph neural network (GNN)], was proposed for predicting the winter wheat yield at the county level. Using the BS-Nets for hyperspectral bands selection at the field scale, we obtained the top 4 bands in selection results for all six stages, the results were band 46 (791 nm), 50 (825 nm), 66 (954 nm), and 161 (2484 nm). Based on the results of hyperspectral bands selection, at the county scale, the similar wavelength bands of Sentinel-2 red-edge 3 (783 nm), NIR (834 nm), red-edge 4 (865 nm), SWIR2 (2190 nm) were chosen as inputs for the GT-LSTM county-level estimates of winter wheat yield. When only remote sensing data were used, the highest prediction accuracy ($R^{2}= 0.688$, RMSE = 0.54 t/ha) was obtained for DOY135 (30 days before harvest). The incorporation of the meteorological data improved the accuracy by 7% ($R^{2}= 0.714$, RMSE = 0.50 t/ha), and the optimal time for predicting wheat yield was at DOY115 (50 days before harvest). Further addition of GNN layers to the model improved the accuracy of the results by an additional 14% ($R^{2}= 0.757$, RMSE = 0.43 t/ha), and the best prediction results were then obtained at DOY105 (60 days before harvest).

Cloud contamination greatly limits the potential utilization of optical images for geoscience applications. An effective alternative is to extract data from synthetic aperture radar (SAR) images to remove clouds due to the strong penetration ability of microwaves. In this article, we propose a novel unified spatial–spectral residual network that utilizes SAR images as auxiliary data to remove clouds from optical images. The method can better establish the relationship between SAR and optical images and be divided into two modules: feature extraction and fusion module and reconstruction module. In the feature extraction and fusion module, a gated convolutional layer is introduced to discriminate cloud pixels from clean pixels, which makes up for the lack of distinguishing ability of vanilla convolutional layers and avoids the error of cloud areas in feature extraction. In the reconstruction module, spatial and channel attention mechanisms are introduced to obtain global spatial and spectral information. The network is tested on three datasets with different spatial resolutions and compositions of land covers to verify the effectiveness and applicability of the method. The results show that the method outperforms other mainstream algorithms that simultaneously use SAR images as auxiliary data with a gain of about 2.3 dB in terms of peak signal-to-noise ratio PSNR on the SEN12MS-CR dataset.

Single-image super-resolution (SISR) for high-resolution (HR) remote sensing image (RSI) acquisition is becoming increasingly valuable and important, and convolutional neural networks (CNNs) have produced considerable progress in this field. In RSIs, many similar geo-objects recur within the same scene, maintaining the same positions in both low resolution (LR) and HR. Based on this observation, we found that these similar geo-objects could be utilized to reconstruct texture details in LR by exploiting the consistent non-local relationships between these geo-objects in LR and HR, thereby improving the quality of SISR. Therefore, we propose a novel graph convolutional network (GCN) for SISR including a dynamic graph attention mechanism to learn the in-scale and cross-scale non-local features of RSIs. In scale, we propose a dynamic graph attention block (DGAB) that adaptively determines non-local patches upon the scene correlation derived from RSIs and further fuses patch-wise non-local information weighed by the attention scores of topological relationships and radiation characteristics in RSIs. Across different scales, we also introduce a dynamic graph attention mixing block (DGAMB) to upsample LR non-local information to HR non-local information. Most SISR methods have the upsampling blocks at the end of the network, ignoring feature extraction in high-dimensional space. To address this problem, DGAMB was designed as an upsampler in the middle of the model, enhancing the level of high-dimensional information extraction from the model. The experiments based on the WHU Building and UC Merced datasets show that our proposed method outperforms state-of-the-art methods. Our code is available athttps://github.com/WenjuanZhang-aircas/NSGCN.

Full-spectrum remote sensing images can simultaneously provide reflectance and emission information about objects, which has great application value. Hyperspectral imaging can record hundreds of spectral bands, but due to technical and space limitations, full-spectrum hyperspectral images (HSI) are difficult to obtain. Recently, we proposed a spectral super-resolution method based on the Linear Spectral Mixing Model (LSMM), which can generate full-spectrum hyperspectral images (HSI) from multispectral images (MSI). After the spectral-unmixing of MSI, we transform MS endmembers into full-spectrum HS endmembers by spectral library. Since the abundance of MSI and HSI with the same spatial resolution is consistent, we linearly mixed the abundance and HS endmember to obtain the full spectrum HSI. In this work, we use Sentinel-2 dataset and EO-1 ALI/Hyperion images to verify the accuracy and applicability. Compared with other works, our method can simulate full-spectrum HSI of large-area scenes without real HSI, which has a certain accuracy and provides more comprehensive information for applications.

Cloud cover is a common problem in optical satellite imagery, which leads to missing information in images. To rapidly acquire noncloud images, we design a cloud removal method to recover single-temporal remote sensing image based on land cover data which is easier to obtain than multitemporal data. Considering that the same features have the same radiation characteristics, we extract the similar pixels from same category around the missing pixels and calculate the value of missing pixels according to the distance weights of these pixels. The performance of the proposed method was evaluated on MODIS images and Landsat images and the results also prove that universal applicability of this algorithm in different resolutions and surface contents.

Single image super-resolution (SISR) algorithm is to recover a high-resolution image from a single low-resolution one and has been widely applied in remote sensing (RS) reconstruction. Numerous SISR models have been proposed for RS ap-plications. However, most existing methods suffer from an inability to reconstruct multi-scale RS images using one fixed pre-trained model. Here, we design a scale-adaptive SISR algorithm for RS images. The main contributions are three-fold: (1) to be applied for the multi-scale reconstruction, we first employ the bicubic interpolation to stretch the images before import so that our convolutional neural network can focus on refining the details of reconstruction images; (2) to extract the deep information of ground surface from RS images, we design multi-scale residual network to recover the image details; (3) we adopt the least-absolute-error loss to constraint our network for reconstructing the RS images. It is demonstrated that our model achieves excellent performance for super-resolution of RS images.

Characteristics of radiance spectrum and radiance error distribution after channel center wavelength shift of imaging spectrometers were analyzed in this paper. The results show that shifts of the channel center wavelength can cause shifts of the radiance spectrum, and the shift direction of the two is opposite. The radiance error caused by the channel center wavelength shift is basically distributed near the solar and atmospheric absorption bands. When the center wavelength shifts the same amount towards the positive and negative directions, the absolute value of radiance error is different, which is caused by the asymmetry of spectral absorption region. For 5nm, 10nm and 15nm resolution imaging spectrometers, there is a significant linear relationship between the center wavelength shift and the maximum percent error of radiance. When the center wavelength shift value is less than 10% of the spectral bandwidth, the 10nm imaging spectrometer is most sensitive to the center wavelength shift; when the center wavelength shift is greater than 30%, the 15nm imaging spectrometer is most sensitive to the center wavelength shift.

Atmospheric absorption bands centered at 2.7 micron are used in missile warning systems for target detection and tracking. Since image simulation is an important tool for sensor development, relevant research should be conducted for sensors using the 2.7 micron absorption bands. In this paper, we propose a surface reflectance image simulation method for this absorption bands, to prepare surface input images for corresponding end-to-end simulation. Considering that surface reflectance is related to the surface material type, reflectance images in the absorption bands are simulated from abundance inversion and spectral mixing. Specifically, spectra in spectral libraries are used as endmembers for data source images, and abundance inversion are conducted to acquire abundance maps of these types of materials. Then, spectral mixing is conducted to generate reflectance images with reflectance in the absorption bands of endmembers and abundance maps. Accuracy analysis shows this method is feasible and with good accuracy.

Mid-infrared atmospheric absorption bands centered at 4.3 μm are applied in target detection. Image simulation, as an important tool for the adaption and optimization of a sensor, ought to be conducted for the development of instruments using this spectral range. In this paper, a top-of-atmosphere (TOA) image simulation method is proposed, and this method is tested on two bands of the sensor SPIRIT III (band S1: 4.21-4.37 μm, S2: 4.23-4.47 μm). Band translation models are established for the generation of surface emissivity images, and an analytic radiative transfer model is modified and utilized to simulate TOA radiance fast and accurately. Accuracy analysis of the proposed method shows relative errors of within ±6% and ±1% in simulated surface emissivity and TOA radiance, respectively. Moreover, image simulation is often used for band selection in the sensor design stage. To illustrate how our proposed simulation method was applied in band selection, we used simulated TOA radiance of bands S1 and S2 as an example and compared their possibility of false alarms caused by high-temperature objects. Experimental results show that high-temperature objects are more unlikely to become false alarms on band-S1 images. Therefore, the spectral range of S1 is a better option for target detection application than S2. This TOA simulation method can be also applied in band selection among other 4.3-μm absorption bandwidths, as was done in this paper.

Land surface temperature (LST) is required by a series of surface studies and usually estimated using thermal infrared remote sensing data. In this paper, we propose a method to retrieve LST for MODIS data using its mid-infrared bands 22 and 23. As the central wavelengths of bands 22 and 23 are quite close, we assume that (1) band-averaged surface e-missivities are equal in these two bands, and (2) the Planck integration between these two bands comply to a statistical relationship. Based on these two assumptions, land surface temperature is retrieved after atmospheric correction on the radiance images. A test case is selected to estimate LST using our proposed method. The estimated LST image shows good consistency with the corresponding standard MODIS land surface temperature product, with the relative errors of ±1%. The experiment results suggest this methodology is effective to retrieve MODIS land surface temperature quickly.

The imaging Fourier transform spectrometer (IFTS) carried on HJ-1A is the first spaceborne hyperspectral earth observation sensor in China. Shifts in the spectral channel center wavelengths of IFTS may occur after launch due to vibrations, and to changes in instrument temperature and pressure. In this paper, we described an improved on-orbit spectral calibration method, which is based on spectrum angle matching between the spectrometer-measured radiance spectrum and the modeled radiance spectrum at atmospheric absorption bands. Compared with the laboratory calibration result of IFTS, spectral shifts ranged from -3.18 to -3.4 nm were derived depending on cross-track spectral position at 760-nm oxygen bands, and from -3.53 to -3.79 nm at 820-nm water vapor bands. With the updated spectral calibration coefficient, the reflectance of vegetation and desert in our study site were reconstructed by applying a further atmospheric correction, and the strong spikes around the atmospheric absorption bands were almost obviously suppressed.

HJ-1A and HJ-1B, the first micro-satellite constellation for Environment and Disaster Monitoring of China, was successfully launched in China on September 6, 2008. The same multispectral imagers named HJ-1/CCD with four bands (R, G, B, Nir) and large swath are installed on both HJ-1A and HJ-1B. The HJ-1/CCD is the main sensor of the constellation. In this paper, data sets includes six image pairs of HJ-1A/CCD and Terra/Modis and field reflectance spectra of Dunhuang Calibration Site are acquired. Cross calibration is taken to get the calibration results of HJ-1A/CCD relative to Terra/Modis. Based on the calibration results, the radiometric performance of HJ-1A/CCD is evaluated. Taking into that the good radiometric performance of Terra/Modis, it is obvious that HJ-1A/CCD has a radiometric attenuation during its second half of the first year. The max attenuation occurred on the near infrared band is about 18%. The min attenuation occurred on the blue band is about 8%. There maybe some inevitable errors about the data sets and produced during the processing. More images should be acquired and more attention should be paid to get the true radiometric attenuation.

A new method for estimating noise in hyperspectral images is described in this letter. Our method is based on the general internal regularity of Earth objects and the strong spectral correlation of hyperspectral images. It can be used to automatically estimate noise for both radiance and reflectance images. Unlike other methods discussed in this letter, our method is more reliable and adaptable, which we demonstrate using simulated images with different scene contents. Finally, we successfully applied this new method in estimating noise for Pushbroom Hyperspectral Imager (PHI) data.

Spectral data , composed of spectra and related attributes, such as environmental parameters, attribute parameters about measured objects and others, are usually stored in spectral database. Spectral database is an important basis of the hyperspectral remote sensing development. Therefore, it is very important to utilize sufficiently, manage effectively, and collect spectral data extensively. The fast development of computer infrastructure and internet technology makes it possible to upload, manage and analyze spectral data in a real-time, long-distance, and online way. This paper takes agriculture spectral database as an example to show the details of the implementation. Using JSP + JavaBeans based on Oracle fulfills the following functions: data browse and query, upload and examination, regression analysis, parameter extraction, etc. Keywords-Spectral Database; Online;Data Analysis and Management