Land surface temperature (LST) is a critical indicator of the interactions between the Earth’s surface and atmosphere and has long been available from satellite observations in the thermal infrared (TIR) region. Recognized as a primary way to evaluate the accuracy of LSTs, in situ validation is still a challenging task because of uncertainties in ground measurements, spatial scale mismatch between ground and satellite-based measurements, the heterogeneity of natural land surfaces, etc., leading to a lack of consistency among sets of validation results; therefore, to improve robustness against uncertainties, an optimized approach for LST validation via the Kalman filter is presented, and prediction of comprehensive validation estimate (CVE) which is close to “true” value, and more precise than those based on a single measurement alone is obtained. After the uncertainties involved in the validation process are constrained, this method is applied to FengYun-3D (FY-3D)/Medium Resolution Spectral Imager II (MERSI-II) LSTs with ground measurements from four sites in China. The results indicate that the CVE is 1.11 K, with an uncertainty of 0.07 K. Additionally, a comparison is performed with the weighted average method, and the efficacy of the Kalman filter approach in enhancing the validation accuracy is confirmed.

Land Surface Temperature (LST) is a critical environmental parameter for describing biophysical processes at the Earth's surface, applicable at regional or global scales. High-resolution LST downscaling is of paramount importance for research in areas such as urban heat islands, crop health, natural disasters, and climate change. However, sensors with a high revisit time are limited in their ability to provide detailed spatial information. Therefore, downscaling of LST products with coarse spatial resolution is considered a necessary and inevitable process to address this challenge and offer valuable data solutions. In this study, we have developed a LST downscaling and reconstruction method based on machine learning. By introducing predictor variables to characterize the spatial distribution of LST, we have successfully downscaled and reconstructed LST data from the Moderate Resolution Imaging Spectroradiometer (MODIS) with a resolution of 990m to 90m. Our analysis was carried out on various land surface cover types, including urban areas, croplands, mountainous regions, and water bodies. The comprehensive comparison and analysis of model performance have shown that in different seasons, the downscaling and reconstructed performance in mountainous areas is the best, with R-squared (R2) values reaching 0.71 and 0.80, and Root Mean Square Error (RMSE) values of 1.72 and 1.64, respectively. The proposed model was subsequently applied for downscaling and reconstructing surface temperatures in cloud-covered areas, and the results were confirmed through both visual assessments and statistical measurements of reconstruction accuracies.

Potatoes, a crucial staple crop, face significant threats from late blight, which poses serious risks to food security. Despite extensive research using ground and unmanned aerial vehicle (UAV) hyperspectral data for crop disease monitoring, satellite-scale identification of diseases, such as potato late blight (PLB) remains limited. This study employs a multiscale analysis approach, integrating high-resolution Sentinel-2 multispectral satellite data with UAV and ground spectral data, to monitor and identify PLB. A key finding of this study is the general similarity in spectral patterns across different scales, with consistent valley values in bands of blue and red and peak values in bands of near infrared (NIR) and narrow NIR, accompanied by a consistent decrease in reflectance correlating with increasing disease severity. Furthermore, the study highlights scale-dependent spectral variations, with changes in bands of Vegetation Red Edge2, Vegetation Red Edge3, NIR, and narrow NIR being more pronounced at the ground scale compared to UAV and satellite scales. Based on the developed red edge index and disease stress index with a suite of machine learning algorithms, we proposed an XGBoost-based model integrating spectral indices for PLB monitoring (PLB-SI-XGBoost). Notably, the proposed model demonstrated the highest average evaluation score of 0.88 and the lowest root-mean-square error (RMSE) of 13.50 during ground-scale validation, outperforming other algorithms. At the UAV scale, the proposed model achieved a robust R-squared value of 0.74 and an RMSE of 18.27. Moreover, the application of Sentinel-2 data for disease detection at the satellite scale yielded an accuracy of 70% in the model. The results of the study emphasize the importance of scale in disease monitoring models and illuminate the potential for satellite-scale surveillance of PLB. The exceptional performance of the PLB-SI-XGBoost model in detecting PLB suggests its utility in enhancing agricultural decision-making with more accurate and reliable data support.

The spatiotemporal distribution of snow depth (SD) has a significant impact on the energy and water balances of the Earth’s system. However, passive microwave remote sensing widely used for SD estimation has large uncertainties due to the variations in snow physical properties. In this study, we demonstrate a new method to minimize these uncertainties and to increase the accuracy of SD estimation. Our method is based on the synergy between the passive microwave AMSR-2 brightness temperature (TB) and a physical snow process model (SNTHERM) to estimate snow grain size, snow density and first-guess SD as priors. On one hand, we used TB from three frequencies and removed non-representative ground measurements at the stations to improve deep snow estimation. Then, we applied a machine learning (ML) algorithm based on both the AMSR-2 TB and the SNTHERM simulations to retrieve the global SD. The results showed that the root-mean-squared error (RMSE) of the retrieved SD was 12.4 cm at the meteorological stations. Independent validations showed that our method significantly reduced the SD and snow water equivalent (SWE) underestimation in the mountains compared to the current satellite products.

Glacier lake is one important component of the ecosystem of the Qinghai Tibet Plateau. The changes of glacier lakes are extremely sensitive to climate and environmental changes, and also closely related to water resources changes and geological disasters. In this study, the typical area of glacial lakes development in Qinghai Tibet Plateau was selected. To extract glacier lakes in this area, a machine-learning based method (MLB) was proposed with Landsat-8 and NASADEM dataset. Considering the spectral features and topographic features, a total of 14 parameters were taken as the inputs of the proposed MLB. Compared with the threshold segmentation method (TS), the MLB performed superior. The kappa coefficient (KC) and overall accuracy (OA) of the MLB method are 0.8602 and 99.49, respectively. While, those values of TS are 0.6123 and 98.88, respectively. The TS may fail under certain conditions, especially in the cloud shadow. The results reveals that the accuracy of glacial lake extraction in the high-altitude area may be improved with the MLB. There is a potential for automated glacial lake mapping with the MLB in rugged mountain areas at a large scale.

Spectral–spatial-based deep learning models have recently proven to be effective in hyper-spectral image (HSI) classification for various earth monitoring applications such as land cover classification and agricultural monitoring. However, due to the nature of “black-box” model representation, how to explain and interpret the learning process and the model decision, especially for vegetation classification, remains an open challenge. This study proposes a novel interpretable deep learning model—a biologically interpretable two-stage deep neural network (BIT-DNN), by incorporating the prior-knowledge (i.e., biophysical and biochemical attributes and their hierarchical structures of target entities)-based spectral–spatial feature transformation into the proposed framework, capable of achieving both high accuracy and interpretability on HSI-based classification tasks. The proposed model introduces a two-stage feature learning process: in the first stage, an enhanced interpretable feature block extracts the low-level spectral features associated with the biophysical and biochemical attributes of target entities; and in the second stage, an interpretable capsule block extracts and encapsulates the high-level joint spectral–spatial features representing the hierarchical structure of biophysical and biochemical attributes of these target entities, which provides the model an improved performance on classification and intrinsic interpretability with reduced computational complexity. We have tested and evaluated the model using four real HSI data sets for four separate tasks (i.e., plant species classification, land cover classification, urban scene recognition, and crop disease recognition tasks). The proposed model has been compared with five state-of-the-art deep learning models. The results demonstrate that the proposed model has competitive advantages in terms of both classification accuracy and model interpretability, especially for vegetation classification.

Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has proven to be an effective deep learning framework for image super-resolution. However, the optimisation process of existing GAN-based models frequently suffers from the problem of mode collapse, leading to the limited capacity of spectral-spatial invariant reconstruction. This may cause the spectral-spatial distortion on the generated HSI, especially with a large upscaling factor. To alleviate the problem of mode collapse, this work has proposed a novel GAN model coupled with a latent encoder (LE-GAN), which can map the generated spectral-spatial features from the image space to the latent space and produce a coupling component to regularise the generated samples. Essentially, we treat an HSI as a high-dimensional manifold embedded in a latent space. Thus, the optimisation of GAN models is converted to the problem of learning the distributions of high-resolution HSI samples in the latent space, making the distributions of the generated super-resolution HSIs closer to those of their original high-resolution counterparts. We have conducted experimental evaluations on the model performance of super-resolution and its capability in alleviating mode collapse. The proposed approach has been tested and validated based on two real HSI datasets with different sensors (i.e. AVIRIS and UHD-185) for various upscaling factors (i.e. ×2, ×4, ×8) and added noise levels (i.e. ∞ db, 40 db, 80 db), and compared with the state-of-the-art super-resolution models (i.e. HyCoNet, LTTR, BAGAN, SR- GAN, WGAN). Experimental results show that the proposed model outperforms the competitors on the super-resolution quality, robustness, and alleviation of mode collapse. The proposed approach is able to capture spectral and spatial details and generate more faithful samples than its competitors. It has also been found that the proposed model is more robust to noise and less sensitive to the upscaling factor and has been proven to be effective in improving the convergence of the generator and the spectral-spatial fidelity of the super-resolution HSIs.

Bistatic/multistatic synthetic aperture radar (Bi-/M-SAR) has extensive applications, including cross- and along-track interferometry, multiangle imaging, and so on. However, these applications are affected by several factors, especially the time and frequency synchronization that this article focuses on. Here, the new insights about the focus are described, based on which an innovative push-to-talk (PTT) scheme is first put forward to solve the time and frequency synchronization problems of distributed SAR. It realizes unidirectional and long-distance synchronization through the two-segment frequency rate (TSFR) waveform composed of the two linear frequency modulation (LFM) signals with different frequency rates and achieves radar imaging and synchronization with a high rate (${f}_{\mathrm{ syn}}$) at the same time by the frequency diversity (FD) waveforms and bandpass filters. To clarify the PTT scheme, its system framework and synchronization error models are detailed. Besides, the channel impulse response, multiple errors, the signal-to-noise ratio (SNR) of synchronous links, and time synchronization accuracy are analyzed. In addition, some simulations are carried out to evaluate its performance. Those results demonstrate that the PTT scheme can perform the long-distance synchronization with high$f_{\mathrm{ syn}}$, its synchronization accuracy increases with the improvement of SNR and$f_{\mathrm{ syn}}$, and it can measure the time and frequency deviations in different ranges accurately. In a word, the PTT scheme has the potential to be used in future distributed SAR missions.

Snow depth (SD) is an important input parameter for snow cover hydrologic model and climate model. In China, the snow volume is affected by the plateau climate and different geographical situation, which shows specific rules and characteristics in space and time distribution. Consequently, it is very necessary to dynamically estimate the snow volume of China area. In this paper, we use passive microwave to estimate the snow depth in China, through the analysis on the characteristics of time, space and geographical environment of the snow zone in China, we added the impact of snow cover in pixel, high-frequency (89.0 GHz) on the accuracy of inversion and on the basis Chang's classical algorithm of inversion of snow water equivalent, considered that there were different responses to the microwave in different types of surface, improve the algorithm of inversion of snow water equivalent in China. The results show that new inversion algorithm can improve the precise of the inversion of snow depth in the area of China. However, the low spatial resolution of microwave, complex types of feature in the ground pixel and the changes of the snow status with time and space, which make it difficult to invert snow water equivalent, so need to further study.

In this paper, we mainly studied of microwave emission behavior of shallow snow cover with the field experiments over Huabei Plain, China., The evaluation of microwave emission character over snow surface was using the data collected by a ground-based multi-frequency and dualpolarization microwave radiometer (RPG-8CH-DP) at 10.7 GHz, 18.7GHz and 36.5 GHz, with the incidence angles ranging from 20° to 60°. Through analysis of the observation brightness temperature, we found that the radiation behavior of thin snow cover is very different from that of deep snow, especially during melting and refreezing period of thin snow cover. One is that the emission over shallow snow surface increased as frequencies increase. Secondly, at the same frequency, when shallow snow was melt in diurnal refreezing-thaw cycle, the emission would decrease. These two emission behavior were caused by the attenuation of snow cover was weak than the increment of emission from the underground snow surface. From this study, it has been shown that the ground-based microwave radiometry provides a useful tool to investigate the radiation characteristics of thin snow cover and snow type identification. It also helps to evaluate snow emission models and develop retrieval algorithms of snow characteristics from space-borne microwave radiometer data.