The existing neural network model in urban land-subsidence prediction is over-reliant on historical subsidence data. It cannot accurately capture or predict the fluctuation in the sequence deformation, while the improper selection of training samples directly affects its final prediction accuracy for large-scale urban land subsidence. In response to the shortcomings of previous urban land-subsidence predictions, a subsidence prediction method based on a neural network algorithm was constructed in this study, from a multi-factorial perspective. Furthermore, the scientific selection of a large range of training samples was controlled using a K-shape clustering algorithm in order to produce this high-precision urban land subsidence prediction method. Specifically, the main urban area of Kunming city was taken as the research object, LiCSBAS technology was adopted to obtain the information on the land-subsidence deformation in the main urban area of Kunming city from 2018–2021, and the relationship between the land subsidence and its influencing factors was revealed through a grey correlation analysis. Hydrogeology, geological structure, fault, groundwater, high-speed railways, and high-rise buildings were selected as the influencing factors. Reliable subsidence training samples were obtained by using the time-series clustering K-shape algorithm. Particle swarm optimization–back propagation (PSO-BP) was constructed from a multi-factorial perspective. Additionally, after the neural network algorithm was employed to predict the urban land subsidence, the fluctuation in the urban land-subsidence sequence deformation was predicted with the LSTM neural network from a multi-factorial perspective. Finally, the large-scale urban land-subsidence prediction was performed. The results demonstrate that the maximum subsidence rate in the main urban area of Kunming reached −30.591 $\mathrm{mm}\cdot {\mathrm{a}}^{-1}$ between 2018 and 2021. Moreover, there were four main significant subsidence areas in the whole region, with uneven distribution characteristics along Dianchi: within the range of 200–600 m from large commercial areas and high-rise buildings, within the range of 400–1200 m from the under-construction subway, and within the annual average. The land subsidence tended to occur within the range of 109–117 mm of annual average rainfall. Furthermore, the development of faults destroys the stability of the soil structure and further aggravates the land subsidence. Hydrogeology, geological structure, and groundwater also influence the land subsidence in the main urban area of Kunming. The reliability of the training sample selection can be improved by clustering the subsidence data with the K-shape algorithm, and the constructed multi-factorial PSO-BP method can effectively predict the subsidence rate with a mean squared error (MSE) of 4.820 mm. The prediction accuracy was slightly improved compared to the non-clustered prediction. We used the constructed multi-factorial long short-term memory (LSTM) model to predict the next ten periods of any time-series subsidence data in the three types of cluster data (Cluster 1, Cluster 2, and Cluster 3). The root mean square errors (RMSE) were 0.445, 1.475, and 1.468 mm; the absolute error ranges were 0.007–1.030, 0–3.001, and 0.401–3.679 mm; the errors (mean absolute error, MAE) were 0.319, 1.214, and 1.167 mm, respectively. Their prediction accuracy was significantly improved, and the predictions met the measurement specifications. Overall, the prediction method proposed from the multi-factorial perspective improves large-scale, high-accuracy urban land-subsidence prediction.

The refracted, reflected, and scattered signals from global navigation satellite systems (GNSS) have been successfully used for remote sensing (RS) of the Earth's surface and atmosphere, demonstrating their potential for sensing the atmosphere, oceans, land surface and cryosphere. As an emerging RS technology, spaceborne GNSS reflectometry (GNSS-R) has been widely used in the field of land RS, with unique advantages such as high spatial and temporal resolution, low observation cost, wide coverage, and all-weather operation. In recent years, the successful launch of several spaceborne GNSS-R satellites has opened new opportunities in this field. The aim of this paper is to provide a comprehensive overview of the breakthrough applications of spaceborne GNSS-R technology in the key areas of soil moisture (SM), soil salinity, vegetation monitoring, soil freezing and thawing, flood detection, inland water bodies, wetland dynamics, forest fire disturbances, and land topography measurements, as well as possible future research directions. In addition, this article also emphasizes the contribution and role of China's recently launched Tianmu-1 (TM-1) constellation (as of January 5, 2024, 23 satellites have been in stable operation in orbit) in the development of spaceborne GNSS-R technology and explores the future development direction and prospects of this technology. By comprehensively analyzing the latest progress and innovative achievements of relevant research, the significant impact of this technology on land RS applications in environmental monitoring, resource management, and disaster warning has been highlighted. Through a comprehensive summary of these fields, the enormous potential of spaceborne GNSS-R technology in promoting sustainable development and ecological protection has been revealed.

Spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) is a new remote sensing technology that uses GNSS signals reflected from the Earth’s surface to estimate geophysical parameters. Because of its unique advantages such as high temporal and spatial resolutions, low observation cost, wide coverage and all-weather operation, it has been widely used in land and ocean remote sensing fields. Ocean wind monitoring is the main objective of the recently launched Cyclone GNSS (CYGNSS). In previous studies, wind speed was usually retrieved using features extracted from delay-Doppler maps (DDMs) and empirical geophysical model functions (GMFs). However, it is a challenge to employ the GMF method if using multiple sea state parameters as model input. Therefore, in this article, we propose an improved deep learning network framework to retrieve global sea surface wind speed using spaceborne GNSS-R data, named GloWS-Net. GloWS-Net considers the fusion of auxiliary information including ocean swell significant wave height (SWH), sea surface rainfall and wave direction to build an end-to-end wind speed retrieval model. In order to verify the improvement of the proposed model, ERA5 and Cross-Calibrated Multi-Platform (CCMP) wind data were used as reference for extensive testing to evaluate the wind speed retrieval performance of the GloWS-Net model and previous models (i.e., GMF, fully connected network (FCN) and convolutional neural network (CNN)). The results show that, when using ERA5 winds as ground truth, the root mean square error (RMSE) of the proposed GloWS-Net model is 23.98% better than that of the MVE method. Although the GloWS-Net model and the FCN model have similar RMSE (1.92 m/s), the mean absolute percentage error (MAPE) of the former is improved by 16.56%; when using CCMP winds as ground truth, the RMSE of the proposed GloWS-Net model is 2.16 m/s, which is 20.27% better than the MVE method. Compared with the FCN model, the MAPE is improved by 17.75%. Meanwhile, the GloWS-Net outperforms the FCN, traditional CNN, modified CNN (MCNN) and CyGNSSnet models in global wind speed retrieval especially at high wind speeds.

The Tianmu-1 constellation is mainly based on BeiDou/GNSS radio occultation (GNSS-RO) and BeiDou/GNSS reflectometry (GNSS-R) remote sensing technology, which can simultaneously achieve integrated stereo detection of GNSS-RO and GNSS-R. It is the first commercial GNSS remote sensing detection constellation in the world to achieve integrated business detection of “land surface, ocean, three-dimensional atmosphere, and ionized environment”. Furthermore, it is the first GNSS remote sensing detection constellation in China that is compatible with receiving the five major GNSS satellite navigation systems (i.e., Global Positioning System, BeiDou, Galileo, GLONASS and Quasi-Zenith Satellite System). This study used Tianmu-1 GPS-R/BDS-R/GAL-R/GLO-R global wind speed data from July 2023 to December 2023, and used five datasets as evaluation data, including the ERA5 reanalysis, CYGNSS L2, SMOS, CCMP and NDBC buoy wind speed products, to present the results of the mission's first evaluation of sea surface wind speed estimates. The results show that the Tianmu-1 retrieval wind speed has good consistency with the CYGNSS verification wind speed. When the wind speed range is 0-35 m/s, its minimum RMSE can reach 1.74 m/s. The RMSE of the Tianmu-1 retrieval wind speed and the other four verification wind speeds (ERA5, CCMP, SMOS_SCA, SMOS_SCD) are 2.25 m/s, 2.33 m/s, 2.74 m/s, and 3.17 m/s, respectively. For the wind speed products of the four systems in the Tianmu-1 constellation, GAL showed the best accuracy results. In addition, a comparative verification was conducted with buoy wind speeds, the BDS system demonstrated the best accuracy results, with an RMSE of 1.97m/s.

The influence of solar altitude and azimuth angles makes shadows prevalent in remote sensing images of rugged terrains. Consequently, the normalized difference vegetation index (NDVI) of the shadow areas is much lower than that of sunlit areas—a phenomenon known as the NDVI topographic shadow effect. In this study, we developed an NDVI topographic shadow effect correction (NTSEC) model. The NTSEC is based on the difference in solar radiation between the sunlit and shadow areas, and introduces a variable factor that indicates the intensity of shadows to simulate the reflectance for direct solar light not received in the shadow areas. The simulated reflectance for direct solar light in the shadow areas is used as a compensation value to be summed with the original reflectance for calculating the corrected NDVI. Landsat 8 Operational Land Imager images from two different regions were used to test the NTSEC method and multiple strategies were employed to provide objective evaluative results. The model performance was compared with four commonly used topographic correction (TC) models: C-correction, Minnaert, variable empirical coefficient algorithm, and statistical empirical. The results show that NTSEC can suppress the overcorrection of the self shadow areas that are difficult to eliminate in the TC methods, while simultaneously improving the undercorrection of the cast shadow areas. The corrected NDVI of the self shadow and cast shadow areas were almost the same. The NDVI differences between shady and sunny slopes were significantly reduced after correction. In addition, the NTSEC method did not produce outliers, and the NDVI of different land cover types retained interclass stability. In summary, the NTSEC model can be used as a simple and robust method for correcting the NDVI in shadow areas.

Spaceborne GNSS reflectometry (GNSS-R) missions have been successfully launched in recent years, such as Technology Demonstration Satellite (TDS-1) in 2014, Cyclone Global Navigation Satellite System (CYGNSS) in 2016, Bufeng (BF)-1 A/B in 2019, and Fengyun (FY)-3E/3F/3G and Tianmu-1, launched successively in 2021. They provide a large amount of data to support spaceborne GNSS-R remote sensing applications, and spaceborne GNSS-R technology has also been widely used in various remote sensing fields by virtue of its advantages. With the rise of artificial intelligence (AI), many machine learning (ML) models have been developed for GNSS-R observations to estimate geophysical parameters. In particular, deep learning (DL) techniques have proved to have great potential to improve the accuracy of retrieval models in spaceborne GNSS-R applications, including ocean, land, cryosphere, atmosphere, and environment monitoring. This article provides the first comprehensive review of the application of ML in GNSS-R for Earth observation and remote sensing. The article first summarizes common ML algorithms as well as their basic concepts and theories. It then thoroughly reviews the progress of ML methods in the field of spaceborne GNSS-R and discusses the advantages, disadvantages, and challenges of ML models applied to GNSS-R. More importantly, it is imperative to adopt DL into the field of GNSS-R remote sensing and use it as a general model to tackle unprecedented, large-scale, and impactful challenges in areas such as ocean, land, cryosphere, atmosphere, hydrology, and environment remote sensing.