Search Results (19)

With the rapid advancement of urban intelligence, there is an increasingly urgent demand for technological innovation in traffic management. License plate recognition technology can achieve high accuracy under ideal conditions but faces significant challenges in complex traffic environments and adverse weather conditions. To address these challenges, we propose the enhanced attention network and decoding for license plate recognition model (EAND-LPRM). This model leverages an encoder to extract features from image sequences and employs a self-attention mechanism to focus on critical feature information, enhancing its capability to handle complex traffic scenarios such as rainy weather and license plate distortion. We have curated and utilized publicly available datasets that closely reflect real-world scenarios, ensuring transparency and reproducibility. Experimental evaluations conducted on these datasets, which include various complex scenarios, demonstrate that the EAND-LPRM model achieves an accuracy of 94%, representing a 6% improvement over traditional license plate recognition algorithms. The main contributions of this research include the development of a novel attention-mechanism-based architecture, comprehensive evaluation on multiple datasets, and substantial performance improvements under diverse and challenging conditions. This study provides a practical solution for automatic license plate recognition systems in dynamic and unpredictable environments. Full article

Satellite observations have provided global and regional soil-moisture estimates in the last four decades. However, the accuracy of these observations largely depends on reducing uncertainties in the retrieval algorithms. In this study, we address two challenges affecting the quality of soil-moisture estimates from a widely used soil-moisture-retrieval model, the land parameter retrieval model (LPRM). We studied two improvement schemes that were aimed at reducing uncertainties in open water signals (the LPRMv6_OWF) and vegetation signals (the LPRMv6_Veg), as well as a scheme to reduce their combined impacts (the LPRMv6_OWFVeg) on LPRM-retrieved soil moisture using the FengYun-3B (FY-3B) satellite observations. To assess the impacts of the improvement schemes, we utilized in situ soil moisture from the Jiangsu and Jiangxi provinces in China. We found that the retrievals (Rs) of the LPRMv6_Veg and the LPRMv6_OWFVeg were mainly in the range of 0.2 to 0.5 in Jiangsu and Jiangxi, with increases of 0.1 compared to those of the LPRMv6. The standard deviation (SD) of the LPRMv6_OWFVeg increased in Jiangsu, while the R of the LPRMv6_OWF increased in Jiangsu by 0.05–0.1 compared to that of the LPRMv6, but the SD tended to become worse. In Jiangxi, there was an increase of 0.1 in R. The results show that each of these algorithms improved the accuracy of soil-moisture inversion to some extent, compared to the original algorithm, with the LPRMv6_OWFVeg showing the greatest improvement, followed by the LPRMv6_Veg. The accuracy of both the LPRMv6_OWF and the LPRMv6_OWFVeg decreased to some extent when the open-water fraction (OWF) was greater than 0.2. Full areal extent analyses based on triple collocation showed significant improvements in correlations and minimized errors across different vegetation scenarios over the entire region of China in both the LPRMv6_OWF and the LPRMv6_Veg. However, reduced qualities were found in arid regions in northern China because of the nonlinear relationships between land-surface temperature, vegetation, and soil moisture in the LPRM. These results highlight important lessons for developing comprehensive improvement schemes for soil-moisture retrievals from passive microwave satellite observations. Full article

Soil moisture (SM) exists at the land-atmosphere interface and serves as a key driving variable that affects global water balance and vegetation growth. Its importance in climate and earth system studies necessitates a comprehensive evaluation and comparison of mainstream global remote sensing/reanalysis SM products. In this study, we conducted a thorough verification of ten global remote sensing/reanalysis SM products: SMAP DCA, SMAP SCA-H, SMAP SCA-V, SMAP-IB, SMOS IC, SMOS L3, LPRM_C1, LPRM_C2, LPRM_X, and ERA5-Land. The verification was based on ground observation data from the International SM Network (ISMN), considering both static factors (such as climate zone, land cover type, and soil type) and dynamic factors (including SM, leaf area index, and land surface temperature). Our goal was to assess the accuracy and applicability of these products. We analyzed the spatial and temporal distribution characteristics of global SM and discussed the vegetation effect on SM products. Additionally, we examined the global high-frequency fluctuations in the SMAP L-VOD product, along with their correlation with the normalized difference vegetation index, leaf area index, and vegetation water content. Our findings revealed that product quality was higher in regions located in tropical and arid zones, closed shrubs, loose rocky soil, and gray soil with low soil moisture, low leaf area index, and high average land surface temperature. Among the evaluated products, SMAP-IB, SMAP DCA, SMAP SCA-H, SMAP SCA-V, and ERA5-Land consistently performed better, demonstrating a good ability to capture the spatial and temporal variations in SM and showing a correlation of approximately 0.60 with ISMN. SMOS IC and SMOS L3 followed in performance, while LPRM_C1, LPRM_C2, and LPRM_X exhibited relatively poor results in SM inversion. These findings serve as a valuable reference for improving satellite/reanalysis SM products and conducting global-scale SM studies. Full article

Remote sensing and land surface models promote the understanding of soil moisture dynamics by means of multiple products. These products differ in data sources, algorithms, model structures and forcing datasets, complicating the selection of optimal products, especially in regions with complex land covers. This study compared different products, algorithms and flagging strategies based on in situ observations in Anhui province, China, an intensive agricultural region with diverse landscapes. In general, models outperform remote sensing in terms of valid data coverage, metrics against observations or based on triple collocation analysis, and responsiveness to precipitation. Remote sensing performs poorly in hilly and densely vegetated areas and areas with developed water systems, where the low data volume and poor performance of satellite products (e.g., Soil Moisture Active Passive, SMAP) might constrain the accuracy of data assimilation (e.g., SMAP L4) and downstream products (e.g., Cyclone Global Navigation Satellite System, CYGNSS). Remote sensing has the potential to detect irrigation signals depending on algorithms and products. The single-channel algorithm (SCA) shows a better ability to detect irrigation signals than the Land Parameter Retrieval Model (LPRM). SMAP SCA-H and SCA-V products are the most sensitive to irrigation, whereas the LPRM-based Advanced Microwave Scanning Radiometer 2 (AMSR2) and European Space Agency (ESA) Climate Change Initiative (CCI) passive products cannot reflect irrigation signals. The results offer insight into optimal product selection and algorithm improvement. Full article

Recent developments in passive microwave remote sensing have provided an effective tool for monitoring global soil moisture (SM) observations on a spatiotemporal basis, filling the gap of uneven in-situ measurement distribution. In this paper, four passive microwave SM products from three bands (L, C, and X) are evaluated using in-situ observations, over a dry–wet cycle agricultural (mostly paddy/wheat cycle crops) critical zone observatory (CZO) in the Central Ganga basin, India. The L-band and C/X-band information from Soil Moisture Active Passive (SMAP) Passive Enhanced Level 3 (SMAP-L3) and Advanced Microwave Scanning Radiometer 2 (AMSR2), respectively, was selected for the evaluation. The AMSR2 SM products used here were derived using the Land Parameter Retrieval Model (LPRM) algorithm. Spatially averaged observations from 20 in-situ distributed locations were initially calibrated with a single and continuous monitoring station to obtain long-term ground-based data. Furthermore, several statistical metrices along with the triple collocation (TC) error model were used to evaluate the overall accuracy and random error variance of the remote sensing products. The results indicated an overall superior performance of SMAP-L3 with a slight dry bias (−0.040 m³·m⁻³) and a correlation of 0.712 with in-situ observations. This also met the accuracy requirement (0.04 m³·m⁻³) during most seasons with a modest accuracy (0.059 m³·m⁻³) for the entire experimental period. Among the LPRM datasets, C1 and C2 products behaved similarly (R = 0.621) with a ubRMSE of 0.068 and 0.081, respectively. The X-band product showed a relatively poor performance compared to the other LPRM products. Seasonal performance analysis revealed a higher correlation for all the satellite SM products during monsoon season, indicating a strong seasonality of precipitation. The TC analysis indicated the lowest error variance (0.02 ± 0.003 m³·m⁻³) for the SMAP-L3. In the end, we introduced Spearman’s rank correlation to assess the dynamic response of SM observations to climatic and vegetation parameters. Full article

Soil moisture plays an essential role in the land-atmosphere interface. It has become necessary to develop quality large-scale soil moisture data from satellite observations for relevant applications in climate, hydrology, agriculture, etc. Specifically, microwave-based observations provide more consistent land surface records because they are unhindered by cloud conditions. The recent microwave radiometers onboard FY-3B, FY-3C and FY-3D satellites launched by China’s Meteorological Administration (CMA) extend the number of available microwave observations, covering late 2011 up until the present. These microwave observations have the potential to provide consistent global soil moisture records to date, filling the data gaps where soil moisture estimates are missing in the existing records. Along these lines, we studied the FY-3C to understand its added value due to its unique time of observation in a day (ascending: 22:15, descending: 10:15) absent from the existing satellite soil moisture records. Here, we used the triple collocation technique to optimize a benchmark retrieval model of land surface temperature (LST) tailored to the observation time of FY3C, by evaluating various soil moisture scenarios obtained with different bias-imposed LSTs from 2014 to 2016. The globally optimized LST was used as an input for the land parameter retrieval model (LPRM) algorithm to obtain optimized global soil moisture estimates. The obtained FY-3C soil moisture observations were evaluated with global in situ and reanalysis datasets relative to FY3B soil moisture products to understand their differences and consistencies. We found that the RMSEs of their anomalies were mostly concentrated between 0.05 and 0.15 m³ m⁻³, and correlation coefficients were between 0.4 and 0.7. The results showed that the FY-3C ascending data could better capture soil moisture dynamics than the FY-3B estimates. Both products were found to consistently complement the skill of each other over space and time globally. Finally, a linear combination approach that maximizes temporal correlations merged the ascending and descending soil moisture observations separately. The results indicated that superior soil moisture estimates are obtained from the combined product, which provides more reliable global soil moisture records both day and night. Therefore, this study aims to show that there is merit to the combined usage of the two FY-3 products, which will be extended to the FY-3D, to fill the gap in existing long-term global satellite soil moisture records. Full article

The CCI Soil Moisture dataset (CCI SM) is the most extensive climate data record of satellite soil moisture to date. To maximize its function as a climate benchmark, both long-term consistency and (model-) independence are high priorities. Two unique L-band missions integrated into the CCI SM are SMOS and SMAP. However, they lack the high-frequency microwave sensors needed to determine the effective temperature and snow/frozen flagging, and therefore use input from (varying) land surface models. In this study, the impact of replacing this model input by temperature and filtering based on passive microwave observations is evaluated. This is derived from an inter-calibrated dataset (ICTB) based on six passive microwave sensors. Generally, this leads to an expected increase in revisit time, which goes up by about 0.5 days (~15% loss). Only the boreal regions have an increased coverage due to more accurate freeze/thaw detection. The boreal regions become wetter with an increased dynamic range, while the tropics are dryer with decreased dynamics. Other regions show only small differences. The skill was evaluated against ERA5-Land and in situ observations. The average correlation against ERA5-Land increased by 0.05 for SMAP ascending/descending and SMOS ascending, whereas SMOS descending decreased by 0.01. For in situ sensors, the difference is less pronounced, with only a significant change in correlation of 0.04 for SM SMOS ascending. The results indicate that the use of microwave-based input for temperature and filtering is a viable and preferred alternative to the use of land surface models in soil moisture climate data records from passive microwave sensors. Full article

An in situ soil moisture observation network at pixel scale is constructed in cropland in the northeast of China for accurate regional soil moisture evaluations of satellite products. The soil moisture products are based on the Japan Aerospace Exploration Agency (JAXA) algorithm and the Land Parameter Retrieval Model (LPRM) from the Advanced Microwave Scanning Radiometer 2 (AMSR2), and the products from the FengYun-3B (FY3B) satellite are evaluated using synchronous in situ data collected by the EC-5 sensors at the surface in a typical cropland in the northeast of China during the crop-growing season from May to September 2017. The results show that the JAXA product provides an underestimation with a bias (b) of -0.094 cm³/cm³, and the LPRM soil moisture product generates an overestimation with a b of 0.156 cm³/cm³. However the LPRM product shows a better correlation with the in situ data, especially in the early experimental period when the correlation coefficient is 0.654, which means only the JAXA product in the early stage, with an unbiased root mean square error (ubRMSE) of 0.049 cm³/cm³ and a b of -0.043 cm³/cm³, reaches the goal accuracy (±0.05 cm³/cm³). The FY3B has consistently obtained microwave brightness temperature data, but its soil moisture product data in the study area is seriously missing during most of the experimental period. However, it recovers in the later period and is closer to the in situ data than the JAXA and LPRM products. The three products show totally different trends with vegetation cover, soil temperature, and actual soil moisture itself in different time periods. The LPRM product is more sensitive and correlated with the in situ data, and is less susceptible to interferences. The JAXA is numerically closer to the in situ data, but the results are still affected by temperature. Both will decrease in accuracy as the actual soil moisture increases. The FY3B seems to perform better at the end of the whole period after data recovery. Full article

High-quality and long time-series soil moisture (SM) data are increasingly required for the Qinghai-Tibet Plateau (QTP) to more accurately and effectively assess climate change. In this study, to evaluate the accuracy and effectiveness of SM data, five passive microwave remotely sensed SM products are collected over the QTP, including those from the soil moisture active passive (SMAP), soil moisture and ocean salinity INRA-CESBIO (SMOS-IC), Fengyun-3B microwave radiation image (FY3B), and two SM products derived from the advanced microwave scanning radiometer 2 (AMSR2). The two AMSR2 products are generated by the land parameter retrieval model (LPRM) and the Japan Aerospace Exploration Agency (JAXA) algorithm, respectively. The SM products are evaluated through a two-stage data comparison method. The first stage is direct validation at the grid scale. Five SM products are compared with corresponding in situ measurements at five in situ networks, including Heihe, Naqu, Pali, Maqu, and Ngari. Another stage is indirect validation at the regional scale, where the uncertainties of the data are quantified by using a three-cornered hat (TCH) method. The results at the regional scale indicate that soil moisture is underestimated by JAXA and overestimated by LPRM, some noise is contained in temporal variations in SMOS-IC, and FY3B has relatively low absolute accuracy. The uncertainty of SMAP is the lowest among the five products over the entire QTP. In the SM map composed by five SM products with the lowest pixel-level uncertainty, 66.64% of the area is covered by SMAP (JAXA: 19.39%, FY3B: 10.83%, LPRM: 2.11%, and SMOS-IC: 1.03%). This study reveals some of the reasons for the different performances of these five SM products, mainly from the perspective of the parameterization schemes of their corresponding retrieval algorithms. Specifically, the parameterization configurations and corresponding input datasets, including the land-surface temperature, the vegetation optical depth, and the soil dielectric mixing model are analyzed and discussed. This study provides quantitative evidence to better understand the uncertainties of SM products and explain errors that originate from the retrieval algorithms. Full article

Long-term climate records of soil moisture are of increased importance to climate researchers. In this study, we aim to evaluate the quality of three different fusion approaches that combine soil moisture retrieval from multiple satellite sensors. The arrival of L-band missions has led to an increased focus on the integration of L-band-based soil moisture retrievals in climate records, emphasizing the need to improve our understanding based on its added value within a multi-sensor framework. The three evaluated approaches were developed on 10-year passive microwave data (2003–2013) from two different satellite sensors, i.e., SMOS (2010–2013) and AMSR-E (2003–2011), and are based on a neural network (NN), regressions (REG), and the Land Parameter Retrieval Model (LPRM). The ability of the different approaches to best match AMSR-E and SMOS in their overlapping period was tested using an inter-comparison exercise between the SMOS and AMSR-E datasets, while the skill of the individual soil moisture products, based on anomalies, was evaluated using two verification techniques; first, a data assimilation technique that links precipitation information to the quality of soil moisture (expressed as the R_value), and secondly the triple collocation analysis (TCA). ASCAT soil moisture was included in the skill evaluation, representing the active microwave-based counterpart of soil moisture retrievals. Besides a semi-global analysis, explicit focus was placed on two regions that have strong land–atmosphere coupling, the Sahel (SA) and the central Great Plains (CGP) of North America. The NN approach gives the highest correlation coefficient between SMOS and AMSR-E, closely followed by LPRM and REG, while the absolute error is approximately the same for all three approaches. The R_value and TCA show the strength of using different satellite sources and the impact of different merging approaches on the skill to correctly capture soil moisture anomalies. The highest performance is found for AMSR-E over sparse vegetation, for SMOS over moderate vegetation, and for ASCAT over dense vegetation cover. While the two SMOS datasets (L3 and LPRM) show a similar performance, the three AMSR-E datasets do not. The good performance for AMSR-E over spare vegetation is mainly perceived for AMSR-E LPRM, benefiting from the physically based model, while AMSR-E NN shows improved skill in densely vegetated areas, making optimal use of the SMOS L3 training dataset. AMSR-E REG has a reasonable performance over sparsely vegetated areas; however, it quickly loses skill with increasing vegetation density. The findings over the SA and CGP mainly reflect results that are found in earlier sections. This confirms that historical soil moisture datasets based on a combination of these sources are a valuable source of information for climate research. Full article

A good knowledge of the quality of the satellite soil moisture products is of great importance for their application and improvement. This paper examines the performance of eight satellite-based soil moisture products, including the Soil Moisture Active Passive (SMAP) passive Level 3 (L3), the Soil Moisture and Ocean Salinity (SMOS) Centre Aval de Traitement des Données SMOS (CATDS) L3, the Japan Aerospace Exploration Agency (JAXA) Advanced Microwave Scanning Radiometer 2 (AMSR2) L3, the Land Parameter Retrieval Model (LPRM) AMSR2 L3, the European Space Agency (ESA) Climate Change Initiative (CCI) L3, the Chinese Fengyun-3B (FY3B) L2 soil moisture products at a coarse resolution of ~0.25°, and the newly released SMAP enhanced passive L3 and JAXA AMSR2 L3 soil moisture products at a medium resolution of ~0.1°. The ground soil moisture used for validation were collected from two well-calibrated and dense networks, including the Little Washita Watershed (LWW) network in the United States and the REMEDHUS network in Spain, each with different land cover. The results show that the SMAP passive soil moisture product outperformed the other products in the LWW network region, with an unbiased root mean square (ubRMSE) of 0.027 m³ m⁻³, whereas the FY3B soil moisture performed the best in the REMEDHUS network region, with an ubRMSE of 0.025 m³ m⁻³. The JAXA product performed much better at 0.25° than at 0.1°, but at both resolutions it underestimated soil moisture most of the time (bias < −0.05 m³ m⁻³). The SMAP-enhanced passive soil moisture product captured the temporal variation of ground measurements well, with a correlation coefficient larger than 0.8, and was generally superior to the JAXA product. The LPRM showed much larger amplitude and temporal variation than the ground soil moisture, with a wet bias larger than 0.09 m³ m⁻³. The underestimation of surface temperature may have contributed to the general dry bias found in the SMAP (−0.018 m³ m⁻³ for LWW and 0.016 m³ m⁻³ for REMEDHUS) and SMOS (−0.004 m³ m⁻³ for LWW and −0.012 m³ m⁻³ for REMEDHUS) soil moisture products. The ESA CCI product showed satisfactory performance with acceptable error metrics (ubRMSE < 0.045 m³ m⁻³), revealing the effectiveness of merging active and passive soil moisture products. The good performance of SMAP and FY3B demonstrates the potential in integrating them into the existing long-term ESA CCI product, in order to form a more reliable and useful product. Full article

A method using a nonlinear auto-regressive neural network with exogenous input (NARXnn) to retrieve time series soil moisture (SM) that is spatially and temporally continuous and high quality over the Heihe River Basin (HRB) in China was investigated in this study. The input training data consisted of the X-band dual polarization brightness temperature (TB) and the Ka-band V polarization TB from the Advanced Microwave Scanning Radiometer II (AMSR2), Global Land Satellite product (GLASS) Leaf Area Index (LAI), precipitation from the Tropical Rainfall Measuring Mission (TRMM) and the Global Precipitation Measurement (GPM), and a global 30 arc-second elevation (GTOPO-30). The output training data were generated from fused SM products of the Japan Aerospace Exploration Agency (JAXA) and the Land Surface Parameter Model (LPRM). The reprocessed fused SM from two years (2013 and 2014) was inputted into the NARXnn for training; subsequently, SM during a third year (2015) was estimated. Direct and indirect validations were then performed during the period 2015 by comparing with in situ measurements, SM from JAXA, LPRM and the Global Land Data Assimilation System (GLDAS), as well as precipitation data from TRMM and GPM. The results showed that the SM predictions from NARXnn performed best, as indicated by their higher correlation coefficients (R ≥ 0.85 for the whole year of 2015), lower Bias values (absolute value of Bias ≤ 0.02) and root mean square error values (RMSE ≤ 0.06), and their improved response to precipitation. This method is being used to produce the NARXnn SM product over the HRB in China. Full article

In recent years, different space agencies have launched satellite missions that carry passive microwave instruments on-board that can measure surface soil moisture. Three currently operational missions are the Soil Moisture and Ocean Salinity (SMOS) mission developed by the European Space Agency (ESA), the Advanced Microwave Scanning Radiometer 2 (AMSR2) developed by the Japan Aerospace Exploration Agency (JAXA), and the Microwave Radiation Imager (MWRI) from China’s National Satellite Meteorological Centre (NSMC). In this study, the quality of surface soil moisture anomalies derived from these passive microwave instruments was sequentially assessed over the mainland of the People’s Republic of China. First, the impact of a recent update in the Land Parameter Retrieval Model (LPRM) was assessed for MWRI observations. Then, the soil moisture measurements retrieved from the X-band observations of MWRI were compared with those of AMSR2, followed by an internal comparison of the multiple frequencies of AMSR2. Finally, SMOS retrievals from two different algorithms were also included in the comparison. For each sequential step, processing and verification chains were specifically designed to isolate the impact of algorithm (version), observation frequency or instrument characteristics. Two verification techniques are used: the statistical Triple Collocation technique is used as the primary verification tool, while the precipitation-based R_value technique is used to confirm key results. Our results indicate a consistently better performance throughout the entire study area after the implementation of an update of the LPRM. We also find that passive microwave observations in the AMSR2 C-band frequency (6.9 GHz) have an advantage over the AMSR2 X-band frequency (10.7 GHz) over moderate to densely vegetated regions. This finding is in line with theoretical expectations as emitted soil radiation will become masked under a dense canopy with stricter thresholds for higher passive microwave frequencies. Both AMSR2 and MWRI make X-band observations; a direct comparison between them reveals a consistently higher quality obtained by AMSR2, specifically over semi-arid climate regimes. Unfortunately, Radio Frequency Interference hampers the usefulness of soil moisture products for the SMOS L-band mission, leading to a significantly reduced revisit time over the densely populated eastern part of the country. Nevertheless, our analysis demonstrates that soil moisture products from a number of multi-frequency microwave sensors are credible alternatives for this dedicated L-band mission over the mainland of the People’s Republic of China. Full article

In the present study, soil moisture assimilation is conducted over the Indian subcontinent, using the Noah Land Surface Model (LSM) and the Soil Moisture Operational Products System (SMOPS) observations by utilizing the Ensemble Kalman Filter. The study is conducted in two stages involving assimilation of soil moisture and simulation of brightness temperature (Tb) using radiative transfer scheme. The results of data assimilation in the form of simulated Surface Soil Moisture (SSM) maps are evaluated for the Indian summer monsoonal months of June, July, August, September (JJAS) using the Land Parameter Retrieval Model (LPRM) AMSR-E soil moisture as reference. Results of comparative analysis using the Global land Data Assimilation System (GLDAS) SSM is also discussed over India. Data assimilation using SMOPS soil moisture shows improved prediction over the Indian subcontinent, with an average correlation of 0.96 and average root mean square difference (RMSD) of 0.0303 m³/m³. The results are promising in comparison with the GLDAS SSM, which has an average correlation of 0.93 and average RMSD of 0.0481 m³/m³. In the second stage of the study, the assimilated soil moisture is used to simulate X-band brightness temperature (Tb) at an incidence angle of 55° using the Community Microwave Emission Model (CMEM) Radiative transfer Model (RTM). This is aimed to study the sensitivity of the parameterization scheme on Tb simulation over the Indian subcontinent. The result of Tb simulation shows that the CMEM parameterization scheme strongly influences the simulated top of atmosphere (TOA) brightness temperature. Furthermore, the Tb simulations from Wang dielectric model and Kirdyashev vegetation model shows better similarity with the actual AMSR-E Tb over the study region. Full article

A method to retrieve soil moisture (SM) from Advanced Scanning Microwave Radiometer—Earth Observing System Sensor (AMSR-E) observations using Soil Moisture and Ocean Salinity (SMOS) Level 3 SM as a reference is discussed. The goal is to obtain longer time series of SM with no significant bias and with a similar dynamical range to that of the SMOS SM dataset. This method consists of training a neural network (NN) to obtain a global non-linear relationship linking AMSR-E brightness temperatures ( $T_{\mathrm{b}}$ ) to the SMOS L3 SM dataset on the concurrent mission period of 1.5 years. Then, the NN model is used to derive soil moisture from past AMSR-E observations. It is shown that in spite of the different frequencies and sensing depths of AMSR-E and SMOS, it is possible to find such a global relationship. The sensitivity of AMSR-E $T_{\mathrm{b}}$ ’s to soil temperature ( $T_{soil}$ ) was also evaluated using European Centre for Medium-Range Weather Forecast Interim/Land re-analysis (ERA-Land) and Modern-Era Retrospective analysis for Research and Applications-Land (MERRA-Land) model data. The best combination of AMSR-E $T_{\mathrm{b}}$ ’s to retrieve $T_{soil}$ is H polarization at 23 and 36 GHz plus V polarization at 36 GHz. Regarding SM, several combinations of input data show a similar performance in retrieving SM. One NN that uses C and X bands and $T_{soil}$ information was chosen to obtain SM in the 2003–2011 period. The new dataset shows a low bias (<0.02 m³/m³) and low standard deviation of the difference (<0.04 m³/m³) with respect to SMOS L3 SM over most of the globe’s surface. The new dataset was evaluated together with other AMSR-E SM datasets and the Climate Change Initiative (CCI) SM dataset against the MERRA-Land and ERA-Land models for the 2003–2011 period. All datasets show a significant bias with respect to models for boreal regions and high correlations over regions other than the tropical and boreal forest. All of the global SM datasets including AMSR-E NN were also evaluated against a large number of in situ measurements over four continents. Over Australia, all datasets show a strong level of agreement with in situ measurements. Models perform better over Europe and mountainous regions in North America. Remote sensing datasets (in particular NN and the Land Parameter Retrieval Model (LPRM)) perform as well as models for other North American sites and perform better than models over the Sahel region. Full article