Search

Soil moisture (SM) plays an essential role in the hydrological cycle, drought monitoring, and water resources management. However, passive microwave remote sensing products offer coarse spatial resolutions (approximately 25–40 km), greatly limiting their applications. In this study, we considered vegetation memory and increased the amount of vegetation data by spatiotemporal fusion, integrated lagged vegetation index and fusion data as model inputs, and downscaled the spatial resolution of SMAP SM using the Random Forest (RF) model as well as multi-source remote sensing data. The downscaled SM was validated with 30 in situ SM measurements and daily precipitation data and explored the contributions of NDVIlagged and NDVIfused in downscaling. The results show that the downscaled SM is highly consistent with the in situ SM measurements. The correlation ranges from 0.628 to 0.849 with an average of 0.689. The root mean square error (RMSE) ranges from 0.024 to 0.094 m3/m3 with an average of 0.057 m3/m3. The proposed method leverages the strengths of the RF model, fusion vegetation data, and lagged vegetation data to improve high-resolution SM accuracy.

In the research of automatic interpretation of remote sensing images, semantic segmentation based on deep convolutional neural networks has been rapidly developed and applied, and the feature segmentation accuracy and network model generalization ability have been gradually improved. However, most of the network designs are mainly oriented to the three visible RGB bands of remote sensing images, aiming to be able to directly borrow the mature natural image semantic segmentation networks and pre-trained models, but simultaneously causing the waste and loss of spectral information in the invisible light bands such as near-infrared (NIR) of remote sensing images. Combining the advantages of multispectral data in distinguishing typical features such as water and vegetation, we propose a novel deep neural network structure called the multispectral semantic segmentation network (MSNet) for semantic segmentation of multi-classified feature scenes. The multispectral remote sensing image bands are split into two groups, visible and invisible, and ResNet-50 is used for feature extraction in both coding stages, and cascaded upsampling is used to recover feature map resolution in the decoding stage, and the multi-scale image features and spectral features from the upsampling process are fused layer by layer using the feature pyramid structure to finally obtain semantic segmentation results. The training and validation results on two publicly available datasets show that MSNet has competitive performance. The code is available: https://github.com/taochx/MSNet.

Study region: Ten major river basins in China. Study focus: The spatial and temporal distribution of terrestrial water storage (TWS) in China is significantly affected by global climate change and increased human activity. In this study, we analyzed the spatial and temporal variability of TWS in ten Chinese basins based on data of the Gravity Recovery and Climate Experiment (GRACE). To discuss the driving force of TWS, we assessed the relative contributions and time lags of precipitation (P), evapotranspiration (ET), and runoff (R) to TWS using Spearman correlation analysis and partial least squares regression (PLS). New hydrological insights for the region: Results indicate that: (1) TWS generally shows a reduction trend at a rate of 1.58 ± 0.067 mm/a from 2003 to 2020, with the most significant decreasing trend in September (−2.77 ± 0.070 mm/a). (2) The relative contributions of P, ET, and R to the TWS in China are 29.89 ± 6.98%, 31.03 ± 6.92% and 39.09 ± 10.82%, respectively, and are more prominent in low-latitude regions than in high-latitude regions. (3) The best-correlated lag times were 1–2 months between the P and TWS responses. (4) Melting snow, ice and groundwater extraction may have weakened the response of the northern TWS to the climate. The results provide insight into the spatial and temporal variation in water storage, which can provide a basis for the scientific and effective management of water resources.

Soil moisture (SM) is an indispensable variable in drought monitoring and weather forecast. L-band is found to be the most suitable band for retrieving surface SM. Here, we evaluate two L-band passive microwave SM products Soil Moisture Active and Passive (SMAP) and Soil Moisture and Ocean Salinity (SMOS) in Inner Mongolia. The collected in-situ data from 24 measured sites and the triple collocation (TC) analysis method (using Global Land Data Assimilation System (GLDAS) Noah and the Advanced Scatterometer (ASCAT) SM data as a reference dataset) are used to evaluate SMAP and SMOS SM products. In the validation based on in-situ SM, SMAP shows the highest correlation with the in-situ SM, followed by GLDAS and SMOS. The root mean square error (RMSE) and bias value of SMAP is the lowest. The validation results of each in-situ station show that the median correlation coefficient of ASCAT is the highest, followed by SMAP, GLDAS, and SMOS. The median RMSE and bias of SMAP are the lowest, while SMOS performs the worst among the three products. TC analysis results show that SMAP has better performance with the majority of the random errors distributed between 0.02 and 0.03 m3/m3. The average random error of SMAP is small, while SMOS has relatively large random errors. Simultaneously, SMAP performs better than GLDAS and SMOS in grassland and low vegetation coverage areas. The research results and analysis of this paper are expected to provide some insights for improving the quality of SM products.

NDVI (Normalized difference vegetation index) is a critical variable for monitoring climate change, studying ecological balance, and exploring the pattern of regional phenology. Traditional neural network models only consider image features in time series prediction, while historical data and its changes play an important role in time series forecasting. For this study, we proposed convolutional neural networks (CNN) combined feature engineering forecasting model (SF-CNN), which integrated both the advantages of image characteristics learned from CNN and statistic characteristics calculated by historical data related to the forecast period to improve the accuracy of NDVI predictions in the next 3 months with 30-day interval at multiple complex areas. To intuitively show the performance of SF-CNN, it was compared with CNN using the same parameters. Results mainly showed that (1) in terms of visual analysis, the texture, pattern, and structure of predicted NDVI using SF-CNN are similar to the observed NDVI, and SF-CNN exhibits strong generalization ability; (2) in terms of quantitative assessment, SF-CNN generally outperforms CNN, and it can improve the reliability and robustness for predicting NDVI through simple statistical characteristics while reducing the uncertainties; (3) SF-CNN can learn seasonal and sudden changes in four different and complex study areas with considerable accuracy and without extra data.

Solar-induced chlorophyll fluorescence (SIF) has been shown to be a powerful proxy for photosynthesis and a promising indicator of drought monitoring, but the ability of high-resolution satellite-derived SIF for drought monitoring has not been widely investigated due to a lack of data. The lack of high spatiotemporal resolution satellite SIF hinders the resolution enhancement of SIF derived by downscaling or reconstruction algorithms. The TROPOspheric Monitoring Instrument (TROPOMI) SIF provides an alternative with finer spatiotemporal resolution. We present an operational downscaling method to generate 500 m 16-day SIF (TSIF) using Neural Networks over a local spatiotemporal window. The results showed that our method is very robust against overfitting, and TSIF has a strong spatiotemporal consistency with TROPOMI SIF (TROPOSIF) with R2=0.956 and RMSE=0.054 mWm−2sr−1nm−1. Comparison with another SIF product (CASIF) showed a spatiotemporal consistency with TSIF. Comparison with tower gross primary productivity (GPP) from AmeriFlux in California showed a strong correlation with R2 for multiple ecosystems ranging from 0.58 to 0.88. We explored the capacity of TSIF for monitoring a drought event in Henan, China, showing that TSIF is more sensitive to drought and precipitation compared to the Enhanced Vegetation Index. Our TSIF is a very promising indicator for regional drought monitoring.

Small-scale maps are generally used in spatial analysis for fast calculation, but part of important features are missing due to its generalization level, which makes the analysis results less accurate. Therefore, it is necessary to improve feature completeness of smallscale maps. The goal of this paper is to put forward a mapping method of integrating the existing multi-scale river thematic maps. In order to achieve this goal, this paper proposed an algorithm for multi-scale line features matching by calculating the distance from node to polyline and an integrating algorithm by simplifying, shortening and merging the features from the original multi-scale thematic maps. The experimental results proved that the new map produced by the method proposed in this paper keeps the same scale as the original small-scale map and it is consistent with the original large-scale map in terms of feature completeness. The strategy proposed in this paper can be used to produce a new river thematic map concluding all the features that users need; moreover, the new map not only expresses features completely but also takes up less storage. [ABSTRACT FROM AUTHOR]