Although numerous satellite-based soil moisture (SM) products can provide spatiotemporally continuous worldwide datasets, they can hardly be employed in characterizing fine-grained regional land surface processes, owing to their coarse spatial resolution. In this study, we proposed a machine-learning-based method to enhance SM spatial accuracy and improve the availability of SM data. Four machine learning algorithms, including classification and regression trees (CART), K-nearest neighbors (KNN), Bayesian (BAYE), and random forests (RF), were implemented to downscale the monthly European Space Agency Climate Change Initiative (ESA CCI) SM product from 25-km to 1-km spatial resolution. During the regression, the land surface temperature (including daytime temperature, nighttime temperature, and diurnal fluctuation temperature), normalized difference vegetation index, surface reflections (red band, blue band, NIR band and MIR band), and digital elevation model were taken as explanatory variables to produce fine spatial resolution SM. We chose Northeast China as the study area and acquired corresponding SM data from 2003 to 2012 in unfrozen seasons. The reconstructed SM datasets were validated against in-situ measurements. The results showed that the RF-downscaled results had superior matching performance to both ESA CCI SM and in-situ measurements, and can positively respond to precipitation variation. Additionally, the RF was less affected by parameters, which revealed its robustness. Both CART and KNN ranked second. Compared to KNN, CART had a relatively close correlation with the validation data, but KNN showed preferable precision. Moreover, BAYE ranked last with significantly abnormal regression values.
Under dual impacts from climate change and human activities, the Yellow River Basin (YRB) of China suffers from droughts and water scarcity. Understanding variations of terrestrial water storage (TWS) over the YRB is significant and beneficial to regional water resources management and sustainable development. This study investigates TWS variations in the YRB using data sets from two solutions (RL05 and RL06) of the Gravity Recovery and Climate Experiment (GRACE) satellites, as well as from global land surface models (the NOAH model and Catchment Land Surface Model [CLSM]) and hydrology and water resources model (PCR‐GLOBWB). Annual terrestrial water storage anomalies (TWSA) variation patterns were tracked by introducing a weighed centroid analysis concept. Human water use was analyzed, and its importance to TWS changes was evaluated by using the random forest algorithm. Conclusions can be briefly summarized as follows: (1) The declining trend of TWS in the YRB from the RL06 solution is more negative than that from RL05; the TWS trend from the PCR‐GLOBWB model is more consistent with GRACE than with the NOAH model and CLSM at the basin level, and the three models all underestimate the declining trend of TWS in the midstream relative to the GRACE solutions. (2) Spatial weighed centroids of annual GRACE TWSA moved toward the headwater of the YRB during the 2003–2015 period, suggesting a wide gap of TWS between the upstream and downstream YRB; the TWSA time series well correlate with the long‐term accumulation of climatic water balance, but the connections became weak in the 2010–2015 period. (3) Groundwater withdrawals have been controlled according to the Water Resources Bulletin, but the stress may be partly shifted to surface water; the increasing trend of ecological and industrial surface water use is significant, following the agriculture water use. (4) For the entire YRB, groundwater use accounts for the majority of feature importance in modeling TWSA time series, and the contribution of climate factors is the least. Agricultural water use ranks first relative to other sectors for the YRB, followed by the ecological and industrial use. This study provides a first comparison of TWSA between the latest Center for Space Research (CSR) GRACE RL06 solution and the previous RL05 solution in the YRB. The results are expected to present a comprehensive picture of TWS variations in the YRB and the impacts from climate and human factors.
Precipitation is an important component of the hydrological cycle and has significant impact on ecological environment and social development, especially in arid areas where water resources are scarce. As a typical arid and semi-arid region, the Mongolian Plateau is ecologically fragile and highly sensitive to climate change. Reliable global precipitation data is urgently needed for the sustainable development over this gauge-deficient region. With high-quality estimates, fine spatiotemporal resolutions, and wide coverage, the state-of-the-art Integrated Multi-satellite Retrievals for Global Precipitation Measurement (IMERG) and European Center for Medium-range Weather Forecasts Reanalysis 5 (ERA5) have great potential for regional climatic, hydrological, and ecological applications. However, how they perform has not been well investigated on the Mongolian Plateau. Therefore, this study evaluated the performance of three IMERG V06 datasets (ER, LR and FR), two ERA5 products (ERA5-HRES and ERA5-Land), and their predecessors (TMPA-3B42 and ERA-Interim) over the region across 2001–2018. The results showed that all products broadly characterized seasonal precipitation cycles and spatial patterns, but only the three reanalysis products, IMERG FR and TMPA-3B42 could capture interannual and decadal variability. When describing daily precipitation, dataset performances ranked ERA5-Land > ERA5-HRES > ERA-Interim > IMERG FR > IMERG LR > IMERG ER > TMPA-3B42. All products showed deficiencies in overestimating weak precipitation and underestimating high-intensity precipitation. Besides, products performed best in agricultural lands and forests along the northern and south-eastern edges, followed by urban areas and grasslands closer to the center, and worst in the sparse vegetation and bare areas of the south-west. Due to a negative effect of topographic complexity, IMERG showed poor detection capabilities in forests. Accordingly, this research currently supports the applicability of reanalysis ERA5 data over the arid, topographically complex Mongolian Plateau, which can inform regional applications with different requirements.
As one of the earliest remote sensing indices, the Normalized Difference Vegetation Index (NDVI) has been employed extensively for vegetation research. However, despite an abundance of NDVI review articles, these studies are predominantly limited to either one subject area or one area, with systematic NDVI reviews being relatively rare. Bibliometrics is a useful method of analyzing scientific literature that has been widely used in many disciplines; however, it has not yet been applied to comprehensively analyze NDVI research. Therefore, we used bibliometrics and scientific mapping methods to analyze citation data retrieved from the Web of Science during 1985–2021 with NDVI as the topic. According to the analysis results, the amount of NDVI research increased exponentially during the study period, and the related research fields became increasingly varied. Moreover, a greater number of satellite and aerial remote sensing platforms resulted in more diverse NDVI data sources. In future, machine learning methods and cloud computing platforms led by Google Earth Engine will substantially improve the accuracy and production efficiency of NDVI data products for more effective global research.
Satellite retrieved soil moisture (SM) shows great potential in hydrological, meteorological, ecological, and agricultural applications, while the coarse resolution limits its utilization in regional scale. The regression tree-based machine learning algorithms reveal promising capability in SM downscaling. However, it lacks systematic study dedicated to intercomparisons of algorithms to explicitly illuminate their characteristics. In this study, comparisons are made to systematically evaluate performances of classification and regression tree (CART), random forest (RF), gradient boost decision tree (GBDT), and extreme gradient boost (XGB) in Soil Moisture Active Passive (SMAP) SM downscaling in southwest France. The results show that the four algorithms downscaled SM are capable of capturing spatial distribution features of the original SMAP SM. The downscaled regions with favorable accuracy are mostly situated in the dominant Mediterranean climate zone with moderate vegetation coverage and mild topography variation. The best results are obtained by GBDT in grassland with R value of 0.77 and ubRMSE value of 0.04 m 3 /m 3. The RF and XGB also achieve good performances. On the whole, the GBDT approach is robust and reliable, which could downscale SM with superior correlation and smaller bias than the others. Besides, it achieves higher accuracy than the original SMAP in grassland and shrubland. The feature importance index of each explainable variable fluctuates regularly among different seasons and models. This study proves the outstanding performance of GBDT in SMAP SM downscaling and is expected to act as a valuable reference for studies focusing on SM scale conversion algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.