摘要：This paper presents a winning solution for the CCKS-2020 financial event extraction task, where the goal is to identify event types, triggers and arguments in sentences across multiple event types. In this task, we focus on resolving two challenging problems (i.e., low resources and element overlapping) by proposing a joint learning framework, named SaltyFishes. We first formulate the event extraction task as a joint probability model. By sharing parameters in the model across different types, we can learn to adapt to low-resource events based on high-resource events. We further address the element overlapping problems by a mechanism of Conditional Layer Normalization, achieving even better extraction accuracy. The overall approach achieves an F1-score of 87.8% which ranks the first place in the competition.
摘要：This paper describes our approach for the Chinese clinical named entity recognition (CNER) task organized by the 2020 China Conference on Knowledge Graph and Semantic Computing (CCKS) competition. In this task, we need to identify the entity boundary and category labels of six entities from Chinese electronic medical record (EMR). We constructed a hybrid system composed of a semi-supervised noisy label learning model based on adversarial training and a rule post-processing module. The core idea of the hybrid system is to reduce the impact of data noise by optimizing the model results. Besides, we used post-processing rules to correct three cases of redundant labeling, missing labeling, and wrong labeling in the model prediction results. Our method proposed in this paper achieved strict criteria of 0.9156 and relax criteria of 0.9660 on the final test set, ranking first.
摘要：The Chinese Software Developer Network (CSDN) is one of the largest information technology communities and service platforms in China. This paper describes the user profiling for CSDN, an evaluation track of SMP Cup 2017. It contains three tasks: (1) user document keyphrase extraction, (2) user tagging and (3) user growth value prediction. In the first task, we treat keyphrase extraction as a classification problem and train a Gradient-Boosting-Decision-Tree model with comprehensive features. In the second task, to deal with class imbalance and capture the interdependency between classes, we propose a two-stage framework: (1) for each class, we train a binary classifier to model each class against all of the other classes independently; (2) we feed the output of the trained classifiers into a softmax classifier, tagging each user with multiple labels. In the third task, we propose a comprehensive architecture to predict user growth value. Our contributions in this paper are summarized as follows: (1) we extract various types of features to identify the key factors in user value growth; (2) we use the semi-supervised method and the stacking technique to extend labeled data sets and increase the generality of the trained model, resulting in an impressive performance in our experiments. In the competition, we achieved the first place out of 329 teams.
摘要：With the popularity of social media, there has been an increasing interest in user profiling and its applications nowadays. This paper presents our system named UIR-SIST for User Profiling Technology Evaluation Campaign in SMP CUP 2017. UIR-SIST aims to complete three tasks, including keywords extraction from blogs, user interests labeling and user growth value prediction. To this end, we first extract keywords from a user’s blog, including the blog itself, blogs on the same topic and other blogs published by the same user. Then a unified neural network model is constructed based on a convolutional neural network (CNN) for user interests tagging. Finally, we adopt a stacking model for predicting user growth value. We eventually receive the sixth place with evaluation scores of 0.563, 0.378 and 0.751 on the three tasks, respectively.
Abstract: Hydrothermal condition is mismatched in arid and semi-arid regions, particularly in Central Asia (including Kazakhstan, Kyrgyzstan, Tajikistan, Uzbekistan, and Turkmenistan), resulting many environmental limitations. In this study, we projected hydrothermal condition in Central Asia based on bias-corrected multi-model ensembles (MMEs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6) under four Shared Socioeconomic Pathway and Representative Concentration Pathway (SSP-RCP) scenarios (SSP126 (SSP1-RCP2.6), SSP245 (SSP2-RCP4.5), SSP460 (SSP4-RCP6.0), and SSP585 (SSP5-RCP8.5)) during 2015–2100. The bias correction and spatial disaggregation, water-thermal product index, and sensitivity analysis were used in this study. The results showed that the hydrothermal condition is mismatched in the central and southern deserts, whereas the region of Pamir Mountains and Tianshan Mountains as well as the northern plains of Kazakhstan showed a matched hydrothermal condition. Compared with the historical period, the matched degree of hydrothermal condition improves during 2046–2075, but degenerates during 2015–2044 and 2076–2100. The change of hydrothermal condition is sensitive to precipitation in the northern regions and the maximum temperatures in the southern regions. The result suggests that the optimal scenario in Central Asia is SSP126 scenario, while SSP585 scenario brings further hydrothermal contradictions. This study provides scientific information for the development and sustainable utilization of hydrothermal resources in arid and semi-arid regions under climate change.
Abstract: Glaciers are highly sensitive to climate change and are undergoing significant changes in mid-latitudes. In this study, we analyzed the spatiotemporal changes of typical glaciers and their responses to climate change in the period of 1990–2015 in 4 different mountainous sub-regions in Xinjiang Uygur Autonomous Region of Northwest China: the Bogda Peak and Karlik Mountain sub-regions in the Tianshan Mountains; the Yinsugaiti Glacier sub-region in the Karakorum Mountains; and the Youyi Peak sub-region in the Altay Mountains. The standardized snow cover index (NDSI) and correlation analysis were used to reveal the glacier area changes in the 4 sub-regions from 1990 to 2015. Glacial areas in the Bogda Peak, Karlik Mountain, Yinsugaiti Glacier, and Youyi Peak sub-regions in the period of 1990–2015 decreased by 57.7, 369.1, 369.1, and 170.4 km², respectively. Analysis of glacier area center of gravity showed that quadrant changes of glacier areas in the 4 sub-regions moved towards the origin. Glacier area on the south aspect of the Karlik Mountain sub-region was larger than that on the north aspect, while glacier areas on the north aspect of the other 3 sub-regions were larger than those on the south aspect. Increased precipitation in the Karlik Mountain sub-region inhibited the retreat of glaciers to a certain extent. However, glacier area changes in the Bogda Peak and Youyi Peak sub-regions were not sensitive to the increased precipitation. On a seasonal time scale, glacier area changes in the Bogda Peak, Karlik Mountain, Yinsugaiti Glacier, and Youyi Peak sub-regions were mainly caused by accumulated temperature in the wet season; on an annual time scale, the correlation coefficient between glacier area and annual average temperature was –0.72 and passed the significance test at P<0.05 level in the Karlik Mountain sub-region. The findings of this study can provide a scientific basis for water resources management in the arid and semi-arid regions of Northwest China in the context of global warming.
Abstract: Precipitation is one of the most important indicators of climate data, but there are many errors in precipitation measurements due to the influence of climatic conditions, especially those of solid precipitation in alpine mountains and at high latitude areas. The measured amount of precipitation in those areas is frequently less than the actual amount of precipitation. To understand the impact of climatic conditions on precipitation measurements in the mountainous areas of Northwest China and the applicability of different gauges in alpine mountains, we established a cryospheric hydrometeorology observation (CHOICE) system in 2008 in the Qilian Mountains, which consists of six automated observation stations located between 2960 and 4800 m a.s.l. Total Rain weighing Sensor (TRwS) gauges tested in the World Meteorological Organization-Solid Precipitation Intercomparison Experiment (WMO-SPICE) were used at observation stations with the CHOICE system. To study the influence of climatic conditions on different types of precipitation measured by the TRwS gauges, we conducted an intercomparison experiment of precipitation at Hulu-1 station that was one of the stations in the CHOICE system. Moreover, we tested the application of transfer functions recommended by the WMO-SPICE at this station using the measurement data from a TRwS gauge from August 2016 to December 2020 and computed new coefficients for the same transfer functions that were more appropriate for the dataset from Hulu-1 station. The new coefficients were used to correct the precipitation measurements of other stations in the CHOICE system. Results showed that the new parameters fitted to the local dataset had better correction results than the original parameters. The environmental conditions of Hulu-1 station were very different from those of observation stations that provided datasets to create the transfer functions. Thus, root-mean-square error (RMSE) of solid and mixed precipitation corrected by the original parameters increased significantly by the averages of 0.135 (353%) and 0.072 mm (111%), respectively. RMSE values of liquid, solid and mixed precipitation measurements corrected by the new parameters decreased by 6%, 20% and 13%, respectively. In addition, the new parameters were suitable for correcting precipitation at other five stations in the CHOICE system. The relative precipitation (RP) increment of different types of precipitation increased with rising altitude. The average RP increment value of snowfall at six stations was the highest, reaching 7%, while that of rainfall was the lowest, covering 3%. Our results confirmed that the new parameters could be used to correct precipitation measurements of the CHOICE system.
Water shortage is one bottleneck that limits economic and social developments in arid and semi-arid areas. As the impacts of climate change and human disturbance intensify across time, uncertainties in both water resource supplies and demands increase in arid and semi-arid areas. Taking a typical arid region in China, Xinjiang Uygur Autonomous Region, as an example, water yield depth (WYD) and water utilization depth (WUD) from 2002 to 2018 were simulated using the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model and socioeconomic data. The supply-demand relationships of water resources were analyzed using the ecosystem service indices including water supply-demand difference (WSDD) and water supply rate (WSR). The internal factors in changes of WYD and WUD were explored using the controlled variable method. The results show that the supply- demand relationships of water resources in Xinjiang were in a slight deficit, but the deficit was alleviated due to increased precipitation and decreased WUD of irrigation. WYD generally experienced an increasing trend, and significant increase mainly occurred in the oasis areas surrounding both the Junggar Basin and Tarim Basin. WUD had a downward trend with a decline of 20.70%, especially in oasis areas. Water resources in most areas of Xinjiang were fully utilized and the utilization efficiency of water resources increased. The water yield module in the InVEST model was calibrated and validated using gauging station data in Xinjiang, and the result shows that the use of satellite-based water storage data helped to decrease the bias error of the InVEST model by 0.69×108 m3. This study analyzed water resource supplies and demands from a perspective of ecosystem services, which expanded the scope of the application of ecosystem services and increased the research perspective of water resource evaluation. The results could provide guidance for water resource management such as spatial allocation and structural optimization of water resources in arid and semi-arid areas.
Hyperspectral remote sensing technology is widely used to detect element contents because of its multiple bands, high resolution, and abundant information. Although researchers have paid considerable attention to selecting the optimal bandwidth for the hyperspectral inversion of metal element contents in rocks, the influence of bandwidth on the inversion accuracy are ignored. In this study, we collected 258 rock samples in and near the Kalatage polymetallic ore concentration area in the southwestern part of Hami City, Xinjiang Uygur Autonomous Region, China and measured the ground spectra of these samples. The original spectra were resampled with different bandwidths. A Partial Least Squares Regression (PLSR) model was used to invert Cu contents of rock samples and then the influence of different bandwidths on Cu content inversion accuracy was explored. According to the results, the PLSR model obtains the highest Cu content inversion accuracy at a bandwidth of 35 nm, with the model determination coefficient (R2) of 0.5907. The PLSR inversion accuracy is relatively unaffected by the bandwidth within 5–80 nm, but the accuracy decreases significantly at 85 nm bandwidth (R2=0.5473), and the accuracy gradually decreased at bandwidths beyond 85 nm. Hence, bandwidth has a certain impact on the inversion accuracy of Cu content in rocks using the PLSR model. This study provides an indicator argument and theoretical basis for the future design of hyperspectral sensors for rock geochemistry.
Long-term monitoring of the ecological environment changes is helpful for the protection of the ecological environment. Based on the ecological environment of the Sahel region in Africa, we established a remote sensing ecological index (RSEI) model for this region by combining dryness, moisture, greenness, and desertification indicators. Using the Moderate-resolution Imaging Spectroradiometer (MODIS) data in Google Earth Engine (GEE) platform, this study analyzed the ecological environment quality of the Sahel region during the period of 2001–2020. We used liner regression and fluctuation analysis methods to study the trend and fluctuation of RSEI, and utilized the stepwise regression approach to analyze the contribution of each indicator to the RSEI. Further, the correlation analysis was used to analyze the correlation between RSEI and precipitation, and Hurst index was applied to evaluate the change trend of RSEI in the future. The results show that RSEI of the Sahel region exhibited spatial heterogeneity. Specifically, it exhibited a decrease in gradient from south to north of the Sahel region. Moreover, RSEI in parts of the Sahel region presented non-zonal features. Different land-cover types demonstrated different RSEI values and changing trends. We found that RSEI and precipitation were positively correlated, suggesting that precipitation is the controlling factor of RSEI. The areas where RSEI values presented an increasing trend were slightly less than the areas where RSEI values presented a decreasing trend. In the Sahel region, the areas with the ecological environment characterized by continuous deterioration and continuous improvement accounted for 44.02% and 28.29% of the total study area, respectively, and the areas in which the ecological environment was changing from improvement to deterioration and from deterioration to improvement accounted for 12.42% and 15.26% of the whole area, respectively. In the face of the current ecological environment and future change trends of RSEI in the Sahel region, the research results provide a reference for the construction of the ''Green Great Wall'' (GGW) ecological environment project in Africa.
摘要：Moganopterus zhuiana L�et al. 2012 was erected as a member of the Boreopteridae, which was questioned by different researchers shortly after the publication. Although the new assignment to the Ctenochasmatidae is widely accepted by pterosaur researchers, some characteristics still require a detailed description. Here, the holotype of this taxon is restudied, and some ambiguous characteristics are re-identified. The diagnosis of this taxon has been revised as the following: a large ctenochasmatid pterosaur, which can be distinguished from other members of this clade by a single autapomorphy: an elongated rod-like parietal crest that extends posterodorsally, forming an angle of about 15�with the ventral margin of the skull. This taxon can be further distinguished from other ctenochasmatids on the basis of the following combination of characteristics: straight occlusal surfaces of the upper and low jaws; presence of a low premaxillary crest confined anterior to the nasoantorbital fenestra; rostrum about two thirds of the skull length; nasoantorbital fenestra occupying slightly more than 20% of the skull length; about 100 slender teeth; and a mid-cervical length/width ratio of about 7. The wingspan of M. zhuiana has been re-estimated according to a simple regression equation for wingspan versus skull length in ctenochasmatids. It confirms that M. zhuiana, although smaller than previous thought, is still the largest known ctenochasmatid. When comparing the sizes of ctenochasmatids in the Jurassic and Cretaceous, ctenochasmatids showed a rough tendency to increase their sizes.
摘要： Precise measurements of the cavity forward (Vf) and reflected signals (Vr) are essential for characterizing other key parameters such as the cavity detuning and forward power. In practice, it is challenging to measure Vf and Vr precisely because of crosstalk between the forward and reflected channels (e.g., coupling between the cavity reflected and forward signals in a directional coupler with limited directivity). For DESY, a method based on the cavity differential equation was proposed to precisely calibrate the actual Vf and Vr. In this study, we verified the validity and practicability of this approach for the Chinese ADS front-end demo superconducting linac (CAFe) facility at the Institute of Modern Physics and a compact energy recovery linac (cERL) test ma#2;chine at KEK. At the CAFe facility, we successfully calibrated the actual Vf signal using this method. The result demonstrated that the directivity of directional couplers might seriously affect the accuracy of Vf measurement. At the cERL facility, we calibrated the Lorentz force detuning (LFD) using the actual Vf. Our study confirmed that the precise calibration of Vf significantly improves the accuracy of the cavity LFD measurement.
摘要： Doped elements in alloys significantly impact their performance. Conventional methods usually sputter the surface material of the sample, or their performance is limited to the surface of alloys owing to their poor penetration ability. The X-ray K-edge subtraction (KES) method exhibits great potential for the nondestructive in situ detection of element contents in alloys. However, the signal of doped elements usually deteriorates because of the strong absorption of the principal component and scattering of crystal grains. This in turn prevents the extensive application of X-ray KES imaging to alloys. In this study, methods were developed to calibrate the linearity between the grayscale of the KES image and element content. The methods were aimed at the sensitive analysis of elements in alloys. Furthermore, experiments with phantoms and alloys demonstrated that, after elaborate calibration, X-ray KES imaging is capable of nondestructive and sensitive analysis of doped elements in alloys.
摘要： The advantages of once-through molten salt reactors include readily available fuel, low nuclear proliferation risk, and low technical difficulty. It is potentially the most easily commercialized fuel cycle mode for molten salt reactors. However, there are some problems in the parameter selection of once-through molten salt reactors, and the relevant burnup optimization work requires further analysis. This study examined a once-through graphite moderated molten salt reactor using enriched uranium and thorium. The fuel volume fraction (VF), initial heavy nuclei concentration (HN0), feeding uranium enrichment (EFU), volume of the reactor core, and fuel type were changed to obtain the optimal conditions for burnup. We found an optimal region for VF and HN0 in each scheme, and the location and size of the optimal region changed with the degree of EFU, core volume, and fuel type. The recommended core schemes provide a reference for the core design of a once-through molten salt reactor.
摘要：Information on the Fe content of bare rocks is needed for implementing geochemical processes and identifying mines. However, the influence of Fe content on the spectra of bare rocks has not been thoroughly analyzed in previous studies. The Saur Mountain region within the Hoboksar of the Russell Hill depression was selected as the study area. Specifically, we analyzed six hyperspectral indices related to rock Fe content based on laboratory measurements (Dataset I) and field measurements (Dataset II). In situ field measurements were acquired to verify the laboratory measurements. Fe content of the rock samples collected from different fresh and weathered rock surfaces were divided into six levels to reveal the spatial distributions of Fe content of these samples. In addition, we clearly displayed wavelengths with obvious characteristics by analyzing the spectra of these samples. The results of this work indicated that Fe content estimation models based on the fresh rock surface measurements in the laboratory can be applied to in situ field or satellite-based measurements of Fe content of the weathered rock surfaces. It is not the best way to use only the single wavelengths reflectance at all absorption wavelengths or the depth of these absorption features to estimate Fe content. Based on sample data analysis, the comparison with other indices revealed that the performance of the modified normalized difference index is the best indicator for estimating rock Fe content, with R2 values of 0.45 and 0.40 corresponding to datasets I and II, respectively. Hence, the modified normalized difference index (the wavelengths of 2220, 2290, and 2370 nm) identified in this study could contribute considerably to improve the identification accuracy of rock Fe content in the bare rock areas. The method proposed in this study can obviously provide an efficient solution for large-scale rock Fe content measurements in the field.
摘要：The Tarim River is the longest inland river in China and is considered as an important river to protect the oasis economy and environment of the Tarim Basin. However, excessive exploitation and over-utilization of natural resources, particularly water resources, have triggered a series of ecological and environmental problems, such as the reduction in the volume of water in the main river, deterioration of water quality, drying up of downstream rivers, degradation of vegetation, and land desertification. In this study, the land use/land cover change (LUCC) responses to ecological water conveyance in the lower reaches of the Tarim River were investigated using ENVI (Environment for Visualizing Images) and GIS (Geographic Information System) data analysis software for the period of 1990–2018. Multi-temporal remote sensing images and ecological water conveyance data from 1990 to 2018 were used. The results indicate that LUCC covered an area of 2644.34 km2 during this period, accounting for 15.79% of the total study area. From 1990 to 2018, wetland, farmland, forestland, and artificial surfaces increased by 533.42 km2 (216.77%), 446.68 km2 (123.66%), 284.55 km2 (5.67%), and 57.51 km2 (217.96%), respectively, whereas areas covered by grassland and other land use/land cover types, such as Gobi, bare soil, and deserts, decreased by 103.34 km2 (14.31%) and 1218.83 km2 (11.75%), respectively. Vegetation area decreased first and then increased, with the order of 2010<2000<1990<2018. LUCC in the overflow and stagnant areas in the lower reaches of the Tarim River was mainly characterized by fragmentation, irregularity, and complexity. By analyzing the LUCC responses to 19 rounds of ecological water conveyance in the lower reaches of the Tarim River from 2000 to the end of 2018, we proposed guidelines for the rational development and utilization of water and soil resources and formulation of strategies for the sustainable development of the lower reaches of the Tarim River. This study provides scientific guidance for optimal scheduling of water resources in the region.
摘要：With the increase of exploration depth, it is more and more difficult to find Au deposits. Due to the limitation of time and cost, traditional geological exploration methods are becoming increasingly difficult to be effectively applied. Thus, new methods and ideas are urgently needed. This study assessed the feasibility and effectiveness of using hyperspectral technology to prospect for hidden Au deposits. For this purpose, 48 plant (Seriphidium terrae-albae) and soil (aeolian gravel desert soil) samples were first collected along a sampling line that traverses an Au mineralization alteration zone (Aketasi mining region in an arid region of China) and were used to obtain soil Au contents by a chemical analysis method and the reflectance spectra of plants obtained with an Analytical Spectral Device (ASD) FieldSpec3 spectrometer. Then, the corresponding relationship between the soil Au content anomaly and concealed Au deposits was investigated. Additionally, the characteristic bands were selected from plant spectra using four different methods, namely, genetic algorithm (GA), stepwise regression analysis (STE), competitive adaptive reweighted sampling (CARS), and correlation coefficient method (CC), and were then input into the partial least squares (PLS) method to construct a model for estimating the soil Au content. Finally, the quantitative relationship between the soil Au content and the 15 different plant transformation spectra was established using the PLS method. The results were compared with those of a model based on the full spectrum. The results obtained in this study indicate that the location of concealed Au deposits can be predicted based on soil geochemical anomaly information, and it is feasible and effective to use the full plant spectrum and PLS method to estimate the Au content in the soil. The cross-validated coefficient of determination (R2) and the ratio of the performance to deviation (RPD) between the predicted value and the measured value reached the maximum of 0.8218 and 2.37, respectively, with a minimum value of 6.56 μg/kg for the root-mean-squared error (RMSE) in the full spectrum model. However, in the process of modeling, it is crucial to select the appropriate transformation spectrum as the input parameter for the PLS method. Compared with the GA, STE, and CC methods, CARS was the superior characteristic band screening method based on the accuracy and complexity of the model. When modeling with characteristic bands, the highest accuracy, R2 of 0.8016, RMSE of 7.07 μg/kg, and RPD of 2.20 were obtained when 56 characteristic bands were selected from the transformed spectra (1/lnR)' (where it represents the first derivative of the reciprocal of the logarithmic spectrum) of sampled plants using the CARS method and were input into the PLS method to construct an inversion model of the Au content in the soil. Thus, characteristic bands can replace the full spectrum when constructing a model for estimating the soil Au content. Finally, this study proposes a method of using plant spectra to find concealed Au deposits, which may have promising application prospects because of its simplicity and rapidity.
摘要：The purpose of the current study was to investigate the eco-physiological responses, in terms of growth and C:N:P stoichiometry of plants cultured from dimorphic seeds of a single-cell C4 annual Suaeda aralocaspica (Bunge) Freitag and Schütze under elevated CO2. A climatic chamber experiment was conducted to examine the effects of ambient (720 μg/L) and CO2-enriched (1440 μg/L) treatments on these responses in S. aralocaspica at vegetative and reproductive stages in 2012. Result showed that elevated CO2 significantly increased shoot dry weight, but decreased N:P ratio at both growth stages. Plants grown from dimorphic seeds did not exhibit significant differences in growth and C:N:P stoichiometric characteristics. The transition from vegetation to reproductive stage significantly increased shoot:root ratio, N and P contents, but decreased C:N, C:P and N:P ratios, and did not affect shoot dry weight. Moreover, our results indicate that the changes in N:P and C:N ratios between ambient and elevated CO2 are mainly caused by the decrease of N content under elevated CO2. These results provide an insight into nutritional metabolism of single-cell C4 plants under climate change.
摘要：Net primary productivity (NPP) of the vegetation in an oasis can reflect the productivity capacity of a plant community under natural environmental conditions. Owing to the extreme arid climate conditions and scarce precipitation in the arid oasis regions, groundwater plays a key role in restricting the development of the vegetation. The Qira Oasis is located on the southern margin of the Taklimakan Desert (Tarim Basin, China) that is one of the most vulnerable regions regarding vegetation growth and water scarcity in the world. Based on remote sensing images of the Qira Oasis and daily meteorological data measured by the ground stations during the period 2006–2019, this study analyzed the temporal and spatial patterns of NPP in the oasis as well as its relation with the variation of groundwater depth using a modified Carnegie Ames Stanford Approach (CASA) model. At the spatial scale, NPP of the vegetation decreased from the interior of the Qira Oasis to the margin; at the temporal scale, NPP of the vegetation in the oasis fluctuated significantly (ranging from 29.80 to 50.07 g C/(m2•month)) but generally showed an increasing trend, with the average increase rate of 0.07 g C/(m2•month). The regions with decreasing NPP occupied 64% of the total area of the oasis. During the study period, NPP of both farmland and grassland showed an increasing trend, while that of forest showed a decreasing trend. The depth of groundwater was deep in the south of the oasis and shallow in the north, showing a gradual increasing trend from south to north. Groundwater, as one of the key factors in the surface change and evolution of the arid oasis, determines the succession direction of the vegetation in the Qira Oasis. With the increase of groundwater depth, grassland coverage and vegetation NPP decreased. During the period 2008–2015, with the recovery of groundwater level, NPP values of all types of vegetation with different coverages increased. This study will provide a scientific basis for the rational utilization and sustainable management of groundwater resources in the oasis.