Responses of vegetation cover to hydro-climatic variations in Bosten Lake Watershed, NW China.

Amidst the backdrop of global climate change, it is imperative to comprehend the intricate connections among surface water, vegetation, and climatic shifts within watersheds, especially in fragile, arid ecosystems. However, these relationships across various timescales remain unclear. We employed the Ensemble Empirical Mode Decomposition (EEMD) method to analyze the multifaceted dynamics of surface water and vegetation in the Bosten Lake Watershed across multiple temporal scales. This analysis has shed light on how these elements interact with climate change, revealing significant insights. From March to October, approximately 14.9-16.8% of the areas with permanent water were susceptible to receding and drying up. Both the annual and monthly values of Bosten Lake's level and area exhibited a trend of initial decline followed by an increase, reaching their lowest point in 2013 (1,045.0 m and 906.6 km2, respectively). Approximately 7.7% of vegetated areas showed a significant increase in the Normalized Difference Vegetation Index (NDVI). NDVI volatility was observed in 23.4% of vegetated areas, primarily concentrated in the southern part of the study area and near Lake Bosten. Regarding the annual components (6 < T < 24 months), temperature, 3-month cumulative NDVI, and 3-month-leading precipitation exhibited the strongest correlation with changes in water level and surface area. For the interannual components (T≥ 24 months), NDVI, 3-month cumulative precipitation, and 3-month-leading temperature displayed the most robust correlation with alterations in water level and surface area. In both components, NDVI had a negative impact on Bosten Lake's water level and surface area, while temperature and precipitation exerted positive effects. Through comparative analysis, this study reveals the importance of temporal periodicity in developing adaptive strategies for achieving Sustainable Development Goals in dryland watersheds. This study introduces a robust methodology for dissecting trends within scale components of lake level and surface area and links these trends to climate variations and NDVI changes across different temporal scales. The inherent correlations uncovered in this research can serve as valuable guidance for future investigations into surface water dynamics in arid regions.

UAV hyperspectral analysis of secondary salinization in arid oasis cotton fields: effects of FOD feature selection and SOA-RF.

Secondary salinization is a crucial constraint on agricultural progress in arid regions. The specific mulching irrigation technique not only exacerbates secondary salinization but also complicates field-scale soil salinity monitoring. UAV hyperspectral remote sensing offers a monitoring method that is high-precision, high-efficiency, and short-cycle. In this study, UAV hyperspectral images were used to derive one-dimensional, textural, and three-dimensional feature variables using Competitive adaptive reweighted sampling (CARS), Gray-Level Co-occurrence Matrix (GLCM), Boruta Feature Selection (Boruta), and Brightness-Color-Index (BCI) with Fractional-order differentiation (FOD) processing. Additionally, three modeling strategies were developed (Strategy 1 involves constructing the model solely with the 20 single-band variable inputs screened by the CARS algorithm. In Strategy 2, 25 texture features augment Strategy 1, resulting in 45 feature variables for model construction. Strategy 3, building upon Strategy 2, incorporates six triple-band indices, totaling 51 variables used in the model's construction) and integrated with the Seagull Optimization Algorithm for Random Forest (SOA-RF) models to predict soil electrical conductivity (EC) and delineate spatial distribution. The results demonstrated that fractional order differentiation highlights spectral features in noisy spectra, and different orders of differentiation reveal different hidden information. The correlation between soil EC and spectra varies with the order. 1.9th order differentiation is proved to be the best order for constructing one-dimensional indices; although the addition of texture features slightly improves the accuracy of the model, the integration of the three-waveband indices significantly improves the accuracy of the estimation, with an R2 of 0.9476. In contrast to the conventional RF model, the SOA-RF algorithm optimizes its parameters thereby significantly improving the accuracy and model stability. The optimal soil salinity prediction model proposed in this study can accurately, non-invasively and rapidly identify excessive salt accumulation in drip irrigation under membrane. It is of great significance to improve the growing conditions of cotton, increase the cotton yield, and promote the sustainable development of Xinjiang's agricultural economy, and also provides a reference for the prevention and control of regional soil salinization.

Recent impacts of water management on dryland's salinization and degradation neutralization.

Reducing soil salinization of croplands with optimized irrigation and water management is essential to achieve land degradation neutralization (LDN). The effectiveness and sustainability of various irrigation and water management measures to reduce basin-scale salinization remain uncertain. Here we used remote sensing to estimate the soil salinity of arid croplands from 1984 to 2021. We then use Bayesian network analysis to compare the spatial-temporal response of salinity to water management, including various irrigation and drainage methods, in ten large arid river basins: Nile, Tigris-Euphrates, Indus, Tarim, Amu, Ili, Syr, Junggar, Colorado, and San Joaquin. In basins at more advanced phases of development, managers implemented drip and groundwater irrigation and thus effectively controlled salinity by lowering groundwater levels. For the remaining basins using conventional flood irrigation, economic development and policies are crucial for establishing a virtuous circle of "improving irrigation systems, reducing salinity, and increasing agricultural incomes" which is necessary to achieve LDN.

Laws Governing Nitrogen Loss and Its Numerical Simulation in the Sloping Farmland of the Miyun Reservoir.

Surface flow (SF) and subsurface flow (SSF) are important hydrological processes occurring on slopes, and are driven by two main factors: rainfall intensity and slope gradient. To explore nitrogen (N) migration and loss from sloping farmland in the Miyun Reservoir, the characteristics of total nitrogen (TN) migration and loss via SF and SSF under different rainfall intensities (30, 40, 50, 60, 70, and 80 mm/h) and slope gradients (5°, 10°, and 15°) were studied using indoor stimulated rainfall tests and mathematical models. Nitrogen loss via SF and SSF was found to increase exponentially and linearly with time, respectively, with SSF showing 14-78 times higher loss than SF. Under different rainfall intensities, SSF generally had larger TN loss loading than SF, thereby indicating that SSF was the main route for TN loss. However, the TN loss loading proportion via SF increasing from 14.03% to 35.82% with increasing rainfall intensity is noteworthy. Furthermore, compared with the measurement data, the precision evaluation index Nash-Suttcliffe efficient (NSE) and the determination coefficient (R2) of the effective mixing depth model in the numerical simulation of TN loss through SF in the sloping farmland in the Miyun Reservoir were 0.74 and 0.831, respectively, whereas those of the convection-dispersion equation for SSF were 0.81 and 0.811, respectively, thus indicating good simulation results. Therefore, this paper provides a reference for studying the mechanism of N migration and loss in sloping farmland in the Miyun Reservoir.

Fertilization altered co-occurrence patterns and microbial assembly process of ammonia-oxidizing microorganisms.

Ammonia-oxidizing archaea and bacteria (AOA and AOB, respectively) are important intermediate links in the nitrogen cycle. Apart from the AOA and AOB communities in soil, we further investigated co-occurrence patterns and microbial assembly processes subjected to inorganic and organic fertilizer treatments for over 35 years. The amoA copy numbers and AOA and AOB communities were found to be similar for the CK and organic fertilizer treatments. Inorganic fertilizers decreased the AOA gene copy numbers by 0.75-0.93-fold and increased the AOB gene copy numbers by 1.89-3.32-fold compared to those of the CK treatment. The inorganic fertilizer increased Nitrososphaera and Nitrosospira. The predominant bacteria in organic fertilizer was Nitrosomonadales. Furthermore, the inorganic fertilizer increased the complexity of the co-occurrence pattern of AOA and decreased the complexity pattern of AOB comparing with organic fertilizer. Different fertilizer had an insignificant effect on the microbial assembly process of AOA. However, great difference exists in the AOB community assembly process: deterministic process dominated in organic fertilizer treatment and stochastic processes dominated in inorganic fertilizer treatment, respectively. Redundancy analysis indicated that the soil pH, NO3-N, and available phosphorus contents were the main factors affecting the changes in the AOA and AOB communities. Overall, this findings expanded our knowledge concerning AOA and AOB, and ammonia-oxidizing microorganisms were more disturbed by inorganic fertilizers than organic fertilizers.

Prediction of Soil Water-Soluble Organic Matter by Continuous Use of Corn Biochar Using Three-Dimensional Fluorescence Spectra and Deep Learning.

The purpose is to study the soil's water-soluble organic matter and improve the utilization rate of the soil layer. This exploration is based on the theories of three-dimensional fluorescence spectroscopy, deep learning, and biochar. Chernozem in Harbin City, Heilongjiang Province, is taken as the research object. Three-dimensional fluorescence spectra and a deep learning model are used to analyze the content of water-soluble organic matter in the soil layer after continuous application of corn biochar for six years and to calculate different fluorescence indexes in the whole soil depth. Among them, the three-dimensional fluorescence spectrum theory provides the detection standard for the application effect detection of biochar, the deep learning theory provides the technical support for this exploration, and the biochar theory provides the specific research direction. The results show that the application of corn biochar for six consecutive years significantly reduces the average content of water-soluble organic matter in different soil layers. Among them, the highest average content of soil water-soluble organic matter is "nitrogen, potassium, phosphorous" (NPK) and the lowest is "boron, carbon" (BC). Comparing the soil with BC alone, in the topsoil, the second section (330-380 nm/200-250 nm) with BC + NPK increases by 13.3%, the third section (380-550 nm/220-250 nm) increases by 8.4%, and the fourth section (250-380 nm/250-600 nm) increases by 50.1%. The combination of nitrogen (N) + BC has a positive effect of 20.7%, 12.2%, and 28.4% on sections I, II, and IV, respectively. In addition, in the topsoil, the combination of NPK + BC significantly increases the content of acid-like substances compared with the application of BC alone. In the black soil, with or without fertilizer NPK, there is no significant difference in the level of fulvic acid-like components. The prediction of soil water-soluble organic matter after continuous application of corn biochar based on three-dimensional fluorescence spectra and deep learning is carried out, which has reference significance for the rapid identification and early prediction of subsequent soil activity.

Effects of Biochar on the Fluorescence Spectra of Water-Soluble Organic Matter in Black Soil Profile after Application for Six Years.

At present, extracting water-soluble organic matter (WSOM) from agricultural organic waste is primarily used to evaluate soil organic matter content in farmland. However, only a few studies have focused on its vertical behavior in the soil profile. This study aims to clarify the three-dimensional fluorescence spectrum characteristics of the WSOM samples in 0-60 cm black soil profile before and after different chemical fertilizer treatments after six years of fertilization. Fluorescence spectroscopy combined with fluorescence and ultraviolet-visible (UV-Vis) spectroscopies are used to divide four different fertilization types: no fertilization (T0), nitrogen phosphorus potassium (NPK) (T1), biochar (T2), biochar + NPK (T3), and biochar + N (T4) in a typical black soil area. The vertical characteristics of WSOC are also analyzed. The results showed that after six years of nitrogen application, T2 had a significant effect on the fluorescence intensity of Zone II (decreasing by 9.6% in the 0-20 cm soil layer) and Zone V (increasing by 8.5% in the 0-20 cm soil layer). The fluorescent components identified in each treatment group include ultraviolet radiation A humic acid-like substances (C1), ultraviolet radiation C humic acid-like substances (C2), and tryptophan-like substance (C3). As compared with the land with T1, the content of C2 in the 20-60 cm soil layer with T2 was lower, while that of C2 in the surface and subsoil with T3 was higher. In addiiton, there were no significant differences in the contents of C1, C2, and C3 by comparing the soils applied with T3 and T4, respectively. The composition of soil WSOM was found to be significantly influenced by the addition of a mixture of biochar and chemical fertilizers. The addition of biochar alone exerted a positive effect on the humification process in the surface soil (0-10 cm). NPK treatment could stimulate biological activity by increasing biological index values in deeper soil layers (40-50 cm). Nitrogen is the sovereign factor that improves the synergism effect of chemical fertilizer and biochar during the humification process. According to the UV-Vis spectrum and optical index, soil WSOM originates from land and microorganisms. This study reveals the dynamics of WSOC in the 0-60 cm soil layer and the biogeochemical effect of BC fertilizer treatment on the agricultural soil ecosystem.

Effects of the Rainfall Intensity and Slope Gradient on Soil Erosion and Nitrogen Loss on the Sloping Fields of Miyun Reservoir.

Environmental loss is primarily caused by soil, water, and nutrient loss, and runoff is associated with nutrient transport and sediment loss. Most existing studies have focused on one influencing factor, namely slope gradient or rainfall intensity, for slope erosion and nutrient loss, but the joint effects of the two factors have rarely been researched. In this context, the impact of slope gradients (0°, 5°, 10°, and 15°) and rainfall intensities (30, 40, 50, 60, 70, and 80 mm/h) on soil erosion and nutrient loss on the sloping fields of Miyun Reservoir were explored using the indoor artificial rainfall simulation testing system. Based on the results of the study, the variation of runoff coefficient with slope gradient was not noticeable for rainfall intensities <40 mm/h; however, for rainfall intensities >40 mm/h, the increased range of runoff coefficient doubled, and the increase was the fastest under 0° among the four slope gradients. The slope surface runoff depth and runoff rate showed positive correlations with the rainfall intensity (r = 0.875, p < 0.01) and a negative correlation with the slope gradient. In addition, the cumulative sediment yield was positively related to the slope gradient and rainfall intensity (r > 0.464, p < 0.05). Moreover, the slope surface runoff-associated and sediment-associated loss rates of total nitrogen (TN) rose as the rainfall intensity or slope gradient increased, and significant linear positive correlations were found between the runoff-associated TN loss rate (NLr) and the runoff intensity and between the sediment-associated NLr and the erosion intensity. In addition, there were positive linear correlations between slope runoff-associated or sediment-associated TN loss volumes and rainfall intensity, surface runoff, and sediment loss volumes, which were highly remarkable. The slope gradient had a significant positive correlation with the slope surface runoff-associated TN loss at 0.05 (r = 0.452) and a significant positive correlation with the sediment-associated TN loss at the level of 0.01 (r = 0.591). The rainfall intensity exhibited extremely positive correlations with the slope surface runoff-associated and sediment-associated TN loss at 0.01 (r = 0.717 and 0.629) Slope gradients have less effect on nitrogen loss on sloped fields than rainfall intensity, mainly because rainfall intensity affects runoff depth. Based on the findings of this study, Miyun Reservoir may be able to improve nitrogen loss prevention and control.

Identification of dust aerosols, their sources, and the effect of soil moisture in Central Asia.

Dust aerosols in Central Asia are an important factor in global climate change and attribution studies. Identifying the source of dust in Central Asia is crucial for understanding the ecological environment and climate, locally and globally. In this study, daily dust aerosol data were calculated and extracted for Central Asia from 2003 to 2018. The multi-year trends of dust aerosols were analyzed, dust sources were identified, the characteristics of dust aerosols in dust sources were analyzed, and the influence of soil moisture on sand initiation was explored. The results show that there are distinct seasonal characteristics in the spatial distribution of dust aerosols in Central Asia. The proportion of the area in the zone of high dust aerosols was the greatest in spring. Nearly half of the dust aerosol areas exhibited an increasing trend. A high incidence of dust sources was mainly distributed in the southern Xinjiang region. The trend of change in the dust area first increased and then decreased. With the increase in soil moisture under different wind speed conditions, the aerosols from dust sources all showed an exponentially decreasing trend, and the increase in soil moisture led to an increase in the wind speed threshold of sand initiation. This study provides basic data support for the study of dust aerosols, identifies dust sources, and provides a basis for studying the radiative forcing and climate effects of dust aerosols in Central Asia.

Changes in fungal community during different phases in conventional and bioreactor composting systems according to metatranscriptomics analysis.

We determined the changes that occurred in fungal community structures and their functions in conventional and bioreactor composting systems. The Illumina MiSeq platform was employed to sequence cDNA by reverse transcription to conduct metatranscriptomics analysis of RNA, and the FUNGuild tool was applied. The α-diversity of fungi in the bioreactor composter increased throughout composting, especially in the initial three phases, but decreased in the conventional composting system. The three dominant phyla in the bioreactor system were Ascomycota (30.27%-68.50%), Mortierellomycota (3.81%-39.51%), and Basidiomycota (9.17%-30.86%). Ascomycota (76.96%-97.18%) was the main phylum in the conventional composting system. Mortierella, Guehomyces, Plectosphaerella, Chaetomium, Millerozyma, and Coprinopsis were the main genera in the bioreactor composter. In the same phase, significant differences in the fungal functions were found between the two composting methods. Available phosphorus was the main factor that affected the community structures and functions of fungi in the bioreactor composter.

Positive Effects of Organic Substitution in Reduced-Fertilizer Regimes on Bacterial Diversity and N-Cycling Functionality in Greenhouse Ecosystem.

Conventional fertilization in the greenhouses of North China used excessive amounts of chemical and organic fertilizer, resulting in soil degradation and severe agricultural non-point source pollution. A nine-year study was conducted on a loamy clay soil in Shijiazhuang, Hebei province, to investigate the effects of reduced-fertilizer input regimes on soil property, bacterial diversity, nitrogen (N) cycling and their interactions. There were four treatments, including high organic + chemical fertilizer application rate and three reduced-fertilizer treatments with swine manure, maize straw or no substitution of 50% chemical N. Treatments with reduced-fertilizer input prevented soil salinization and acidification as in local conventional fertilization after being treated for nine years. In comparison to chemical fertilizer only, swine manure or maize straw substitution maintained higher nutrient availability and soil organic C contents. Fertilizer input reduction significantly increased bacterial richness and shifted bacterial community after nine years, with decisive factors of EC, Olsen P and C/N ratio of applied fertilizer. Soil chemical characteristics (EC, pH and nutrients), aggregation and C/N ratio of applied fertilizer selected certain bacterial groups, as well as N-cycling functions. Reduced-fertilizer input decreased the potential nitrification and denitrification functioning of bacterial community, but only in organic substitution treatments. The results of this study suggested that fertilizer input reduction combined with organic C input has potential in reducing non-point source pollution and increasing N-use efficiency in greenhouse vegetable production in North China.

Quantifying the effects of human activities and climate variability on runoff changes using variable infiltration capacity model.

Detecting and assessing changes in the hydrologic cycle and its response to a changing environment is essential for maintaining regional ecological security and restoring degraded ecosystems. There is no clear scientific evidence on the effects of human activities and climate variability on runoff and its components in typical arid areas. Therefore, in this study, a heuristic segmentation algorithm, a variable infiltration capacity model (VIC), and remote sensing data to quantify the effects of human activities and climate variability on runoff in the catchment of Lake Ebinur, Xinjiang, China. The results found: (1) The heuristic segmentation algorithm divided the study period into reference period (1964-1985) and two impact periods: I (1986-2000) and II (2001-2017). (2) Cropland and forest land showed an increasing trend, with grassland and barren land accounting for most of the increase. At the same time, the leaf area index (LAI) increased by 0.002 per year during the growing season. (3) Compared with the reference period, runoff depth decreased by 108.80 mm in impact period I due to human activities, but increased by 110.5 mm due to climate variability, resulting in an overall increase in runoff depth of 1.72 mm. Runoff depth increased by 11.10 mm in the impact period II compared to the reference period, with climate variability resulting in an increase of 154.40 mm, but human activities resulted in a decrease of 143.30 mm. Our results shed light on decision-making related to water stress in changing circumstances in arid regions.

Drivers of PM2.5 in the urban agglomeration on the northern slope of the Tianshan Mountains, China.

Fine particulate matter (PM2.5) is a major source of air pollution in China. Although there have been many studies of the drivers of PM2.5 pollution in the megacities clustered in eastern China, the behavior of PM2.5 in the northwestern urban agglomeration is not well understood. This study used near-surface observation data for 2015-2019 obtained from the national air environmental monitoring network to examine variation in PM2.5 in the urban agglomeration on the northern slopes of the Tianshan Mountains (UANSTM). Two-factor interaction provided new insights into the dominant factors of PM2.5 in the study region. The annual average PM2.5 concentrations over the study period was 54.3 µg/m3, with an exceedance rate of 23.3%. Wavelet analysis showed two dominant cycles of 320-370 d and 150-200 d with high pollution events occurring in winter. The generalized additive model (GAM) contained linear functions of pressure, non-linear functions of SO2, NO2, relative humidity, sunshine duration and temperature. The two most primary variables, NO2 and SO2, represent 20.65% and 19.54% of the total deviance explained, respectively, while the meteorological factors account for 36.1% of the total deviance explained. In addition, the interaction between NO2 and other factors had the strongest effect on PM2.5. The deviance explained in the two factor interaction model (88.5%) was higher than that in the single factor model (78.4%). Our study emphasized that interaction between meteorological factors and pollutant emissions enhanced the impact on PM2.5 compared with individual factors, which can provide a scientific basis for developing effective emission reduction strategies in UANSTM.

Multidimensional soil salinity data mining and evaluation from different satellites.

Soil salinization, a common land degradation mode, restricts the ecological environment and is a global issue due to climate change. Accurately, quickly and effectively monitoring soil salinity is critical for governmental institutions that develop hazard prevention and mitigation strategies. Remote sensing (RS) technology provides a viable alternative to traditional field work due to its large area coverage, abundant spectral information and nearly constant observations. Key issues in RS-based soil salinity monitoring include the lack of both data-mining techniques for obtaining spectral band information and comprehensive considerations of synergies among different spectra. The main objective of this study was to provide in-depth explorations of data mining and integration algorithms from different satellites to multidimensionally evaluate soil salinity models. The Ebinur Lake Wetland Reserve (Xinjiang Province, China) was selected as a case study. First, ground-measured visible and near infrared (VIS-NIR) spectral data were combined with the RS band to simulate Landsat 8 (L8) and Sentinel 2 (S2) and 3 (S3) data. Second, one-dimensional RS bands and 15 soil salinity and vegetation indices were selected, and 15 spectral data transformations (reciprocal, differential, absorbance, etc.) were obtained. Two- and three-dimensional spectral indices were constructed, and the response relationships between different spectral indices and soil electrical conductivity (EC) were comprehensively explored. Finally, an integrated multidimensional algorithm was used to estimate soil salinity in high-performance models for the three satellites. The results showed that all data-mining-based model combinations performed well for all satellites (R2 > 0.80). However, with multidimensional model combinations, S3 presented the highest predictive capability (R2 = 0.89, RMSE = 2.57 mS·cm-1, RPD = 2.05), followed by S2 (R2 = 0.86, RMSE = 2.71 mS·cm-1, RPD = 1.90) and L8 (R2 = 0.85, RMSE = 2.84 mS·cm-1, RPD = 1.87). Therefore, data mining with integration algorithms in model combinations performs significantly better than previous models and could be considered a promising method for obtaining improved results from soil salinity susceptibility models in similar cases.

Exploring the potential of UAV hyperspectral image for estimating soil salinity: Effects of optimal band combination algorithm and random forest.

Hyperspectral remote sensing by unmanned aerial vehicle (UAV) is an important technical tool for rapid, accurate, and real-time monitoring of soil salinity in arid zone agroecosystems. However, the key to effective soil salinity (electrical conductivity, EC) prediction by UAV visible and near-infrared (Vis-NIR) spectroscopy depends on the selection of effective features selection techniques and robust prediction characteristics algorithms. Therefore, in this study, two advanced feature selection methods and two commonly used modeling methods were applied to predict and characterize the spatial patterns of soil salinity (EC). The aim of this study was to explore the predictive performance of different feature band selection methods and to identify a robust soil salinity mapping strategy. The results demonstrated that standard normal variate (SNV) pre-processing broadened the absorption characteristics of the spectrum. Compared with competitive adaptive reweighted sampling (CARS), the optimal band combination algorithm (OBCA) strengthened the correlation with soil salinity and had a higher variable importance in the modeling. Random forest (RF) was more stable in mapping the spatial pattern of surface soil salinity compared to the partial least squares regression model (PLSR). Our results confirm the effectiveness of OBCA and RF in the developing UAV remote sensing models for surface soil salinity estimation and mapping.

Machine learning driven by environmental covariates to estimate high-resolution PM2.5 in data-poor regions.

PM2.5, which refers to fine particles with an equivalent aerodynamic diameter of less than or equal to 2.5 µm, can not only affect air quality but also endanger public health. Nevertheless, the spatial distribution of PM2.5 is not well understood in data-poor regions where monitoring stations are scarce. Therefore, we constructed a random forest (RF) model and a bagging algorithm model based on ground-monitored PM2.5 data, aerosol optical depth (AOD) and meteorological data, and auxiliary geographical variables to accurately estimate the spatial distribution of PM2.5 concentrations in Xinjiang during 2015-2020 at a resolution of 1 km. Through 10-fold cross-validation (CV), the RF model and bagging algorithm model were verified and compared. The results showed the following: (1) The RF model achieved better model performance and thus can be used to estimate the PM2.5 concentration at a relatively high resolution. (2) The PM2.5 concentrations were high in southern Xinjiang and low in northern Xinjiang. The high values were concentrated mainly in the Tarim Basin, while most areas of northern Xinjiang maintained low PM2.5 levels year-round. (3) The PM2.5 values in Xinjiang showed significant seasonality, with the seasonally averaged concentrations decreasing as follows: winter (71.95 µg m-3) > spring (64.76 µg m-3) > autumn (46.01 µg m-3) > summer (43.40 µg m-3). Our model provides a way to monitor air quality in data-scarce places, thereby advancing efforts to achieve sustainable development in the future.

Estimation of Soil Organic Carbon Content in the Ebinur Lake Wetland, Xinjiang, China, Based on Multisource Remote Sensing Data and Ensemble Learning Algorithms.

Soil organic carbon (SOC), as the largest carbon pool on the land surface, plays an important role in soil quality, ecological security and the global carbon cycle. Multisource remote sensing data-driven modeling strategies are not well understood for accurately mapping soil organic carbon. Here, we hypothesized that the Sentinel-2 Multispectral Sensor Instrument (MSI) data-driven modeling strategy produced superior outcomes compared to modeling based on Landsat 8 Operational Land Imager (OLI) data due to the finer spatial and spectral resolutions of the Sentinel-2A MSI data. To test this hypothesis, the Ebinur Lake wetland in Xinjiang was selected as the study area. In this study, SOC estimation was carried out using Sentinel-2A and Landsat 8 data, combining climatic variables, topographic factors, index variables and Sentinel-1A data to construct a common variable model for Sentinel-2A data and Landsat 8 data, and a full variable model for Sentinel-2A data, respectively. We utilized ensemble learning algorithms to assess the prediction performance of modeling strategies, including random forest (RF), gradient boosted decision tree (GBDT) and extreme gradient boosting (XGBoost) algorithms. The results show that: (1) The Sentinel-2A model outperformed the Landsat 8 model in the prediction of SOC contents, and the Sentinel-2A full variable model under the XGBoost algorithm achieved the best results R2 = 0.804, RMSE = 1.771, RPIQ = 2.687). (2) The full variable model of Sentinel-2A with the addition of the red-edge band and red-edge index improved R2 by 6% and 3.2% over the common variable Landsat 8 and Sentinel-2A models, respectively. (3) In the SOC mapping of the Ebinur Lake wetland, the areas with higher SOC content were mainly concentrated in the oasis, while the mountainous and lakeside areas had lower SOC contents. Our results provide a program to monitor the sustainability of terrestrial ecosystems through a satellite perspective.

Estimation of Soil Organic Matter in Arid Zones with Coupled Environmental Variables and Spectral Features.

The soil organic matter (SOM) content is a key factor affecting the function and health of soil ecosystems. For measurements of land reclamation and soil fertility, SOM monitoring using visible and near-infrared spectroscopy (Vis-NIR) is one approach to quantifying soil quality, and Vis-NIR is important for monitoring the SOM content in a broad and nondestructive manner. To investigate the influence of environmental factors and Vis-NIR spectroscopy in estimating SOM, 249 soil samples were collected from the Werigan-Kuqa oasis in Xinjiang, China, and their spectral reflectance, SOM content and soil salinity were measured. To classify and improve the prediction accuracy, we also take into account the soil salinity content as a variable indicator. Relevant environmental variables were extracted using remote sensing datasets (land-use/land-cover (LULC), digital elevation model (DEM), World Reference Base for Soil Resources (WRB), and soil texture). On the basis of Savitzky-Golay (S-G) smoothing and first derivative (FD) preprocessing of the original spectrum, three clusters were obtained by K-means clustering through the use of Vis-NIR and used as spectral classification variables. Using Vis-NIR as Model 1, Vis-NIR combined with spectral classification as Model 2, environmental variables as Model 3, and the combination of all the above variables (Vis-NIR, spectral classification, environmental variables, and soil salinity) as Model 4, a SOM content estimation model was constructed using partial least squares regression (PLSR). Using the 249 soil samples, the modeling set contained 166 samples and the validation set contained 83 samples. The results showed that Model 2 (validation r2 = 0.78) was better than Model 1 (validation r2 = 0.76). The prediction accuracy for Model 4 (validation r2 = 0.85) was better than Model 2 (validation r2 = 0.78). Among these, Model 3 was the worst (validation r2 = 0.39). Therefore, the combination of environmental variables with Vis-NIR spectroscopy to estimate SOM content is an important method and has important implications for improving the accuracy of SOM predictions in arid regions.

Attribution of changes in the trend and temporal non-uniformity of extreme precipitation events in Central Asia.

Extreme precipitation events exhibit an increasing trend for both the frequency and magnitude on global and regional scales and it has already proven the impact of man-made global warming on the extreme precipitation amplification. Based on the observed datasets and global climate model (GCM) output, this study has evaluated the impact from anthropogenic forcing on the trend and temporal non-uniformity (i.e. increase in unevenness or disparity) of the precipitation amounts (PRCPTOT), extremes (R95p and RX5day) and intensity (SDII) in Central Asia (CA) from 1961 to 2005. Results indicate that radiative forcing changes, mainly driven by human activities, have significantly augmented the extreme precipitation indices in CA. The median trend with the influence of anthropogenic activities for the PRCPTOT, SDII, R95p and RX5day amounted to 2.19 mm/decade, 0.019 mm/decade, 1.39 mm/decade and 0.21 mm/decade during the study period, respectively. A statistically insignificant decrease in non-uniformity was noticed for the PRCPTOT, SDII and RX5day in Central CA (CCA) and Western CA (WCA), while Eastern CA (ECA) was the only region with a statistically significant increase in non-uniformity of the PRCPTOT, SDII, R95p and RX5day by 4.22%, 3.98%, 3.73% and 3.97%, respectively from 1961 to 2005 due to anthropogenic forcing. These results reflect the difference in various regions regarding the impact of anthropogenic forcing on the non-uniformity of extreme precipitation events in CA, which might help to fully understand the role of anthropogenic forcing in the changes of the precipitation extremes in CA and contribute to the development of water resource management strategies.

Multi-U-Net: Residual Module under Multisensory Field and Attention Mechanism Based Optimized U-Net for VHR Image Semantic Segmentation.

As the acquisition of very high resolution (VHR) images becomes easier, the complex characteristics of VHR images pose new challenges to traditional machine learning semantic segmentation methods. As an excellent convolutional neural network (CNN) structure, U-Net does not require manual intervention, and its high-precision features are widely used in image interpretation. However, as an end-to-end fully convolutional network, U-Net has not explored enough information from the full scale, and there is still room for improvement. In this study, we constructed an effective network module: residual module under a multisensory field (RMMF) to extract multiscale features of target and an attention mechanism to optimize feature information. RMMF uses parallel convolutional layers to learn features of different scales in the network and adds shortcut connections between stacked layers to construct residual blocks, combining low-level detailed information with high-level semantic information. RMMF is universal and extensible. The convolutional layer in the U-Net network is replaced with RMMF to improve the network structure. Additionally, the multiscale convolutional network was tested using RMMF on the Gaofen-2 data set and Potsdam data sets. Experiments show that compared to other technologies, this method has better performance in airborne and spaceborne images.