•The established model could reflect the impact of non-point source pollution on water quality.•The hybrid model performed very well in the water quality prediction.•The hybrid model improved the ...accuracy of extreme water quality prediction.
Non-point source (NPS) pollution is an important factor affecting the quality of water environment. In recent years, a large number of online water quality monitoring stations have been used to obtain continuous time series water quality monitoring data. These data provide the necessary basis for the application of deep learning methods in water quality prediction. However, the prediction accuracy of traditional deep learning methods is low, especially in predicting the water quality with NPS pollution. Aiming to address this limitation, a novel deep learning model named SOD-VGG-LSTM with the simulation-observation difference (SOD) modular based on physical process, the visual geometry (VGG) modular reflecting spatial characteristics, and the long short-term memory (LSTM) modular based on deep learning method was developed to improve the accuracy of the water quality prediction with NPS pollution. The established model can overcome the problem that mechanism models can not predict the changes of water quality on the hourly or minute time scale. The model was applied in Lijiang River watershed. Experimental results indicated that the proposed model had the highest accuracy in the extreme value prediction compared with the mechanism model and LSTM model. The maximum relative errors between the predicted and observed results for DO, CODMn, NH3-N, and TP were 8.47%, 19.76%, 24.1%, and 35.4%, respectively. The model evaluation demonstrated thatthe established SOD-VGG-LSTM model achieved superior computational performance compared to Auto Regression Integreate Moving Average model (ARIMA), Support Vector Regression model (SVR), and Recurrent Neural Network model (RNN). The evaluation results showed that SOD-VGG-LSTM achieved 3.2–39.3% higher R2 than ARIMA, SVR and RNN. The proposed model can provide a new method for water quality prediction with NPS pollution.
The spatial distribution of mine water quality and geochemical controls must be investigated for water safety and ecosystem protection in Shaanxi-Inner Mongolian Coal Mine Base (SICMB). Based on 122 ...mine water samples collected from 14 mining areas, self-organizing maps (SOM) combining with principal component analysis (PCA) derived that the mine water samples were classified into seven clusters. Clusters 1 and 3 (C1 and C3) samples were dominant by HCO3-Ca and mixed types, which were distributed in the recharge area of the middle SICMB. In this area, the active groundwater circulation contributed to the good water quality. Cluster 2 (C2) samples were characterized by HCO3-Na type, mainly distributed in the discharge area of the middle SICMB. These samples were threatened by heavy fluorine contamination and high residual sodium carbonate (RSC) because of slow groundwater flow in this area. Clusters 4 and 5 (C4 and C5) samples, distributed in the northeast and middle SICMB, were characterized by high Cl− concentration and light fluorine contamination. They were influenced by anthropogenic input through faults or underground mining. In contrast, Clusters 6 and 7 (C6 and C7) samples with high salinity and sulfate were distributed in the southwest SICMB. The deep groundwater circulation enhanced water-rock interaction and contributed to poor water quality. These findings are beneficial to the management of mine water resources in the SICMB and provide an insight to investigate the mine water quality in large spatial scale.
Display omitted
•Seven clusters are identified by hydrochemical types and pollution degree.•Water-rock interaction, human inputs, fluoride pollution and RSC hazard controlled mine water quality.•Spatial patterns of mine water quality in the SICMB were identified.•SOM as well as PCA methods were used in mine water quality assessment.
In the digital era, using social media big data to capture the true views and psychological trends shown by the public regarding waste reduction could considerably improve the formulation of targeted ...waste reduction policies and guide residents to participate in environmental governance from the source side. This study used big data mining technology to trawl 617,771 pieces of waste reduction text from a typical social media site (Sina Microblog). A machine learning algorithm model was used to identify the psychological and cognitive focus of the public and their preferences based on large-scale text data. The temporal and spatial differences in public attention trends, hot topic trends, and sentiment trends were also investigated. The results showed that the public attention level was related to the release of policies by government and that public attention in the southeast coastal areas was higher than that in the northwest inland areas. Moreover, waste reduction had a “working attribute” because the public paid more attention to waste reduction during working hours (i.e., 9:00–12:00 and 15:00–18:00) than during leisure hours. In terms of individual heterogeneity, males were initiators of the topic, whereas females were followers. In particular, participation by young people in waste reduction discussions was higher than for other groups. The topic analysis showed that public attention followed a cooperative construction pattern that had multiple entities, including the individual, community, and government. Overall, the public sentiment score towards waste reduction increased year by year during the study period, with positive sentiment posts accounting for over 70% of the total number of blog posts, and that the vast majority of residents had a positive attitude towards waste reduction. This study expanded current research knowledge by exploring the public attitude response to waste reduction from a social media perspective. The study will help the government to effectively intervene in public behavior tendencies toward waste reduction from the psychological perspective and provided important implications about how the government can enhance its use of social media to effectively guide public opinion and improve policies.
Long-time-series, high-resolution datasets of the column-averaged dry-air mole fraction of carbon dioxide (XCO2) have great practical importance for mitigating the greenhouse effect, assessing carbon ...emissions and implementing a low-carbon cycle. However, the mainstream XCO2 datasets obtained from satellite observations have coarse spatial resolutions and are inadequate for supporting research applications with different precision requirements. Here, we developed a new spatial machine learning model by fusing spatial information with CatBoost, called SCatBoost, to fill the above gap based on existing global land-mapped 1° XCO2 data (GLM-XCO2). The 1-km-spatial-resolution dataset containing XCO2 values in China from 2012 to 2019 reconstructed by SCatBoost has stronger and more stable predictive power (confirmed with a cross-validation (R2 = 0.88 and RSME = 0.20 ppm)) than other traditional models. According to the estimated dataset, the overall national XCO2 showed an increasing trend, with the annual mean concentration rising from 392.65 ppm to 410.36 ppm. In addition, the spatial distribution of XCO2 concentrations in China reflects significantly higher concentrations in the eastern coastal areas than in the western inland areas. The contributions of this study can be summarized as follows: (1) It proposes SCatBoost, integrating the advantages of machine learning methods and spatial characteristics with a high prediction accuracy; (2) It presents a dataset of fine-scale and high resolution XCO2 over China from 2012 to 2019 by the model of SCatBoost; (3) Based on the generated data, we identify the spatiotemporal trends of XCO2 in the scale of nation and city agglomeration. These long-term and high resolution XCO2 data help understand the spatiotemporal variations in XCO2, thereby improving policy decisions and planning about carbon reduction.
•We propose SCatBoost as a new model to reconstruct XCO2 with 1 km resolution.•Validation indicates high accuracy of the novel reconstruction model.•The spatiotemporal distributions of XCO2 in China from 2012 to 2019 is studied.
Various existing anomaly detection (AD) technologies focus on the background feature extraction and suppression, which serves as a crucial step to extrude anomalies from the hyperspectral imagery ...(HSI). In this article, motivated by the advantages of the joint sparse representation (JSR) model for adaptive background base selection, a robust background feature extraction method through homogeneous region-based JSR is proposed and used for AD. By segmenting the scene from the spatial domain through an eight-connected region division operation based on the clustering result, a series of nonoverlapping homogeneous regions each sharing a common sparsity pattern are obtained. After discarding small regions, JSR is performed on each region with the dictionary constituted by the overall spectral items in the corresponding cluster. By calculating the usage frequency of dictionary atoms, the most representative background bases describing each background cluster are adaptively selected and then combined into the global background bases. In addition, considering the interference of noise on detection accuracy, an energy deviation-based noise estimation strategy is presented by analyzing the residual obtained from JSR. Finally, the anomaly response of each pixel is measured by comparing its projection energy obtained from the background orthogonal subspace projection with the noise energy in its corresponding region. The proposed method overcomes the shortcomings of traditional neighborhood-based JSR in the common sparsity pattern and anomaly proportion. The spatial characteristics of HSI are fully explored. Furthermore, the interference of noise on detection accuracy is eliminated. Experiments on four HSI data sets demonstrate the superiority of the proposed method.
Soil organic carbon (SOC) plays an important role in controlling the function and quality of soil and offsetting the emissions of greenhouse gases. However, the dynamic monitoring and estimation of ...SOC are very difficult due to the complex traditional methods and the changing environmental variables. For instance, the calculation of SOC stock requires measurement of a few relevant soil attributes, such as soil organic matter (SOM), soil bulk density (SBD), soil moisture, and soil weight, in the laboratory. Many studies have suggested that visible and near-infrared (vis–NIR) spectra are a practical and affordable alternative to accurately and rapidly estimate the soil attributes relevant to SOC stock, and airborne hyperspectral images can be used as a valuable data source to perform digital soil mapping with high spatial resolution. The objective of this research was to check the predicted capability of SOC stock through laboratory and airborne vis–NIR spectral data. A total of 50 topsoil samples (0–15 cm) from the farmland of Iowa City were used as the study object. The partial least squares regression model was used to predict SOC stock through the direct and indirect methods. In the direct method, the SOC stock was predicted using the spectral data. In the indirect method, the relevant soil properties (SOM and SBD) of the SOC stock were predicted using the spectral data, and then the SOC stock was calculated. The mechanism of the prediction methods and the potential influencing factors of the model performance were discussed from the aspect of electromagnetic theory and empirical statistics. Results showed the following: (i) SOC stock can be successfully predicted using the laboratory spectra and the airborne hyperspectral image through the direct and indirect methods; (ii) the SOC stock and its relevant soil properties (SOM and SBD) showed evident spectral absorption characteristics in the vis–NIR spectral band; (iii) the atmospheric environment and soil surface conditions were the main influencing factors of the prediction accuracy between the airborne and laboratory spectra. This research might be useful for the dynamic monitoring and modeling of SOC in agricultural and environmental fields.
•Verify the potential of lab and airborne hyperspectral data in predicting SOC stock•Explore the prediction capability of vis–NIR spectra for SOC stocks•Discuss the potential influencing factors in predicting SOC stock
Drought is one of the most complex and harmful natural disasters. A study on the temporal and spatial patterns and the evolution of drought can provide a scientific basis for predicting drought ...occurrences. Based on a multi-source dataset, we select a suitable control drought indicator for improving the vegetation health index (VHI), optimize its algorithm through Pearson correlation analysis, and compare the VHI performance before and after the improvement for various vegetation types. Results show that (1) the self-calibrated Palmer drought severity index is more suitable than the standardized precipitation evapotranspiration index for improving the VHI; (2) the contribution of the thermal condition index to the VHI in most parts of the world is higher than that of the vegetation condition index; (3) the enhanced VHI significantly improves the detection of vegetation drought; and (4) vegetation drought events occurring in high latitudes tend to worsen, and the response of different vegetation types to drought is significantly different. Our research presents a step forward in improving the effectiveness of the VHI in detecting vegetation drought and thus its application prospects. Furthermore, the response characteristics of various vegetation types to drought are identified, deepening our understanding of vegetation drought, which may help decision-makers and authorities to develop better mitigation and adaptation strategies to reduce losses caused by these events.
In most areas of the world, the contribution of TCI to VHI is larger than that of VCI. The newly developed VHIopt presents a significantly improved ability to detect vegetation drought when compared to the standard VHI. Furthermore, its performance in various vegetation types around the world is better than the VHIori. The new enhanced VHIopt is a step forward towards a better applicability prospect and reliability of VHI in drought detection. Display omitted
•sc-PDSI is more suitable for optimizing VHI on a global scale than SPEI.•VHIopt significantly improves the ability of vegetation drought detection.•There are obvious differences in the response of various types of vegetation to drought.•The contribution of TCI to VHI in most parts of the world is higher than that of VCI.•Our research improves the application prospect of VHI in vegetation drought detection.
•Sea breeze front (SBF) is one of the important weather systems affecting the occurrence and development of severe convective weather in the Bohai Bay region.•226 cases of merger-type SBFs (MSBFs) ...merged with gust fronts (GFs) and convective systems (CSs), respectively, were identified based on observational data from May to September during 2009–2018 in the BBR.•basic tempo-spatial characteristics and associated atmospheric circulation backgrounds of the MSBFs are documented for the first time.
Sea breeze front (SBF) is one of the important weather systems affecting the occurrence and development of severe convective weather in the Bohai Bay region (BBR). 226 cases of merger-type SBFs (MSBFs) merged with gust fronts (GFs) and convective systems (CSs), respectively, were identified based on Doppler weather radar data and ground-based automatic weather station data from May to September during 2009–2018 in the BBR, and their basic tempo-spatial characteristics and associated atmospheric circulation backgrounds are documented for the first time.
The number of MSBFs cases merged with GFs (MSBF-GFs) and that of MSBFs merged with CSs (MSBF-CSs) were 172 and 54, respectively. The number of MSBFs varied significantly in each year, with 37 (13) in the most (least) frequent year, and with an average number of 22.6 per year. More than 93.8 % of the MSBFs occurred from June to August, especially most frequent (37.2 %) in July. The merging locations of the MSBFs were mainly distributed in the central-northern Tianjin and the southeastern Hebei province, and the horizontal scales of MSBFs were mainly distributed in the range of 130–309 km. About 29.6 % (51.9 %) of the MSBF-CSs cases resulted in significantly (slightly) enhanced convections, while 51.4 % (23.8 %) of the MSBF-GFs bring about significantly (slightly) enhanced convections. About 72.1 % of the MSBF-GFs cases are merged in near “face-to-face” form, and their 49.2 % (23.4 %) proportion lead to significantly (slightly) enhanced convections. The atmospheric circulation patterns of MSBFs identified using objective classification method showed that, the major two patterns (occupied 56.6 % cases) have similar dynamic, thermodynamic, and water vapor characteristics including westerlies or southwesterlies with intensity about 8–10 m/s at 500 hPa, showing significant warm and moist air delivered from the south and relatively weak vertical wind shear along with intense water vapor convergence at 850 hPa.