Search

• Siltation transport behaviour of pipeline influenced by water flow remains unclear. • Critical bed shear stress model is proposed to solve boundary constraint problem. • Probability settlement function is adopted to assess ease of particle settlement. • Adaptive penalisation mechanism is adopted for intelligent settlement prediction. Siltation of drainage pipelines is a major disaster-causing factor in urban flooding. Owing to critical bed shear stress and the possibility of settlement at the bottom of pipes, there are significant nonlinear differences in the hydraulic transport and retardation response characteristics of siltation particles under different initial flow velocities, siltation degrees, and siltation lengths. Studies on siltation in drainage pipelines lack a comprehensive understanding of the intricate coupling dynamics between siltation particles and water flow, and the regularity governing the siltation transport behaviour under varying water flow conditions remains unclear. To solve these problems, this study constructs computational fluid dynamics and discrete element (CFD-DEM) coupling method and adaptive penalty model for pipeline deposition based on probabilistic settlement function, adaptive genetic algorithm, and bidirectional long short-term memory neural network (PSF-AGA-BLSTM). A three-dimensional transient hydraulic model of pipeline siltation was adopted to clarify the critical bed shear stress of the silt particles, after which an adaptive genetic algorithm with a probability settlement function as fitness was constructed to generate a numerous silt particle sample sets with settlement result labels. Adaptive genetic algorithms were combined with bidirectional long short-term memory neural networks to establish a spatiotemporal adaptive penalisation mechanism for pipeline silt particle transport. The simulation model based on PSF-AGA-BLSTM and CFD-DEM was analysed using simulation and scale tests and was found to have strong robustness and reliability. The results showed that the effects of siltation degree, flow rate, and siltation length on the transport of silt particles were all non-negligible; when the siltation degree exceeded 0.2, the siltation degree had a more significant effect on particle transport than siltation length and flow rate. The transport of silt particles occurred in two phases, rapid growth and steady growth under erosion by water flow. The rate of change in silt length accounted for up to 45% of the reason for silt nudging and silt spreading. The study clarified the hydraulic transport law of silt particles and analyzed the effect of different influencing factors. These efforts provide technical support for subsequent pipe cleaning and maintenance as well as flood prevention and mitigation. [ABSTRACT FROM AUTHOR]

• Siltation diagnosing systems of drainage pipes cannot achieve full coverage. • Generative adversarial network solves the small data sample problem. • Guided faster R-CNN and parallel multiscale U-Net improves flow measurement. • Stochastic neighbour embedding is better at compressing key silting features. • Multi-scale sampling improves the accuracy and robustness of siltation diagnosis. The regular detection and diagnosis mechanism for the silting disease of drainage pipelines (SDP) is critical for making dredging decisions and flood forecasting. Simultaneously, there is a complex coupling relationship between the pipeline siltation and the dynamic changes of the inlet and outlet flows. However, the traditional silting detection frameworks of drainage pipelines face difficulties in two aspects, accurate flow rate measurements and efficient and intelligent siltation diagnoses. In this paper, an automatic and integrated self-diagnosing system for the silting disease of drainage pipelines is proposed. First, a gradient penalty generative adversarial network (GPGAN), a target recognition algorithm called guided faster R-CNN (GF R-CNN) and an image segmentation method called parallel multiscale U-Net (PMSU-Net) are introduced to dynamically measure the flow of water in the drainage pipelines. Second, an automatic siltation detection and diagnosis algorithm of SDP is constructed based on a t-SNE stack sparse autoencoder (SSAE-TSNE) and multiscale long short-term memory (MS-LSTM). Then, a full-scale prototype verifies the feasibility of the system. This improved flow measurement algorithm achieves the highest accuracy of 90.32%, and an F1 score of 0.963 in comparison with the other algorithms, and the precision-recall curve was the closest to the top right corner. The error rate of the proposed self-diagnosing system is controlled within 8%, which is far better than the other algorithms. Finally, the system algorithms are embedded in an intelligent platform consisting of an unmanned pipeline measuring device (UPM), an unmanned aerial vehicle (UAV) and a server diagnostic centre. The practical application and test show that the accuracy, precision and response speed of the proposed integrated self-diagnosing system have obvious advantages in the function of siltation detection and diagnosis in drainage pipelines. [ABSTRACT FROM AUTHOR]

In order to realise the spatial equilibrium allocation of water resources in basin, a spatial pattern analysis model on the functions of water resources economic–social–ecological complex system (SP-FWESE) is constructed based on emergy analysis and spatial autocorrelation analysis. The function indicators (function, function intensity, and function density) of the water resources economic–social–ecological complex system (FWESEs) are corrected by the outlier detection and optimal interpolation methods based on local outlier factor (LOF) after quantifying by the emergy analysis method and their spatial patterns (spatial distribution, spatial correlation, and spatial aggregation characteristics) are explored by spatial autocorrelation analysis. The model is applied to nine Yellow River Basin (YRB) provinces (regions) to study the spatial pattern of the FWESEs, which verify the feasibility of SP-FWESE model from theoretical research and practical application. Major findings are: (1) There are differences in the spatial distribution of FWESEs in provinces (regions) of the YRB, some measures should be taken to adjust the spatial distribution of FWESEs. (2) The Moran's I of FWESEs is greater than 0, indicating the FWESEs have potential correlation among provinces (regions). (3) FWESEs in each province (region) of the YRB have obvious spatial aggregation characteristics, and the development stages of each province (region) are different and uncoordinated. These findings provide policy suggestions for the optimal allocation of water resources in the YRB from the perspective of spatial patterns. In addition, SP-FWESE model is also suitable for studying the spatial pattern of FWESEs in other regions. [Display omitted] • Realise the quantification of system function, function intensity and density. • Construct a spatial pattern analysis model on system functions. • Explore the spatial distribution, correlation and aggregation of system functions. • The model is applied to the Yellow River Basin to propose water policy suggestions. [ABSTRACT FROM AUTHOR]

The ecological restoration of the Yellow River Basin (YRB) requires urgent scientific and rational quantification of comprehensive value of water resources to optimally allocate water resources. Considering the sustainability of ecological environment, the quantifications of sediment transport value and negative sewage value were introduced into the calculation of comprehensive value of water resources in this study. First, Reynolds time-averaged turbulence equations, force analysis and fluid mechanics were adopted in succession to precisely calculate the work on the bedload sediment and the suspended load sediment. Next, the quantification of the value of sediment transport in each river interval was presented based on the emergy theory. Furthermore, to coordinate and optimize the ecological environmental, economic, and social values, a dynamic differential game-based multi-objective optimal water allocation model of the basin was proposed. On this basis, the Lagrangian multiplier method and the Hamiltonian function were exploited to obtain the optimal trading quantity of water in each province and bargain price. The provinces in the YRB were selected as a case study to verify the feasibility and practicality of the proposed model. Results indicate that (1) compared with previous optimal water allocation schemes, the economic value, social value, ecological environmental value, sediment transport value and negative sewage value of the YRB in this study in 2019 are ¥2.57✕1011, ¥3.27✕1011 , ¥2.74✕1011 , ¥6.27✕1010 , and ¥3.30✕1010 , respectively, which is more balanced and sustainable in each field; (2) this model significantly increases the ecological environmental value (EEV) of YRB in 2019 from ¥2.21✕1011 to ¥2.74✕1011—which takes into consideration the sediment transport value (STV) and negative sewage value, and thus the method in this study pays more attention to water ecological sustainability; (3) the model significantly improved the comprehensive value of water resources in the YRB to ¥ 785.2169✕108 if T = 1 month and ¥ 4471.0611✕108 if T = 0.5 year in 2019. Therefore, instead of pursuing economic value unilaterally, this study can coordinate and optimize the ecological environmental, economic, and social values (SV) to improve the strategic trade-offs in efforts towards basin water sustainability. [ABSTRACT FROM AUTHOR]

Water rights transaction has proved to be an effective method for constructing an efficient water distribution system (WDS) in various regions of the Yellow River Basin (YRB). In this study, an optimal WDS in the YRB is proposed by considering the comprehensive value of water resources, administrative management system, and market-based system. To accurately quantify the comprehensive value of water resources, the work analysis method of suspended load and bedload based on the emergy theory and time-averaged motion equation is introduced, and the quantification process of sediment transport value in the river course is formulated in the YRB. Based on this, an administrative and market-based game for water rights transaction is formulated. In this double-layer game model, the administrative authorities of the basin (Yellow River Conservancy Commission) and the corresponding regions (Water Resources Department) seek to maximize their own target revenue function/comprehensive value of the water resources. Then, the optimal trading quantity of water in each region and the bargain price can be solved. A case study is presented in the YRB to verify the effectiveness of this method. The results reveal that (1) the error rate of the riverbed shear stress as well as the sediment transport rate between the theoretical value and the calculated value does not exceed 8.76%, which indicates the rationality of the calculation method of sediment transport value; (2) the proposed dynamic differential game and pricing game perform well in determining the optimal trading quantity of water in each region. They also reveal the bargain price with optimal results of ¥ 4151.1456 half yearly and ¥ 8197.3466 per year in 2018, outperforming other methodologies. Unlabelled Image • Sediment transport value is related to the work done by the river flow. • Sediment movement in the river is divided into two types: bedload movement and suspended load movement. • Regions/provinces should obey unified coordination of the administrative agency in Yellow River Basin. • Market supply and demand has an influence on the bargain price in water rights transaction. • The double-layer dynamic game promotes the improvement of water efficiency. [ABSTRACT FROM AUTHOR]

• This research discussed the significance and composition of river eco-environmental benefits. • This study proposed the calculation method on the solar transformity of subtypes of water bodies. • This research proposed a quantification method for the sediment transportation benefit and improved the indicators' assessment of the eco-environmental benefits of rivers. • The calculation and comparative analysis of river eco-environmental benefits were carried out. The assessment of the eco-environmental benefits of rivers has important guiding significance for improving water resource management, establishing water resource protection mechanisms, and maintaining river health. In view of the current imprecise quantitative methods of determining the eco-environmental benefits of rivers and based on the viewpoint of ecology, the significance and composition of river eco-environmental benefits were discussed. An emergy theory was introduced to quantify both the solar transformity of subtypes of water bodies and the sediment transportation benefit, which improved the indicator system of eco-environmental benefits. Applying the indicator system to the management practice of the Yellow River Basin, the eco-environmental benefits in 2015 were calculated by dividing the Yellow River into 66 sections. A Geographic Information System (GIS) atlas was then used to describe their spatial distribution. Eight typical cities were selected for the key analysis. Among these eight cities, the eco-environmental benefit inside the river in Xi'an section is the largest with a total emergy benefit of 1.08 × 1021 solar equivalent joules (sej) and a corresponding monetary benefit of 28.03 Chinese Yuan (¥)/m3. The eco-environmental benefit outside the river in Jinan section is the largest with a total emergy benefit of 1.37 × 1020 sej and a corresponding monetary benefit of 12.39 ¥/m3. This study proposed that rivers have great eco-environmental benefits, and the harmonious development of economy, society, and environment should be pursued in water resources management. [ABSTRACT FROM AUTHOR]

• Existing siltation diagnosis schemes cannot solve the distortion. • Discretisation solves engineering calculation of differential equations. • Hard constraint projection is better at enhancing system robustness. • Theory-guided loss function improves the diagnosis accuracy. An accurate and robust diagnostic model for the silting disease of drainage pipelines is significant for the numerical simulation of urban waterlogging and assessment of risk areas. Various long short-term memory (LSTM) neural networks have been adopted for intelligently diagnosing pipeline siltation owing to the strong correlation between pipeline siltation and flow characteristics over time. However, LSTM often has strong randomness and uncertainty when diagnosing the collocation points of non-training set features and rules and violates the basic fluid–solid coupling physical mechanism. To fully integrate fluid–solid coupling domain knowledge with data-driven neural networks to improve the accuracy of the diagnostic model, this study proposes a knowledge-data collaboratively driven model based on hard constraint projection (HCP) and theory-guided loss function correction (TLFC) for the intelligent diagnosis of drainage pipeline siltation (IDPS). This diagnostic model converts physical fluid–solid coupling constraints, such as the governing equations and boundary/initial conditions, into a mathematical simplification that is easy to handle through discretisation. It adjusts input data sequence and optimises diagnostic results from intelligent algorithms through HCP on the hyperplane and theory-guided loss function correction. The performance of the self-diagnosing system integrating fluid–solid coupling domain knowledge with deep learning models was verified through experiments based on a full-scale prototype. The experiment results indicate that the proposed model had a good ability of robustness to resist the noisy input observations when no less than 600 boundary points were adopted. Compared with typical LSTM, TLFC-based LSTM and HCP-based LSTM, the proposed algorithm achieved highest performance regarding diagnostic accuracy. The mean absolute percentage error of the proposed system was kept below 2%. Furthermore, owing to the knowledge-data collaboratively driven mechanism, the proposed system can extrapolate and accurately diagnose situations outside the training dataset range. [ABSTRACT FROM AUTHOR]

[Display omitted] • Refine the concept and composition of social values of water resources (SVWR). • Propose an emergy-spatial autocorrelation-spatial regression (ESSR) model. • Reveal the spatial distribution characteristics of SVWR in the basin by ESSR model. • Determine the spatial influencing factors of SVWR in the basin by ESSR model. Identifying the spatial distribution characteristics and influencing factors (SDC-IF) of the social value of water resources (SVWR) within a basin is an effective means to realize the dynamic regulation of water resources. In this paper, the concept of the SVWR was based on energy flow in the water resources social subsystem. Spatial econometric methods were initially introduced into the study of the SVWR to establish an emergy-spatial autocorrelation-spatial regression (ESSR) model to explore the above problem. The study area, the Yellow River Basin (YRB), was used to verify model applicability, in which the analysis highlighted three key findings: 1) The Moran's I of the SVWR exceeded 0, indicating the SVWR had spatial correlation in the YRB. 2) The SVWR in provinces (regions) and cities were 30.76–32.87 and 24.88–30.67 yuan/m3, respectively, and its spatial distribution in the YRB was non-uniform, highlighting inequity in current water allocation. 3) The greatest spatial influencing factors of the SVWR in provinces (regions) were agriculture and forestry water inputs, whereas it was domestic water consumption in cities. The factors with the least influence were the employees of agriculture-forestry-stockbreeding-fishery; these should be considered in future water resources management. The findings show that the dynamic equilibrium regulation of water resources in the basin can be realized by adjusting the SDC-IF of SVWR, contributing to the fair distribution of water resources. In addition, the model may provide technical references for similar studies in other watersheds, contributing to the sustainable development of global water resources. [ABSTRACT FROM AUTHOR]

• Fatigue tests and reliable 3D simulations on concrete pipes under traffic loads were conducted. • The mechanical response of concrete pipes under fatigue traffic loads was investigated. • Fatigue life of concrete pipes was accurately predicted with the developed formula. In recent years, there has been a concerning increase in road collapses triggered by failures in urban drainage systems. Concrete pipes, commonly uesd in urban drainage pipelines, endure prolonged cyclic loading from traffic above. However, the mechanisms governing the long-term performance and fatigue damage remain unclear. Through conducting fatigue model box tests on concrete pipes, the effects of different fatigue loading cycles on the circumferential strain of concrete pipes were investigated. A fatigue life prediction equation for concrete pipes was proposed, and the crack propagation under various fatigue loading cycles was observed. Additionally, corresponding 3D FE models of concrete pipe-soil interaction with bell-and-spigot joints and gaskets were constructed. These models were used to explore the vertical displacements, circumferential bending moments, and circumferential stresses of the concrete pipes under different fatigue loading cycles, the damage and failure mechanisms of the concrete pipes under fatigue loading were revealed. The results indicate that the potential failure location of concrete pipes is within the inner crown of the bell under the fatigue traffic loads. The circumferential strains and crack propagation exhibiting a three-stage evolution pattern under fatigue loads. The proposed fatigue life prediction equation accurately predicts the remaining life of concrete pipes. Upon reaching 21.89 million loading cycles, the strain at the inner crown of the bell reaches 575.0 με, resulting in complete failure. Cracks on the inner crown of the bell extend inward and to the right from the middle of the joint, forming a channel for crack propagation. The vertical displacements at the crown and the circumferential bending moments of the bell and spigot exhibit rapid increases, stabilization, and subsequent declines with the increasing loading cycles. When concrete pipes undergo fatigue fracture, the maximum vertical displacement and circumferential bending moment at the bell are measured as 2.26 mm and 17.82 kN·m/m, respectively. Stress concentration at the bell and spigot during fatigue loading leads to crack propagation and convergence, causing redistribution of stress fields characterized by an initial increase followed by a decrease in the inner crown and invert of the bell. [ABSTRACT FROM AUTHOR]

• A simulation method that integrates the spatial random frequency function and drainage pipe model is presented. • Utilizing attention operators to construct attention mechanisms, a Point Transformer drainage pipe detection model is established. • The study investigates how various parameters affect the model's accuracy. • The effect of different proportions of datasets on the segmentation performance of the model is studied. • The developed model is employed for accurately segmenting corrosion in drainage pipes. Deep learning based Closed Circuit Television (CCTV) image detection has achieved remarkable accuracy in identifying and segmenting concrete pipeline damages. However, the lack of in-depth information and requirement for large amounts of training data are two major drawbacks. Therefore, this study proposes a point cloud data segmentation method that incorporates depth information to address the issue of insufficient training data for depth models, enabling efficient and accurate segmentation. Firstly, 3D simulation technology is employed to construct a simulation dataset. Secondly, an optimized point transformation model is established to identify and segment the point cloud data. The proposed method achieved a test accuracy of 94.36 % by optimizing the network structure and the training strategy. The Mean Intersection over Union (MIoU) increased by 3.62 % and 10.3 %, respectively, compared with the classic PointNet++ and before adding simulation data, reaching 86.31 %. These results demonstrate that the proposed method exhibits high precision defect detection capability on three-dimensional point clouds of drainage pipelines. [ABSTRACT FROM AUTHOR]

• Introduces a novel Genetic Algorithm-optimized BP Neural Network for accurate polymer fracture grouting predictions. • Designs a precise test device to explore fracture and grouting parameters systematically. • The GA algorithm significantly improves the accuracy and robustness of the grouting effect prediction when compared with multiple prediction models. Polymer grouting can effectively improve the stability of surrounding rock fractures. However, in practical construction, it is difficult to judge the degree of coupling between the slurry and the rock, and the effective grouting range after grouting. Therefore, early prediction of the effect of grouting on the surrounding rock is crucial. In this paper, a new artificial intelligence method is proposed to predict the polymer fracture grouting effect. The genetic algorithm optimized back propagation neural network (GA-BP) is employed to construct an intelligent prediction model. To acquire a substantial dataset for constructing the model, an easily assembled/disassembled test apparatus for polymer fracture grouting is designed. The maximum coupling degree of the fractures and slurry diffusion distance are chosen as the evaluation metrics for the grouting effectiveness. The influences of the fracture characteristic parameters and grouting volume on the grouting effect are investigated. Furthermore, a comprehensive analysis is conducted on the spatiotemporal diffusion characteristics and slurry-rock coupling mechanism of polymer grouting. Compared to traditional BP neural networks, and three other machine learning algorithms (decision trees, random forests and gradient boosting decision trees), the GA-BP model outperforms them in terms of R2 (coefficient of determination), MSE (mean squared error), MBE (mean bias error), MAE (mean absolute error) and RMSE (root mean squared error) in both the test and training sets. The GA algorithm significantly improves the accuracy and robustness of the prediction model. The optimized model demonstrates significant accuracy in predicting grouting results and assessing efficiency, providing a practical reference for grouting construction. [ABSTRACT FROM AUTHOR]

Promoting environmental management system reform in an orderly manner and coordinating central and local environmental protection responsibilities are important for high-quality economic development. Based on panel data of 289 cities in China from 2008 to 2016, this paper uses the fixed effects model and threshold regression model to discuss the relationships among regional competition, environmental decentralization, and target selection of local governments and to analyze whether environmental decentralization produces the Porter effect. Findings show that environmental decentralization does significantly promote economic development, strengthen environmental pollution control, and generate a strong Porter effect, due to greater R&D investment, improvement in green technology innovation ability, and optimization of the industrial structure. The effect of environmental decentralization shows significant regional heterogeneity in terms of regional financial pressure, economic development level, and environmental pressure, while regional competition distorts the effect of environmental decentralization. With the intensification of regional competition, environmental decentralization greatly improves the emission intensity of pollutants, whereas it promotes economic development after inhibiting it. The above conclusions are of great significance for pushing forward environmental decentralization, formulating a differentiated environmental decentralization strategy, and perfecting the government performance appraisal system. Environmental decentralization will promote economic development, reduce pollutant emission intensity and produce Porter effect. And environmental decentralization will improve the ability of regional innovation, promote the optimization of industrial structure, and then affect the target selection of local government. With regional competition intensification, while promoting local economic development, environmental decentralization greatly increases the emission intensity of pollutants. Unlabelled Image • Coordinating central and local environmental protection responsibilities is important guarantees for high-quality economic development. • This paper discussed the relationship between regional competition, environmental decentralization and target selection of local government. • Environmental decentralization can significantly promote economic development, strengthening the environmental pollution control. • With the intensification of regional competition, environmental decentralization greatly increases the emission intensity of pollutants. [ABSTRACT FROM AUTHOR]

The prestressed concrete cylinder pipe (PCCP) with broken wires should be strengthened to maintain the safe operation of the pipeline. A new reinforcement technology is proposed in this study: expanded polystyrene (EPS) + carbon fiber reinforced polymer (CFRP) liner. The innovative method allows CFRP to bear the internal pressure prior to PCCP, greatly improving the reinforcement effect of the pipe. A three-dimensional finite element model is established and assessed by the experimental results. Then, the mechanical properties of the PCCP when subjected to different pressures and wire breakage are analyzed under three conditions (i.e. no strengthen, strengthened by only CFRP liner, and strengthened by EPS+CFRP liner). And the improvement effect of the innovative technology on the PCCP's bearing capacity compared with the traditional method is studied. The results showed that when repaired by 8-layer CFRP liner only and EPS and 6-layer CFRP composite liner, the internal pressure bearing capacity of PCCP can be increased by 9.17% and 50.83%, respectively. Based on the elastic limit state of the pipe, the wire breakage threshold of PCCP is 65 and 89 under the cases of no repair and CFRP liner repair. For the case of EPS + CFRP liner repair, when the number of broken wires is 100, the steel cylinder does not yield. • An innovative reinforcement technology of EPS + CFRP liner is proposed. • A 3D FE model is established and assessed by the experimental results. • The mechanical properties of the PCCP are analyzed under three conditions. • The bearing capacity of PCCP can be increased by 50.83%. [ABSTRACT FROM AUTHOR]

The two-component non-water reactive foamed polyurethane (TNFPU) material utilized in structural restoration scenarios may experience shear failure when subjected to multifaceted external factors, potentially culminating in structural instability or even failure. Consequently, it is imperative to conduct a thorough examination of the shear properties of TNFPU material. A series of direct shear tests were conducted to investigate the impact of factors such as density, normal stress, and shear rate on the shear properties of TNFPU material. These properties encompass shear strength, shear modulus, peak shear displacement, shear deformation, and shear dilation angle. The findings underscore the density and normal stress had more significant effects on the shear properties of TNFPU material. Conversely, the impact of shear rate on shear performance was relatively modest and exhibited a diminishing trend as density increased. Notably, a specific discovery emerged: the effects of density, normal stress, and shear rate on the shear properties of TNFPU displayed pronounced distinctions before and after reaching a critical density threshold of 0.51 g/cm³. Furthermore, the study revealed a phenomenon of shear dilation and contraction transformation when the density or normal stress exceeded a certain critical value. • The shear behaviors of TNFPU material are investigated by direct shear tests. • The evolution of stress-displacement curves from hardening to softening is revealed. • The shear dilation and shear contraction are revealed through shear deformation. • The shear property exhibits significant differences around a density of 0.51 g/cm³. [ABSTRACT FROM AUTHOR]

• An 3D inspection method on point clouds for pipe defects was proposed. • The network structure was optimized to improve the inspection accuracy. • The training strategies were improved to stabilize training and avoid overfitting. • Two data augmentation methods are used to facilitate training. With the development of deep learning (DL), sewer pipe inspection on two-dimensional (2D) images has achieved remarkable accuracy. However, extracting defect measurements from these 2D images is challenging due to the curved nature of pipes and the lack of depth information. Point clouds can restore the three-dimensional (3D) information of objects. To effectively identify defects in disordered and sparse point clouds, a 3D sewer pipe classification and segmentation method was proposed. In the encoder, the original point clouds are sampled and grouped and the local features in the clusters are extracted by two symmetric functions (1 × 1 convolution and the maximization function) to process the points with permutation invariance. In the decoder, the multi-scaling abstract features are upsampled using feature pyramid network (FPN) to predict the category of each point. Especially, the network structure and training strategy of the inspection method is optimized to improve the inspection accuracy. Furthermore, two data augmentation methods, namely random scaling and point jitter, are used to increase the data volume. An ablation experiment shows that the optimization of network structure can effectively improve the performance of the inspection model and the novel training strategies can stabilize the training process and prevent overfitting. Comparison among the state-of-the-art networks demonstrates that the proposed segmentation model attains the highest mIoU of 94.15 %, which is improved by 11.46 % with the optimization of network structure and training strategy. For the classification task, the F1 score and accuracy of the established model are 6.79 % and 5.46 % higher than PointNet++, respectively. These results signify the high-accuracy defect inspection capability of our proposed method on 3D point clouds of sewer pipelines. [ABSTRACT FROM AUTHOR]

• A DCGAN with an improved loss function is applied to augment the GPR data. • A recognition model of defects strengthened by attention modules is proposed. • The location and span size of defects are obtained. • The effectiveness of this method is verified in the field experiment. Collapses of urban roads caused by defects in shallow underground spaces are extremely dangerous, and this imposes high requirements for the detection of potential defect areas. Although the characteristics of defects, including voids, water-bearing voids, hyperbola defects and loose defects, can be effectively detected using ground penetrating radar (GPR), amounts of GPR data are currently limited. In this work, a deep convolutional generative adversarial network (DCGAN) with an improved loss function is applied to augment existing GPR data to give a total of 3,256 images. More importantly, a recognition model for underground defects is proposed based on GPR B-scans and strengthened with attention modules using YOLO v5. The mean average precision (mAP) of the model is 85.4 %, a value 3.26 % higher than that of YOLO v5. The values of the average precision (AP) for voids, water-bearing voids, hyperbolae, and loose defects are 87.5 %, 86.6 %, 96.2 %, and 71.1 %, respectively. Finally, the locations and span sizes of the defects are obtained by estimating the velocity of the electromagnetic wave, and this approach is verified through a field test. The absolute error in the burial depth is less than 0.16 m, and the average error ratio is less than 15 %. The absolute error in the horizontal span is found to be lower than 0.28 m, with an average error ratio of smaller than 22 %. Consequently, the proposed method provides reasonable support for more accurate and effective detection of underground defects. [ABSTRACT FROM AUTHOR]

Water pollution compensation is one of the important economic means of water pollution control and management, and the quantification of compensation standard is the key link in the implementation of water pollution ecological compensation. Because the ecological compensation refers to ecological environment, society and economy at the same time, the emergy analysis method of ecological economics was introduced to the quantification study of water pollution ecological compensation standard to overcome the shortcomings of traditional methods, and the ecological economic value of pollutants dilution water is defined as water pollution ecological compensation standard In the process, the key pollutants in river was confirmed by water quality assessment, then the water dilution model was built and the dilution water amount when pollutant concentration meeting the standards of water quality section was determined on the basis of purification of key pollutants. Using the Qingyi River as an example, the water pollution compensation standard of the key pollutants (NH 3 -N and COD) were calculated, which showed that the comprehensive compensation standard of NH 3 -N are all higher than COD in six control section. Among them, the highest comprehensive compensation standard is 93.99 yuan/t in Heshang Bridge (Changge City), the next one is 74.07 yuan/t in Hutuo sluice, and Zengfumiao Village is without compensation. Therefore, the pollutant discharge levels are different in different section, and then their compensation standards are different. To sum up, the economic, social and ecological losses caused by water pollution were considered synthetically and the emergy method for the accurate quantification of water pollution ecological compensation standard was provided. [ABSTRACT FROM AUTHOR]