Spatiotemporal Simulation Research Articles

Numerical simulation of the temporal and spatial evolution of sandstone pore type reservoir damage types and severity

During the oilfield development process, various factors can cause different types of reservoir damage, leading to reduced oil well production or even shutdown, and decreased water injection capacity in water wells, resulting in significant economic losses for the oilfield. However, formation damage control measures must be based on the quantitative diagnosis of the types and degrees of reservoir damage. This paper establishes a spatiotemporal evolution numerical model for 12 common types of damage during the oil and gas exploration and development process, based on the material balance theory and Fick’s diffusion law in reservoir damage processes. This model achieves numerical simulation of the degree of various reservoir damage types in different spatiotemporal domains. The overall damage degree of a specific well’s evolution with time and space is further simulated in simple superposition way. The sequential core flow experiment was carried out in the laboratory, and then compared with the calculation results. The accuracy is above 90%. Finally, using field test data, the simulation results show a 95% or higher degree of agreement with the actual field measurements, proving that the reservoir damage spatiotemporal evolution quantitative simulation technology established in this paper has high accuracy and practicality.

Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence

Simulating spatiotemporal turbulence with high fidelity remains a cornerstone challenge in computational fluid dynamics (CFD) due to its intricate multiscale nature and prohibitive computational demands. Traditional approaches typically employ closure models, which attempt to represent small-scale features in an unresolved manner. However, these methods often sacrifice accuracy and lose high-frequency/wavenumber information, especially in scenarios involving complex flow physics. In this paper, we introduce an innovative neural differentiable modeling framework designed to enhance the predictability and efficiency of spatiotemporal turbulence simulations. Our approach features differentiable hybrid modeling techniques that seamlessly integrate deep neural networks with numerical PDE solvers within a differentiable programming framework, synergizing deep learning with physics-based CFD modeling. Specifically, a hybrid differentiable neural solver is constructed on a coarser grid to capture large-scale turbulent phenomena, followed by the application of a Bayesian conditional diffusion model that generates small-scale turbulence conditioned on large-scale flow predictions. Two innovative hybrid architecture designs are studied, and their performance is evaluated through comparative analysis against conventional large eddy simulation techniques with physics-based subgrid-scale closures and purely data-driven neural solvers. The findings underscore the potential of the neural differentiable modeling framework to significantly enhance the accuracy and computational efficiency of turbulence simulations. This study not only demonstrates the efficacy of merging deep learning with physics-based numerical solvers but also sets a new precedent for advanced CFD modeling techniques, highlighting the transformative impact of differentiable programming in scientific computing.

Assessment and Multiscenario Simulation of Land Use and Ecosystem Services Interactions in Inner Mongolia

ABSTRACTBalancing land development and ecological protection poses significant challenges for sustainable development in arid and semi‐arid regions like Inner Mongolia. This study uses the integrated valuation of ecosystem services (ESs) trade‐offs model and patch‐generated land‐use simulation model to analyze the impacts of land‐use/cover (LULC) changes on ESs from 2005 to 2020 and simulate scenarios for 2035. The results show that (1) ecological governance efforts improved the comprehensive ecological index (CEI), habitat quality, and soil conservation capacity but led to a decrease in the annual water yield (AWY) in the eastern region. Additionally, the conversion of grassland and forest land to construction land and farmland caused slight declines in carbon sequestration and increased nitrogen export. (2) The external driving factors of different ESs vary, and the internal relationships within ESs have also changed. Notably, changes in LULC transformed the synergy between AWY and habitat quality into a trade‐off relationship after 2010 due to increased forest and grassland. (3) Among the five land‐use scenarios, the comprehensive development scenario combined with zonal management strategies can achieve the sustainable development goals of economic growth, ecological protection, and food security. This study clarifies the internal and external factors affecting ESs in Inner Mongolia and provides a scientific basis for future LULC management and ecological governance policies. It fills a gap in the spatiotemporal simulation of ESs under multiple scenarios in this region. These findings offer valuable references for promoting sustainable development in similar arid and semi‐arid regions, highlighting the importance of integrating multi‐objective strategies and adaptive management practices to balance ecological and economic objectives.

Spatiotemporal Evolution and Simulation Prediction of Ecosystem Carbon Storage in the Yellow River Basin Before and After the Grain for Green Project

Under the background of "dual carbon", the impact of the implementation of the Grain for Green project on the carbon storage of the ecosystem in the Yellow River Basin must be explored, which can serve as an important reference for improving the policy implementation of the new round of the Grain for Green project and improving the carbon sink capacity of the ecosystem in the Yellow River Basin. In this study, 1990, before the implementation of the project, was selected as the starting year of the research period, and 2020, after the implementation of the two rounds of the project, was selected as the end year of the research period. Based on the ecosystem type data from 1990 to 2020, the InVEST model was used to calculate the soil carbon pool, underground carbon pool, below carbon pool, dead organic matter carbon pool, and total carbon storage of ecosystems in the Yellow River Basin and the area where the project was implemented from 1990 to 2020. The results showed that： ① From 1990 to 2020, the area of forest ecosystem in the Yellow River Basin expanded by 26 610.06 km2, and the area of farmland decreased by 46 849.06 km2 after the implementation of two rounds of the project. Spatially, the upper reaches of the Yellow River were dominated by grassland and other ecosystems； the middle reaches of the Yellow River were dominated by farmland, forest, and grassland ecosystems； and the lower reaches of the Yellow River were dominated by farmland ecosystems. ② From 1990 to 2020, the carbon storage in the project implementation area showed a fluctuating and increasing trend, and the total carbon storage reached a peak （219.47×108 t） in 2009 and decreased to 218.59×108 t in 2020 due to the decrease of grassland ecosystem from 2010 to 2020. Spatially, the high-value areas of carbon storage were distributed in Aba Tibetan and Qiang Autonomous Prefecture of Sichuan Province and the southern tip of Gansu Province in the upper reaches of the forest and grass accumulation and in the whole of Shanxi Province and the central and southern parts of Shaanxi Province in the middle reaches. Shangluo City in Shaanxi Province and Alxa League in Inner Mongolia Autonomous Region were prefecture-level cities with the highest and lowest average carbon density. ③ In 2035, the carbon storage loss of the natural development scenario was predicted to be 0.83×108 t, and the other three scenarios would increase this loss. Under the moderate farmland return scenario, the Yellow River Basin ecosystem had the strongest carbon sequestration capacity, and the predicted carbon storage would increase by 2.72×108 t compared with that in 2020, and the deep farmland return scenario was the comprehensive optimal scenario. Therefore, in the future, the Yellow River Basin could refer to the deep farmland return scenario to optimize and adjust the implementation plan of the Grain for Green project, and the predicted value of carbon storage can provide some data support for achieving the dual carbon goal.

Time-guided convolutional neural networks for spatiotemporal urban flood modelling

Urban flood modelling is key to understand flood risks and develop effective interventions in flood management. Deep learning (DL), known for its robust and automatic feature extraction capabilities, has been applied for urban flood predictions. However, the hybrid spatiotemporal structure of conventional DL-enabled urban flood models is limited in terms of accuracy and efficiency. To address this gap, this study develops a new DL model guided by time information. This model uses a classic CNN (Convolution Neural Network) architecture, Unet, as its backbone. Time information is integrated into inputs via an extra channel to specify the desired prediction time, facilitating the simulation of the spatiotemporal flood process. Additionally, a modified loss function is formulated to tackle the sample imbalance problem between flooded and non-flooded sites. The model performance is assessed in an urban area in Dalian, China with a total of 18 rainfall events of varying return periods. The model attains average precision and recall values of 0.90 and 0.81, respectively, across different time steps during various events. Furthermore, the model exhibits transferability in ungauged regions where a high influence of surrounding environments on local flood processes is identified by Grad-CAM (Gradient-weighted Class Activation Mapping) analysis. The results show that the new Unet model has great promise in efficiently providing accurate spatiotemporal flood simulations. The time-guided Unet model can serve as practical tools for rapid flood simulation in urban areas.

Research Progress in Spatiotemporal Dynamic Simulation of LUCC

Land Use and Land Cover Change (LUCC) represents the interaction between human societies and the natural environment. Studies of LUCC simulation allow for the analysis of Land Use and Land Cover (LULC) patterns in a given region. Moreover, these studies enable the simulation of complex future LUCC scenarios by integrating multiple factors. Such studies can provide effective means for optimizing and making decisions about the future patterns of a region. This review conducted a literature search on geographic models and simulations in the Web of Science database. From the literature, we summarized the basic steps of spatiotemporal dynamic simulation of LUCC. The focus was on the current major models, analyzing their characteristics and limitations, and discussing their expanded applications in land use. This review reveals that current research still faces challenges such as data uncertainty, necessitating the advancement of more diverse data and new technologies. Future research can enhance the precision and applicability of studies by improving models and methods, integrating big data and multi-scale data, and employing multi-model coupling and various algorithmic experiments for comparison. This would support the advancement of land use spatiotemporal dynamic simulation research to higher levels.

Enhanced damping and bandwidth in roton-like dispersion of a beyond nearest neighbor periodic chain

This paper investigates the intriguing roton-like phenomenon occurring in systems with non-local interactions, wherein a single dispersion curve exhibits positive and negative group velocities. Previous research has predominantly concentrated on investigating the roton dispersion in undamped metamaterials through steady-state vibration and driven wave methodologies. However, exploring transient wave propagation in damped metamaterials, employing a free wave approach to study damping enhancement (metadamping), has received comparatively little attention. Addressing this research gap, the damping of the system is quantified as the rate of decay of transient vibrations. Results show a significant increase in damping and attenuation bandwidth, coinciding with the presence of the roton-like phenomenon. Unlike previous studies on metadamping, the proposed beyond nearest neighbor (BNN) chain simultaneously enhances both damping and reduction in acoustic bandwidth without sacrificing either property. Spatiotemporal domain simulation evidenced the existence of backward propagating wave packets due to a roton-like phenomenon in the specific frequency range.

Spatio-temporal evolution, driving mechanisms, and simulation of land use and cover in China from 2000 to 2060

Spatio-temporal evolution, driving mechanisms, and simulation of land use and cover in China from 2000 to 2060

Spatio-temporal analysis and prediction of land use landcover (LULC) change in Wular Lake, Jammu and Kashmir, India.

Landsat land use/land cover (LULC) data analysis to establish freshwater lakes' temporal and spatial distribution can provide a solid foundation for future ecological and environmental policy development to manage ecosystems better. Analysis of changes in LULC is a method that can be used to learn more about direct and indirect human interactions with the environment for sustainability. Neural network technology significantly facilitates mapping between asymmetric and high-dimensional data. This paper presents a methodological advancement that integrates the CA-ANN (cellular automata-artificial neural network) technique with the dynamic characteristics of the water body to forecast forthcoming water levels and their spatial distribution in "Wular Lake." We used remote sensing data from 2001 to 2021 with a 10-year interval to predict spatio-temporal change and LULC simulation. The validation of the calibration of predicted and accurate LULC maps for 2021 yielded a maximum kappa value of 0.86. Over the past three decades, the study region has seen an increase in a net change % in the impervious surface of 22.41% and in agricultural land by 52.02%, while water decreased by 14.12%, trees/forests decreased by 40.77%, shrubs decreased by 11.53%, and aquatic vegetation decreased by 4.14%. Multiple environmental challenges have arisen in the environmentally sustainable Wular Lake in the Kashmir Valley due to the vast land transformation, primarily due to human activities, and have been predominantly negative. The research acknowledges the importance of (LULC) analysis, recognizing it as a fundamental cornerstone for developing future ecological and environmental policy frameworks.

Development of a coupled surface water–groundwater model for the spatiotemporal simulation of river–aquifer interactions

AbstractIntegrating surface and groundwater use is a crucial part of water management. When one type of water is depleted, the other follows suit because of the constant movement and interaction between them. Therefore, the primary objective of this research is to establish a method by which the water evaluation and planning system (WEAP) surface water model and the MODFLOW groundwater model can communicate with one another. This article aims to demonstrate the interdependence of groundwater and surface water. Here, we use MODFLOW to model the saturated soil region and the soil moisture method to model the unsaturated soil region. The interaction between surface water and groundwater will affect the region's water resources and how they will operate under the continuance of existing practices. The simulation of saturated and unsaturated soil zones using a connected model of surface and groundwater employing all the hydroclimatology balance components is one of the most significant accomplishments of this research. The findings show that the (Iran) Sonqor Plain's maximum aquifer recharge throughout the months of November to May during a period of 30 years (October 1991 to September 2020) ranges between 1.5 and 2.6 million m³. A lack of recharge from irrigation water infiltration occurs in some of these months in addition to rain. The highest rate of groundwater level increase in this area is 4.5 m yr⁻¹ as a result of the distribution of irrigation water provided from the dam in the north‐western region.

Spatiotemporal dynamic relationships and simulation of urban spatial form changes and land surface temperature: a case study in Chengdu, China.

Exploring the spatiotemporal dynamic evolution of local climate zones (LCZ) associated with changes in land surface temperature (LST) can help urban planners deeply understand urban climate. Firstly, we monitored the evolution of 3D urban spatial form in Chengdu City, Sichuan Province, China from 2010 to 2020, used the ordinary least squares model to fit the dynamic correlation (DR) between the changes in urban spatial patterns and changes in LST, and revealed the changes of urban spatial patterns closely related to the rise in LST. Secondly, the spatiotemporal patterns of LST were examined by the integration of the Space-Time Cube model and emerging hotspot analysis. Finally, a prediction model based on curve fitting and random forest was integrated to simulate the LST of study area in 2025. Results show the following: the evolution of the urban spatial form consists of three stages: initial incremental expansion, midterm incremental expansion and stock renewal, and late stock renewal and ecological transformation. The influence of the built environment on the rise of LST is greater than that of the natural environment, and the building density has a greater effect than the building height. The overall LST shows a warming trend, and the seven identified LST spatiotemporal patterns are dominated by oscillating and new hotspots patterns, accounting for 51.99 and 11.44% of the study area, respectively. The DR between urban spatial form and LST varies across different time periods and built environment types, whereas the natural environment is always positively correlated with LST. The thermal environment of the city will warm up in the future, and the area affected by the heat island will shift to the central of the city.

Spatio-temporal evolution mechanism and dynamic simulation of nitrogen and phosphorus pollution of the Yangtze River economic Belt in China

Excess nitrogen and phosphorus inputs are the main causes of aquatic environmental deterioration. Accurately quantifying and dynamically assessing the regional nitrogen and phosphorus pollution emission (NPPE) loads and influencing factors is crucial for local authorities to implement and formulate refined pollution reduction management strategies. In this study, we constructed a methodological framework for evaluating the spatio-temporal evolution mechanism and dynamic simulation of NPPE. We investigated the spatio-temporal evolution mechanism and influencing factors of NPPE in the Yangtze River Economic Belt (YREB) of China through the pollution load accounting model, spatial correlation analysis model, geographical detector model, back propagation neural network model, and trend analysis model. The results show that the NPPE inputs in the YREB exhibit a general trend of first rising and then falling, with uneven development among various cities in each province. Nonpoint sources are the largest source of land-based NPPE. Overall, positive spatial clustering of NPPE is observed in the cities of the YREB, and there is a certain enhancement in clustering. The GDP of the primary industry and cultivated area are important human activity factors affecting the spatial distribution of NPPE, with economic factors exerting the greatest influence on the NPPE. In the future, the change in NPPE in the YREB at the provincial level is slight, while the nitrogen pollution emissions at the municipal level will develop towards a polarization trend. Most cities in the middle and lower reaches of the YREB in 2035 will exhibit medium to high emissions. This study provides a scientific basis for the control of regional NPPE, and it is necessary to strengthen cooperation and coordination among cities in the future, jointly improve the nitrogen and phosphorus pollution tracing and control management system, and achieve regional sustainable development.

Spatio-temporal evolution analysis of land use change and landscape ecological risks in rapidly urbanizing areas based on Multi-Situation simulation − a case study of Chengdu Plain

Land use change in emerging nations raises landscape ecological risks (LERS), hastens the deterioration of urban and rural ecosystem services, endangers human well-being, and undermines sustainable development in the face of rapidly increasing urbanization. Here, using the Chengdu Plain as the study area and long time series data from 2000 to 2020, the optimal time span is selected for multi-context spatio-temporal simulation. The land use map of Chengdu Plain in 2025 under the four scenarios of “Natural Development” (ND), “Economic Priority Development” (END), “Ecological Priority Development” (ELD), and “Sustainable Development” (SD) was simulated, and the multi-indicator landscape ecological risk index (ERI) was generated to compare and analyze the differences between land use and landscape ecological risk under different policy preferences. Subsequently, the land use data from 2025 to 2040 were simulated, the landscape ecological risk pattern was mapped, and the spatial and temporal evolution analysis from 2010 to 2040 was conducted to explore the spatial evolution law of land use change and landscape ecological risk. Based on the results, the high ecological risk aggregation areas are prone to appear in END scenarios, whereas medium-ecological risk aggregation areas are more likely to appear in ELD scenarios, and the government should focus its policy on arable land protection. Moreover, the land use pattern of cultivated land surrounding construction land and forested land surrounding cultivated land, caused by the irrational single-core development pattern and the policy of returning farmland to forests, has exacerbated the landscape ecological risk of the Chengdu Plain, constituting a unique landscape ecological risk pattern. It’s also important to remember that the Chengdu Plain’s less economically developed regions need to focus on the high-quality development of ecological land use. We adopted high-precision simulation methods to simulate the complex land use changes in rapidly urbanizing areas and explored the spatial evolution law and causes of landscape ecological risk evolution in the context of land use changes, with the intention of offering a solid theoretical foundation for such areas’ future planning in developing nations.

Spatiotemporal Modeling of Carbon Fluxes over Complex Underlying Surfaces along the North Shore of Hangzhou Bay

Urban areas contribute to over 80% of carbon dioxide emissions, and considerable efforts are being undertaken to characterize spatiotemporal variations of CO2 (carbon dioxide) at a city, regional, and national level, aiming at providing pipelines for carbon mission reduction. The complex underlying surface composition of urban areas makes process-based and physiology-based models inadequate for simulating carbon flux in this context. In this study, long short-term memory (LSTM), support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were employed to develop and investigate their viability in estimating carbon flux at the ecosystem level. All the data used in our study were derived from the long-term chronosequence observations collected from the flux towers within urban complex underlying surface, along with meteorological reanalysis datasets. To assess the generalization ability of these models, the following statistical metrics were utilized: coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). Our analysis revealed that the RF model performed the best in simulating carbon flux over long time series, with the highest R2 values reaching up to 0.852, and exhibiting the smallest RMSE and MAE values at 0.293 μmol·m−2·s−1 and 0.157 μmol·m−2·s−1. As a result, the RF model was chosen for simulating carbon flux at spatial scale and assessing the impact of urban impervious surfaces in the simulation. The results showed that the RF model performs well in simulating carbon flux at the spatial scale. The input of impervious surface area index can improve the performance of the RF model in simulating carbon flux, with R2 values of 84.46% (with the impervious surface area index in) and 83.74% (without the impervious surface area index in). Furthermore, the carbon flux in Fengxian District, Shanghai, exhibited significant spatial heterogeneity: the CO2 flux in the western part of Fengxian District was less than in the eastern part, and the CO2 flux gradually increased from the west to the east. In addition, we creatively introduced the diurnal impervious surface area index based on the Kljun model, and clarified the influence of impervious surface on the spatiotemporal simulation of CO2 flux over the complex urban underlying surface. Based on these findings, we conclude that the RF models can be effectively applied for estimating carbon flux on the complex underlying urban surface. The results of our study reduce the uncertainty in modeling carbon cycling in terrestrial ecosystems, and make the variety of models for the carbon cycling of terrestrial ecosystems more diverse.

Spatio-temporal differences and simulation studies of the carbon budget from fisheries in the northern marine economic circle of China

With the proposal of dual carbon goals, enhancing carbon sinks and reducing carbon emissions has become a critical issue. Fisheries, as a component of agriculture, possess the dual attributes of being a “carbon sink” (biological carbon fixation) and a “carbon source” (the carbon emissions from fishing vessels). Therefore, it is necessary to assess the carbon sink and carbon emission levels of fisheries. The northern marine economic circle, which includes Liaoning, Hebei, Tianjin, and Shandong, is an important site for fisheries in China, characterized by abundant aquatic resources. However, a comprehensive assessment of the carbon budget for fisheries in this region is still unclear. This study calculated the carbon sinks, carbon emissions, and net carbon emissions associated with fisheries in the region from 2013 to 2020. Additionally, we used sensitivity analysis and scenario simulation to explore the factors influencing the net carbon emissions. The results revealed that the carbon budget of the northern marine economic circle was in a carbon deficit (the amount of carbon emissions was higher than that of carbon sinks) from 2013 to 2020. However, a downward trend in the net carbon emissions was observed, indicating the potential of achieving carbon neutrality. From the perspective of provinces, significant differences among provinces (cities) were found in terms of carbon sinks, carbon emissions, and net carbon emissions, with Shandong having the largest net carbon emissions. Furthermore, the production of clams and the use of seawater trawl net have a significant impact on the net carbon emissions. Increasing the production of clams while reducing the power of trawling operations can significantly decrease net carbon emissions. Based on these results, this study provides relevant suggestions to enhance the carbon sink capacity and decrease the carbon emissions of fisheries in the northern marine economic circle.

Spatiotemporal Simulation of Soil Pb Accumulation Process in Urban-Rural Areas: A Case Study of a Large City in Central China

The high intensity of diverse human activities in urban-rural areas leads to complex soil Pb accumulation processes and high spatiotemporal heterogeneity, making it difficult to reveal the spatiotemporal characteristics of soil Pb accumulation in these areas. This study used a typical urban-rural area in a large city in Central China as the study area, constructed a soil Pb accumulation model, and established a spatiotemporal simulation method for soil Pb accumulation processes combining this model and land use classification and simulation results. Using this method, we simulated the soil Pb content in the study area from 2013 to 2040 and elucidated the future spatiotemporal variation characteristics of soil Pb content. The results showed that the average soil Pb content in the study area in 2013 was approximately 1.77 times the background value of the Pb content in the surface soil of the province where the city is located, indicating significant soil Pb pollution. The soil Pb content was predicted to continue increasing from 2013 to 2040, with relatively low increases (0.53-2.25 mg·kg-1) in the western, northern, and southern parts of the study area, accounting for 25.46 % of the total area, and relatively high increases (3.98-5.70 mg·kg-1) in the eastern part, accounting for 17.14 % of the total area. The increase in the area of forest land and the decrease in the area of water bodies and grassland in the eastern part of the study area led to a substantial rise in soil Pb content in this region; in addition, the spatial distribution of soil Pb content was highly correlated with the distribution of important factories and transportation facilities. This study overcomes the limitations of previous research that treated land use as unchanging and to a certain extent reflects the impact of regional land use changes on the heavy metal accumulation process. It provides a method for simulating the soil Pb accumulation process in urban-rural areas and a basis for controlling soil Pb pollution in the city's urban-rural areas.

Accounting for spatio-temporal and sampling dependence in survey and CPUE biomass indices: simulation and Bayesian modeling framework

Abstract Estimating changes in the biomass of a fish stock is crucial for successful management. However, fishery assessment may be affected by the quality of the inputs used in stock assessment models. Survey biomass indices derived from fishery-independent and catch per unit effort (CPUE) biomass indices derived from fishery-dependent data are key inputs for model calibration. These indices have biases that could compromise the accuracy of the stock assessment models results. Therefore, there are plenty proposed methods to standardize survey or CPUE biomass data. From simpler models like generalized linear models (GLMs) to more complex models that take into account spatio-temporal correlation, like geostatistical models, and sampling dependence, like marked point processes. But many of them do not consider the underlying spatio-temporal or sampling dependence of these data. Hence, the goal of the study is to present a spatio-temporal simulation and Bayesian modeling framework to assess the impact of applying models that do not consider spatio-temporal and sampling dependence. Results indicate that geostatistical models and marked point processes achieve the lowest measures of error. Hence, to capture the underlying spatio-temporal process of the survey and CPUE biomass indices and data sampling preferentiality, it is essential to apply models that consider the spatio-temporal and sampling dependence.

A charge-discharge optimization strategy considering the spatiotemporal distribution of electric vehicles and the operational safety of the power distribution network in the power-transportation coupling network

An electric vehicle (EV) charge-discharge optimization (CDO) strategy that accommodates both grid-side and user-side demands is conducive to mitigating the adverse effects of disordered EV charging on the power distribution network (PDN). To tackle the issue of inaccurate estimation of the schedulable capacity of EVs in existing research, a high temporal resolution dynamic spatiotemporal distribution simulation model for EVs is developed. Furthermore, leveraging the characteristics of the power-transportation coupling network (PTCN), a sub-districted dynamic electricity pricing (DEP) is proposed to assist in improving the PDN node voltage distribution. Subsequently, an incentive coefficient is introduced to incentivize the discharge of EVs during potential peak periods. The proposed CDO strategy, considering the non-cooperative behavior of EV owners (EVOs), can provide personalized charge-discharge plans for them. The temporal sequence experiments reveal a significant decrease in the peak-to-valley disparity of the load, achieving an optimization rate of load mean square error that exceeds 80%. The sub-districted DEP exhibits a significant advantage in maintaining PDN voltage stability compared to traditional time-of-use electricity pricing (TOUEP) and DEP, while also achieving reductions in active power losses of more than 15% and 10% for PDN, respectively. Moreover, in comparison to the conventional scenario, the CDO strategy leads to a maximum reduction of up to 942.5% and 22.3% in the total economic cost for electric private cars and electric taxis respectively. Lastly, the impact of seasonal factors is discussed. Numerical results indicate effective alleviation of load peak-valley differences, load fluctuations, and voltage drop phenomena in both winter and summer. Additionally, the maximum reduction in active power losses reaches 20.1% and 21.9%, respectively, while the total economic cost for EVOs participating in the CDO strategy is reduced by up to 97.7% and 114.7%.

Physics-constrained and flow-field-message-informed graph neural network for solving unsteady compressible flows

With the increasing use of deep neural networks as surrogate models for accelerating computational simulations in mechanics, the application of artificial intelligence in computational fluid dynamics has seen renewed interest in recent years. However, the application of deep neural networks for flow simulations has mainly concentrated on relatively simple cases of incompressible flows. The strongly discontinuous structures that appear in compressible flows dominated by convection, such as shock waves, introduce significant challenges when approximating the nonlinear solutions or governing equations. In this work, we propose a novel physics-constrained, flow-field-message-informed (FFMI) graph neural network for spatiotemporal flow simulations of compressible flows involving strong discontinuities. To enhance the nonlinear approximation capability of strong discontinuities, a shock detector method is leveraged to extract the local flow-field messages. These messages are embedded into the graph representation to resolve the discontinuous solutions accurately. A new FFMI sample-and-aggregate-based message-passing layer, which aggregates the edge-weighted attributes with node features on different hop layers, is then developed to diffuse and process the flow-field messages. Furthermore, an end-to-end paradigm is established within the encoder–decoder framework to transform the extracted information from the flow field into latent knowledge about the underlying fluid mechanics. Finally, a variety of one- and two-dimensional cases involving strong shock waves are considered to demonstrate the effectiveness and generalizability of the proposed FFMI graph neural network.

Quick large-scale spatiotemporal flood inundation computation using integrated Encoder-Decoder LSTM with time distributed spatial output models

Accurate spatiotemporal flood simulations are essential for making informed decisions regarding flood release in affected regions, such as flood detention areas. Traditional spatiotemporal flood simulation approach uses partial differential equation (PDE) models (or physics-based models), which need high computational time. Although many machine learning (ML) models for inundation are increasingly being used to emulate the PDE models to address this issue, utilizing conventional ML models to achieve large-scale spatiotemporal flood prediction (i.e., simulation output in tens of thousands of grids and time steps over the whole flood event) remains a significant challenge. Therefore, we developed a new inundation model (IM) using encoder-decoder long short-term memory (ED-LSTM) with Time Distributed Spatial output model (ED-LSTM-TDS) that can acquire accurate spatially distributed flood information more rapidly. In the new IM framework, each ED-LSTM-TDS is built to simultaneously generate output for multiple (K) cell grids and multiple ED-LSTM-TDS models are built for prediction at all grids of entire PDE model. This study is the first of its kind to employ the ED-LSTM-TDS method to address spatiotemporal flood inundation simulation problems for flood detention areas. A 1994 km2 flood detention area in northeastern China was used as a case study. ED-LSTM-TDS exhibited better performance in predicting flood characteristics (e.g., water depth, velocity) than alternative methods, including ordinary LSTM, artificial neural network (ANN), and multiple linear regression (MLR). In addition, we investigated the trade-off relationship between the accuracy of flood characteristic prediction and the computation time of the proposed model by considering different numbers of K cell grids in each ED-LSTM-TDS model. The final proposed inundation model could accurately predict the spatiotemporal flood characteristics within 1.5 min to acquire the same information that required approximately 1 h by the PDE models. Such rapid and accurate prediction by the proposed model is important for evacuation planning, upstream flood control decisions and flood damage reduction.