Predictive Process Monitoring (PPM) aims to predict the future states of ongoing process instances. A primary objective is to accurately predict process outcomes while ensuring decision transparency, which is critical for enhancing process efficiency and reducing operational risk. Existing interpretable approaches to process monitoring often struggle with balancing transparency and reliability. Specifically, approaches that prioritize transparency often fall short in predictive accuracy and generalization, while those that achieve higher prediction performance often provide less reliable explanations. To address these limitations, we propose a novel Transparent Process Outcome Prediction framework (TPOP) using a graph neural network with stochastic attention. We begin by applying a SHAP-based feature selection technique to identify and extract the most relevant attributes from the log, thereby improving the quality of graph-based process representations. Next, we introduce a graph stochastic attention mechanism, which helps the model in concentrate on key paths and activities during training, leading to transparent and trustworthy predictions. Experimental evaluations on ten real-life event logs demonstrate that our approach outperforms state-of-the-art approaches in both predictive performance and interpretability. Furthermore, by visualizing how specific activities influence process outcomes across various cases, we confirm the reliability of the explanations generated by our approach.

A flood evacuation represents a complex geographic phenomenon that includes comprehensive interactions among humans, the flood and urban environments; thus, the simulation of flood evacuations requires crowd simulation models to be coupled with flood models. This paper studies the human-environment relationship during flooding and promotes a simulation model that combines cellular automata and a multiagent system to simulate crowd evacuations in flood disasters. A case study of Niaodao Island was used to evaluate the performance of flood evacuation experiments, and real-participant experiments based on the virtual reality (VR) environment were employed for bench-mark comparisons. The integrated model can provide a comprehensive solution to assist flood risk analysis.

Oblique airborne photogrammetry-based three-dimensional (3D) city model (OAP3D) provides a spatially continuous representation of urban landscapes that encompasses buildings, road networks, trees, bushes, water bodies, and topographic features. OAP3D is usually present in the form of a group of unclassified triangular meshes under a multi-resolution data structure. Modifying such a non-separable landscape constitutes a daunting task because manual mesh editing is normally required. In this paper, we present a systematic approach for easily embedding user-generated content into OAP3D. We reduce the complexity of OAP3D modification from a 3D mesh operation to a two-dimensional (2D) raster operation through the following workflow: (1) A region of interest (ROI) is selected to cover the area that is intended to be modified for accommodating user-defined content. (2) Spatial interpolation using a set of manually controlled elevation samples is employed to generate a user-defined digital surface model (DSM), which is used to reform the ROI surface. (3) User-generated objects, for example, artistically painted road textures, procedurally generated water effects, and manually created 3D building models, are overlaid onto the reformed ROI.

It is difficult to obtain accurate simulation results without observation data. So using real-time dynamic observation data in the simulation process has become an academic frontier of international research. This paper is a probing research on the data-driven adaptive modeling and automatic refactoring methods of flood routing simulation. A cellular automata (CA) data-driven flooding model was developed using the Hunhe River in Shenyang City as a case study. The proposed model can increase the accuracy of simulations by calculating differences in the water stages using high temporal resolution observational data. Meanwhile, corresponding parameter analysis was carried out based on the proposed CA model and the best lagging time between simulation and observation was discussed.

The temporal and spatial distribution of solar energy in urban areas is highly variable because of the complex building structures present. Traditional GIS-based solar radiation models rely on two-dimensional (2D) digital elevation models to calculate insolation, without considering building facades and complicated three-dimensional (3D) shading effects. Inspired by the ‘texture baking’ technique used in computer graphics, we propose a full 3D method for computing and visualizing urban solar radiation based on image-space data representation. First, a surface mapping approach is employed to project each 3D triangular mesh onto a 2D raster surface whose cell size determines the calculation accuracy. Second, the positions and surface normal vectors of each 3D triangular mesh are rasterized onto the associated 2D raster using barycentric interpolation techniques. An efficient compute unified device architecture -accelerated shadow-casting algorithm is presented to accurately capture shading effects for large-scale 3D urban models. Solar radiation is calculated for each raster cell based on the input raster layers containing such information as slope, aspect, and shadow masks. Finally, a resulting insolation raster layer is produced for each triangular mesh and is represented as an RGB texture map using a color ramp. Because a virtual city can be composed of tens of thousands of triangular meshes and texture maps, a texture atlas technique is presented to merge thousands of small images into a single large image to batch draw calls and thereby efficiently render a large number of textured meshes on the graphics processing unit.

Chapinghe Barrier Lake was the largest among the barrier lakes formed in the aftermath of the magnitude 5.12 Wenchuan Earthquake. A rapid quantitative method for the evaluation of potential risk to lives and properties downstream was of the utmost importance for disaster management. The proposed method is based on spatiotemporal simulation using different dam-break scenarios and downstream hazard distribution analyses. This article adopts a cellular automata (CA) model to synthetically integrate multiple sets of geographic layers, including those containing the models needed for routine computation of flood hazards and those needed for vulnerability analysis of the people living downstream. A CA-based simulation and analysis method integrating hydrologic/hydraulic mechanisms is herein introduced, and relevant techniques are investigated. Our prototype experiment demonstrates that the proposed CA-based flood-hazard model can be conveniently integrated into a digital earth system and can further provide real-time simulation analyses of dam-break flood risks.

Cholera is an infectious disease, which begins abruptly, spreads fast, influences a wide range and is easy to outbreak, but traditional way of monitoring epidemic trends of cholera is of lag because of the incubation period and period from treatment to diagnosis. In order to improve cholerae surveillance and to show early warning of cholera epidemic in time, a growth and reproduction model of vibrio cholera based on improved Cellular Automata Model, is created and verified. According to the model, diffusion of vibrio cholera in river is simulated, integrated with multi-source data including remote sensing inversion data, hydro-geomorphological data, basic geographical data, monitored environmental data and monitored bacteria data.

To improve the efficiency of planning and designing silt dam systems, this article employs theories and technologies of collaboration and distributed virtual geographic environments (VGEs) to construct a collaborative virtual geographic environment (CVGE) system. The CVGE system provides geographically distributed users with a shared virtual space and a collaborative platform to implement collaborative planning. Many difficulties have been found in integrating data resources and model procedures for the planning of silt dam systems because of their diversity in heterogeneous environments. Unlike most of the current distributed system applications, the proposed CVGE system not only supports multi-platform and multi-program-language interoperability in the dynamically changing network environment, but also shares programs, data and software in the collaborative environment. Based on creating a shared 3D space by virtual reality technology, agent and grid technologies were tightly coupled to develop the CVGE system. A grid-based multi-agent system service framework was designed to implement this new paradigm for the CVGE system, which efficiently integrates and shares geographically distributed resources as well as having the ability to build modelling procedures on different platforms. At the same time, mobile agent computing services were implemented to reduce the network load, process parallel tasks, enhance communication efficiency and adapt dynamically to the changing network environment. Using Java, JMF (Java Media Framework API), Globus Toolkits (GT) core, Voyager, C++, and the OpenGL development package, a prototype system was developed to support silt dam systems planning in the case study area, the Jiu-Yuan-Gou watershed of the Loess Plateau, China. Compared with the traditional workflow, the CVGE system can reduce the workload by between one third and a half.

In order to integrate kinds of data, models and applications in virtual geography environment (VGE), we propose the grid-VGE based on the technology of grid. With regard to the specific applications of grid-VGE, the tasks submitted by users can be divided into several sorts, such as science computing, I/O species, data management, simulating and modeling. With the development of VGE, more and more applications will join the grid-VGE, but they may not belong to any species that has been listed up. Of course, many tasks may be covered by several species. When a user submits a complex and onerous task, the task needs to be decompounded to assign to different locations for implementation. Based on the theoretic of Bernstein by layer upon layer, we decompose the task into many sub-tasks, which will be distributed to certain nodes based on the upper capability hierarchy. And these sub-tasks will cooperate to complete the whole task. In an addition, a status-word will be added to every sub-task which is used to record the status of the sub-task implementation. In the last, we will give an example. The user can ramble and interact with each other in the three-dimension visional scene and can use kinds of peripheral equipments to hence the sense of immersion and interact each other in real time. The experiment results show that decomposition and distribution of tasks regarding grid-VGE are correct and effective for the cooperative implementation of the tasks.

As a development in geography and geographic information science, virtual geographic environment (VGE) embodies abstract concepts, makes people immerge in the virtual world, studies the geography problems, and carries out geographic examinations. VGE has plenty of multi-kinds of data, such as digital elevation model data, data of objects under and on the Earth surface, image data, audio data, video data, avatar movement data, interaction data, environment data, and so on. VGE data can be classified as dynamic data and static data according to data changing. At the same time, VGE data can also be classified into global data and local data with an eye to data using range. According to VGE data attributes and its classifications, we design a VGE database, which fits VGE's three main contents: virtual geographic environment construction, entities construction and the interaction between environment and entities. There has a global database to store global data and several local databases to store their region data. The database is also distributed, so we study a method and an architecture to solve the database collaboration. We call the method "pre-data-preparing". In the end, we give an example of DEM database collaboration of GuanTing lake located in the west of Beijing.

A geographic information services grid (GISG) is an open frame and software system based on grid for discovering, sharing, processing, integrating multi-source and heterogeneous geographic information, and conducting collaborative work. At present, many technologies are introduced and applied to implement sharing, integration and collaboration of geographic information, of which grid computing technology, OpenGIS, and Web services are the most important ones. In this paper, we aim to utilize Open GIS specification and Web services technology to design the architecture of GISG according to OGSA. Specially, GI services are taken as the GISG's center. Based on GISG, we develop designa framework for establish the public health management and disease control system.