Geographic modeling and simulation systems for geographic research in the new era: Some thoughts on their development and construction

Advancing river flood forecasting with a collaborative integrated modeling method

River flood forecasting and assessment are crucial for reducing flood risks, as they offer early alerts and allow for proactive actions to safeguard individuals from possible flood-related damage. Effective modeling in this field often multiple interconnected aspects of the hydrologic cycle, such as precipitation, infiltration, runoff, and evaporation, requiring collaboration among hydrology experts. Such collaboration enables experts to handle and manage their specialized processes more effectively, thereby enhancing the efficiency of the development of integrated flood forecasting models. Tight integration and loose integration are two common strategies for integrating different hydrologic cycle process models in river flood forecasting. However, most integration strategies rely on centralized models, necessitating experts to configure models and data on local computers. Currently, there is a deficiency in the capacity for effective collaboration in the integrated modeling of river flood forecasts. This issue arises from multiple obstacles: the complexity of understanding heterogeneous data and hydrologic cycle process models; the difficulty of integrating models with diverse runtime environments; and the challenge of synchronizing forecasting model changes among experts in real time. Therefore, we propose a web-based collaborative integrated modeling method, designed to support both tightly and loosely integrated modes, to enhance collaborative river flood forecasting and assessment. This method includes three core modules: (1) data and model description for providing a structured description of the execution logic of forecasting models and the internal structure of forecast data for expert understanding; (2) model access and integration for access and integration of data and multi-source heterogeneous models of hydrologic cycle processes; and (3) modeling scenario configuration for collaborative development of forecasting models and the execution of simulation tasks. Finally, we illustrate the application of the proposed method by utilizing the GEFS v12 (Global Ensemble Forecast System) rainfall ensemble forecasting dataset with the CREST (Coupled Routing and Excess STorage) hydrologic model. The results show enhanced efficiency in the collaborative development of river flood forecasts by hydrology experts, particularly in model accessibility, data processing, simulation, and evaluation, thereby potentially aiding decision-making.

Artificial intelligence for geoscience: Progress, challenges, and perspectives

This paper explores the evolution of geoscientific inquiry, tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence (AI) and data collection techniques. Traditional models, which are grounded in physical and numerical frameworks, provide robust explanations by explicitly reconstructing underlying physical processes. However, their limitations in comprehensively capturing Earth's complexities and uncertainties pose challenges in optimization and real-world applicability. In contrast, contemporary data-driven models, particularly those utilizing machine learning (ML) and deep learning (DL), leverage extensive geoscience data to glean insights without requiring exhaustive theoretical knowledge. ML techniques have shown promise in addressing Earth science-related questions. Nevertheless, challenges such as data scarcity, computational demands, data privacy concerns, and the "black-box" nature of AI models hinder their seamless integration into geoscience. The integration of physics-based and data-driven methodologies into hybrid models presents an alternative paradigm. These models, which incorporate domain knowledge to guide AI methodologies, demonstrate enhanced efficiency and performance with reduced training data requirements. This review provides a comprehensive overview of geoscientific research paradigms, emphasizing untapped opportunities at the intersection of advanced AI techniques and geoscience. It examines major methodologies, showcases advances in large-scale models, and discusses the challenges and prospects that will shape the future landscape of AI in geoscience. The paper outlines a dynamic field ripe with possibilities, poised to unlock new understandings of Earth's complexities and further advance geoscience exploration.

Promoting forest landscape dynamic prediction with an online collaborative strategy

Modeling and predicting forest landscape dynamics are crucial for forest management and policy making, especially under the context of climate change and increased severities of disturbances. As forest landscapes change rapidly due to a variety of anthropogenic and natural factors, accurately and efficiently predicting forest dynamics requires the collaboration and synthesis of domain knowledge and experience from geographically dispersed experts. Owing to advanced web techniques, such collaboration can now be achieved to a certain extent, for example, discussion about modeling methods, consultation for model use, and surveying for stakeholders' feedback can be conducted on the web. However, a research gap remains in terms of how to facilitate online joint actions in the core task of forest landscape modeling by overcoming the challenges from decentralized and heterogeneous data, offline model computation modes, complex simulation scenarios, and exploratory modeling processes. Therefore, we propose an online collaborative strategy to enable collaborative forest landscape dynamic prediction with four core modules, namely data preparation, forest landscape model (FLM) computation, simulation scenario configuration, and process organization. These four modules are designed to support: (1) voluntary data collection and online processing, (2) online synchronous use of FLMs, (3) collaborative simulation scenario design, altering, and execution, and (4) participatory modeling process customization and coordination. We used the LANDIS-II model as a representative FLM to demonstrate the online collaborative strategy for predicting the dynamics of forest aboveground biomass. The results showed that the online collaboration strategy effectively promoted forest landscape dynamic prediction in data preparation, scenario configuration, and task arrangement, thus supporting forest-related decision making.

Future land-use change and its impact on terrestrial ecosystem carbon pool evolution along the Silk Road under SDG scenarios

Sustainable development goals (SDGs) in the United Nations 2030 Agenda call for action by all nations to promote economic prosperity while protecting the planet. Projection of future land-use change under SDG scenarios is a new attempt to scientifically achieve the SDGs. Herein, we proposed four scenario assumptions based on the SDGs, including the sustainable economy (ECO), sustainable grain (GRA), sustainable environment (ENV), and reference (REF) scenarios. We forecasted land-use change along the Silk Road (resolution: 300 m) and compared the impacts of urban expansion and forest conversion on terrestrial carbon pools. There were significant differences in future land use change and carbon stocks, under the four SDG scenarios, by 2030. In the ENV scenario, the trend of decreasing forest land was mitigated, and forest carbon stocks in China increased by approximately 0.60% compared to 2020. In the GRA scenario, the decreasing rate of cultivated land area has slowed down. Cultivated land area in South and Southeast Asia only shows an increasing trend in the GRA scenario, while it shows a decreasing trend in other SDG scenarios. The ECO scenario showed highest carbon losses associated with increased urban expansion. The study enhances our understanding of how SDGs can contribute to mitigate future environmental degradation via accurate simulations that can be applied on a global scale.

Prediction for Origin-Destination Distribution of Dockless Shared Bicycles: A Case Study in Nanjing City

Shared bicycles are currently widely welcomed by the public due to their flexibility and convenience; they also help reduce chemical emissions and improve public health by encouraging people to engage in physical activities. However, during their development process, the imbalance between the supply and demand of shared bicycles has restricted the public's willingness to use them. Thus, it is necessary to forecast the demand for shared bicycles in different urban regions. This article presents a prediction model called QPSO-LSTM for the origin and destination (OD) distribution of shared bicycles by combining long short-term memory (LSTM) and quantum particle swarm optimization (QPSO). LSTM is a special type of recurrent neural network (RNN) that solves the long-term dependence problem existing in the general RNN, and is suitable for processing and predicting important events with very long intervals and delays in time series. QPSO is an important swarm intelligence algorithm that solves the optimization problem by simulating the process of birds searching for food. In the QPSO-LSTM model, LSTM is applied to predict the OD numbers. QPSO is used to optimize the LSTM for a problem involving a large number of hyperparameters, and the optimal combination of hyperparameters is quickly determined. Taking Nanjing as an example, the prediction model is applied to two typical areas, and the number of bicycles needed per hour in a future day is predicted. QPSO-LSTM can effectively learn the cycle regularity of the change in bicycle OD quantity. Finally, the QPSO-LSTM model is compared with the autoregressive integrated moving average model (ARIMA), back propagation (BP), and recurrent neural networks (RNNs). This shows that the QPSO-LSTM prediction result is more accurate.

An online participatory system for SWMM-based flood modeling and simulation

In the context of the continuous development of urbanization and global climate change, urban flooding risk has become a well-publicized research issue. The Storm Water Management Model (SWMM) performs very well in urban rain-runoff simulations and is widely used to build flood models in specific areas. Because of the complicated and tedious processing work for urban flood modeling and simulation, multifield participants' cooperation is becoming a trend. To promote the research and application of flood modeling and simulation, some resource sharing-oriented systems and platforms have been proposed with the advantages of network technology. However, they still require a participatory environment that can help modeling participants overcome the difficulties of distributed cooperation in the process of SWMM-based flood modeling and simulation. Therefore, we designed and implemented an online participatory system to coordinate the effective collaboration of modeling participants in this process. By referring to the scenarios and specific participatory demands in the modeling process, the system provides a guiding framework that consists of multiple participatory activities and prepares a series of online auxiliary tools designed for these activities. Using the main urban area of Lishui City as the study area, it was confirmed that the process of SWMM-based flood modeling and simulation can be demonstrated collaboratively on the online participatory system developed in this study.

A Barotropic Tide Model for Global Ocean Based on Rotated Spherical Longitude-Latitude Grids

Ocean modeling and simulation are important for understanding the dynamic processes in the geophysical system, and the simulation of tidal dynamics is of great significance for understanding the dynamic evolution of the ocean. However, there are some problems in existing simulations, including lack of specific standards to produce a desirable discrete spherical mesh for global ocean modelling. Many global ocean numerical models based on conventional longitude-latitude (LL) coordinates suffer from the “pole problem” in regions adjacent to the North Pole due to the convergence of meridians, which seriously hinders global ocean simulations. In this paper, a new longitude-latitude spherical grid coupled with rotated coordinate mapping is proposed to overcome the problem. In the design of the numerical model, for spatial approximation, the finite volume method on staggered C grid is proposed to solve the two-dimensional tidal wave equations for the global ocean. For temporal integration, the third-order Adams-Bashforth method is used to explicitly extrapolate the value on the next time interval half layer, and then the fourth-order implicit Adams-Moulton method is used to correct the water level. Finally, the constructed model is used to simulate the dynamics of two-dimensional tidal waves in the global ocean, and the co-tidal maps of two major diurnal tide and semidiurnal tide components are shown. The results demonstrate that the proposed model can support the simulation of tidal dynamics in the global ocean, especially for the Arctic Ocean.