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.

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.

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

Regionality, comprehensiveness, and complexity are regarded as the basic characteristics of geography. The exploration of their core connotations is an essential way to achieve breakthroughs in geography in the new era. This paper focuses on the important method in geographic research: Geographic modeling and simulation. First, we clarify the research requirements of the said three characteristics of geography and its potential to address geo-problems in the new era. Then, the supporting capabilities of the existing geographic modeling and simulation systems for geographic research are summarized from three perspectives: Model resources, modeling processes, and operational architecture. Finally, we discern avenues for future research of geographic modeling and simulation systems for the study of regional, comprehensive and complex characteristics of geography. Based on these analyses, we propose implementation architecture of geographic modeling and simulation systems and discuss the module composition and functional realization, which could provide theoretical and technical support for geographic modeling and simulation systems to better serve the development of geography in the new era.