Search

The rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stability of transportation path is an important part of port operation and management, and it is one of the basic tasks to build an intelligent port. Existing research mainly focuses on collaborative operation between port equipment and path optimization under environmental perception, while there is relatively little research on optimization of path smoothness and safety. Therefore, we propose a path optimization model based on the artificial potential field and twin delayed deep deterministic policy gradient (APF-TD3) framework for the port environment. Firstly, we obtain the scheduling task plan of a single AGV by enumeration. Secondly, according to the artificial potential field (APF) algorithm to generate repulsion for obstacles in the harbor and attraction for container storage at the target point with the position information of the AGV as the input data of the reinforcement learning algorithm is inputted into the twin delayed deep deterministic policy gradient algorithm (TD3). Then TD3 selects the optimal action strategy for the AGV according to the input AGV state information and the designed reward mechanism as well as executes the action. Through repeated execution, the optimal action for the next step is selected at each point to generate a path with start and end points. We validate the model by simulating the scale of containerized cargo in the port i.e. small scale, medium scale and large scale scenes. The experimental results show that the method has the shortest path length of 27.519 m, 270.847 m, and 496.389 m compared to artificial potential field and deep deterministic policy gradient (APF-DDPG), APF, and rapidly-exploring random tree (RRT) algorithms, which also have significant advantages in terms of path security and path smoothness. This framework could respond to the scheduling and transportation tasks of single AGV in different environmental layouts and guarantee the smoothness and safety of the path based on the optimization of the path, which promotes the efficient operation and management of ports. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping is vital for landslide risk management and urban planning. In this study, we used three statistical models [frequency ratio, certainty factor and index of entropy (IOE)] and a machine learning model [random forest (RF)] for landslide susceptibility mapping in Wanzhou County, China. First, a landslide inventory map was prepared using earlier geotechnical investigation reports, aerial images, and field surveys. Then, the redundant factors were excluded from the initial fourteen landslide causal factors via factor correlation analysis. To determine the most effective causal factors, landslide susceptibility evaluations were performed based on four cases with different combinations of factors ("cases"). In the analysis, 465 (70%) landslide locations were randomly selected for model training, and 200 (30%) landslide locations were selected for verification. The results showed that case 3 produced the best performance for the statistical models and that case 2 produced the best performance for the RF model. Finally, the receiver operating characteristic (ROC) curve was used to verify the accuracy of each model's results for its respective optimal case. The ROC curve analysis showed that the machine learning model performed better than the other three models, and among the three statistical models, the IOE model with weight coefficients was superior. [ABSTRACT FROM AUTHOR]

One of the major challenges of species distribution models (SDMs) is incorporating the influence of prey on the predator. An ensemble modeling approach, the prey-predator species distributabion model (PPSDM), uses environmental variables (sea surface temperature, bathymetry, sea surface salinity, and sea surface current) and a biotic variable (predicted prey distribution: Japanese anchovy) to predict a piscivorous fish (Japanese Spanish mackerel) habitat in the China Seas. PPSDM comprised selected preferable single algorithms from nine algorithms, including tree-based models, machine learning models, regression models, an envelope-style method, and a classification model. Compared with that obtained when using habitat without the Japanese anchovy distribution, the regression models, machine learning models and a classification model have significant improvements. However, tree-based models have only slightly improved. The PPSDM results well reflected the ontogenetic migration of Japanese Spanish mackerel. We found that the wintering ground was distributed in regions with temperatures between 11 and 17 °C and salinities between 33.6 and 34.1. The bottom topography was also closely correlated with Japanese Spanish mackerel, and the suitable habitat was at 50–100 m isobaths as topography determined the position of isotherms (11, 17 °C), salinity isolines (33.6, 34.1), and fronts (temperature, salinity) in winter. The relationships among different climatic indices, temperature, and Japanese Spanish mackerel were analyzed. We found that the East Asian monsoon significantly influenced the Japanese Spanish mackerel habitat by affecting temperature variation. In the future, the suitable habitat of Japanese Spanish mackerel is projected to decrease by 21%, 28%, 36%, and 42% under RCP2.6, RCP4.5, RCP6.0, and RCP8.5, respectively. The Japanese Spanish mackerel in the northern Yellow Sea is projected to experience the 'cul de sac' effect, which would drive this species toward local extinction. The Japanese Spanish mackerel in the China Seas will probably shift northeastward through the Tsushima Strait, and the Sea of Japan may form the main habitat at the end of the century. • Prey-predator species distribution model (PPSDM) was developed by an ensemble model. • The prediction accuracy of predator distribution was improved by PPSDM with prey. • Spanish mackerel is closely related with temperature and salinity isolines in winter. • Spanish mackerel experience a 'cul de sac' effect in the northern Yellow Sea. • Spanish mackerel suitable habitat was projected to shrink by 21–42% in the future. [ABSTRACT FROM AUTHOR]