Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation

Next point-of-interest(POI)recommendation is an important personalized task in location-based social networks(LBSNs)and aims to recommend the next POI for users in a specific situation with historical check-in data.State-of-the-art studies linearly discretize the user’s spatiotemporal information and then use recurrent neural network(RNN)based models for modeling.However,these studies ignore the nonlinear effects of spatiotemporal information on user preferences and spatiotemporal correlations between user trajectories and candidate POIs.To address these limitations,a spatiotemporal trajectory(STT)model is proposed in this paper.We use the long short-term memory(LSTM)model with an attention mechanism as the basic framework and introduce the user’s spatiotemporal information into the model in encoding.In the process of encoding information,an exponential decay factor is applied to reflect the nonlinear drift of user interest over time and distance.In addition,we design a spatiotemporal matching module in the process of recalling the target to select the most relevant POI by measuring the relevance between the user’s current trajectory and the candidate set.We evaluate the performance of our STT model with four real-world datasets.Experimental results show that our model outperforms existing state-of-the-art methods.

Driving factors and spatiotemporal effects of environmental stress in urban agglomeration: Evidence from the Beijing-Tianjin-Hebei region of China

Environmental stress is used as an indicator of the overall pressure on regional environmental systems caused by the output of various pollutants as a result of human activities. Based on the pollutant emissions and socioeconomic databases of the counties in Beijing–Tianjin–Hebei region, this paper comprehensively calculates the environmental stress index(ESI) for the urban agglomeration using the entropy weight method(EWM) at the county scale and analyzes the spatiotemporal patterns and the differences among the four types of major functional zones(MFZ) for the period 2012–2016. In addition, the socioeconomic driving forces of environmental stress are quantitatively estimated using the geographically weighted regression(GWR) method based on the STIRPAT model framework. The results show that:(1) The level of environmental stress in the Beijing–Tianjin–Hebei region was significantly alleviated during that time period, with a decrease in ESI of 54.68% by 2016. This decrease was most significant in Beijing, Tangshan, Tianjin, Shijiazhuang, and other central urban areas, as well as the Binhai New Area. The level of environmental stress in counties decreased gradually from the central urban areas to the suburban areas, and the high-level stress counties were eliminated by 2016.(2) The spatial spillover effect of environmental stress increased further at the county scale from 2012 to 2016, and spatial locking and path dependence emerged in the cities of Tangshan and Tianjin.(3) Urbanized zones(development-optimized and development-prioritized zones) were the major areas bearing environmental pollution in the Beijing–Tianjin–Hebei region in that time period. The ESI accounted for 65.98% of the whole region, where there was a need to focus on the prevention and control of environmental pollution.(4) The driving factors of environmental stress at the county scale included population size and the level of economic development. In addition, the technical capacity of environmental waste disposal, the intensity of agricultural production input, the intensity of territorial development, and the level of urbanization also had a certain degree of influence.(5) There was spatial heterogeneity in the effects of the various driving factors on the level of environmental stress. Thus, it was necessary to adopt differentiated environmental governance and reduction countermeasures in respect of emission sources, according to the intensity and spatiotemporal differences in the driving forces in order to improve the accuracy and adaptability of environmental collaborative control in the Beijing–Tianjin–Hebei region.

Tree-Fall Gaps Effects on Spider(Araneae)Assemblages in an Atlantic Forest Landscape in Northeastern Brazil

The study investigates the effect of spatial and temporal tree-fall gaps structure on spiders’ assemblage in an Atlantic forest fragmented area in Brazil. It was conducted in the Michelin Ecological Preserve-REM (Bahia), 190 ha forest remnant. Samples were collected on leaf-litter (50 × 50 cm) at five tree-fall gaps formations (2), within five adjacent primary forest and five inner edge parcels. During 16 months (between May 2009 and October 2012), 480 m2 leaf-litter samples were collected, from which spiders were extracted using mini-Winkler traps. The observed and estimated richness of spider’s species was higher at the edge

The spatiotemporal scale effect on vegetation interannual trend estimates based on satellite products over Qinghai-Tibet Plateau

The trend estimate of vegetation change is essential to understand the change rule of the ecosystem.Previous studies were mainly focused on quantifying trends or analyzing their spatial distribution characteristics.Nevertheless,the uncertainties of trend estimates caused by spatiotemporal scale effects have rarely been studied.In response to this challenge,this study aims to investigate spatiotemporal scale effects on trend estimates using Moderate-Resolution Imaging Spectroradiometer(MODIS)Normalized Difference Vegetation Index(NDVI)and Gross Primary Productivity(GPP)products from 2001 to 2019 in the Qinghai-Tibet Plateau(QTP).Moreover,the possible influencing factors on spatiotemporal scale effect,including spatial heterogeneity,topography,and vegetation types,were explored.The results indicate that the spatial scale effect depends more on the dataset with a coarser spatial resolution,and temporal scale effects depend on the time span of datasets.Unexpectedly,the trend estimates on the 8-day and yearly scale are much closer than that on the monthly scale.In addition,in areas with low spatial heterogeneity,low topography variability,and sparse vegetation,the spatiotemporal scale effect can be ignored,and vice versa.The results in this study help deepen the consciousness and understanding of spatiotemporal scale effects on trend detection.

The Apollon 10 PW laser: experimental and theoretical investigation of the temporal characteristics

The objective of the Apollon 10 PW project is the generation of 10 PW peak power pulses of 15 fs at 1 shot min^(-1). In this paper a brief update on the current status of the Apollon project is presented, followed by a more detailed presentation of our experimental and theoretical investigations of the temporal characteristics of the laser. More specifically the design considerations as well as the technological and physical limitations to achieve the intended pulse duration and contrast are discussed.