Historical AIS Data-Driven Unsupervised Automatic Extraction of Directional Maritime Traffic Networks
استخراج خودکار بدون نظارت داده های AIS از شبکه های ترافیکی دریایی جهت دار-2020
Vessel experience route analysis can provide empirical support for maritime traffic management. Recently, the application of the Automatic Identification System (AIS) provides multi-dimensional data about voyages and vessels. However, traditional route extraction methods do not take into account information such as the vessel traffic pattern and the density distribution in the channel. The experience routes obtained is not accurate enough. This paper proposes an unsupervised method for extracting vessel experience routes from historical AIS data. The method consists of three parts: vessel traffic pattern extraction, channel boundary extraction, channel triangle network construction and hottest route extraction. The method comprehensively considers the spatiotemporal information and density distribution of the vessel trajectories, and constructs a directional maritime traffic network which can effectively convert historical data into information supporting decision-making.
Keywords : AIS | Traffic Pattern | Triangular Network | Directional Maritime Traffic Network
AI Down on the Farm
هوش مصنوعی کوچک در مزرعه-2020
Agriculture has become an information-intensive industry. In the production of crops and animals, precision agriculture approaches have resulted in the collection of spatially and temporally dense datasets by farmers and agricultural researchers. These big datasets, often characterized by extensive nonlinearities and interactions, are often best analyzed using machine learning (ML) or other artificial intelligence (AI) approaches. In this article, we review several case studies where ML has been used to model aspects of agricultural production systems and provide information useful for farm-level management decisions. These studies include modeling animal feeding behavior as a predictor of stress or disease, providing information important for developing precise and efficient irrigation systems, and enhancing tools used to recommend optimum levels of nitrogen fertilization for corn. Taken together, these examples represent the current abilities and future potential for AI applications in agricultural production systems.
Projection of spatiotemporal variability of wave power in the Persian Gulf by the end of 21st century: GCM and CORDEX ensemble
پیش بینی تغییر پذیری مکانی و قدرت موج در خلیج فارس تا پایان قرن بیست و یکم: GCM و CORDEX-2020
This study investigates future variability of wave power in the Persian Gulf. The contribution of this paper is twofold: (a) to evaluate spatiotemporal resolutions, downscaling techniques and global circulation model (GCM) selection impacts running multi-climate models, and (b) to project wave energy resources and its variability by the end of 21st century using RCP4.5 and RCP8.5 as two different representative concentration pathways (RCPs). The SWAN (Simulating Waves Nearshore) model forcing with near surface wind components was employed for wave simulation. The numerical wave model was calibrated and validated using wave measurements by two buoys prior to wave energy computations. The results of wave models obtained from different climate models showed a wide range of variety for different climatic resources associated with GCM selection, temporal and spatial resolutions and downscaling approach. Outputs of the wave model forcing with 3 hourly wind data of CMCC-CM and CORDEX-MPI (Max Plank Institute) with daily temporal resolution were recognized as the models with the best performance. Using a weighted average of these two models, the wave characteristics were obtained and wave energy were computed for the historical and future periods. Temporal distribution of energy shows highly intra-annual and seasonal variability when the mean wave power for the strongest month exceeds 1000Watt per meter that is 10 times higher than the mean wave power in the weakest month. Similarly, a strong spatial variability in wave power distributionwas revealed where the middle part of the Gulf has found to have the highest energy and the eastern and northwestern regions have the lowest energy. The projections illustrated a decreasing trend on future wave energy up to 40% in the Iranian coastlines and lower rate of changes in the southern stripe of the study area.
Keywords: Renewable energy | Climate change | CORDEX | Representative concentration pathways | Energy management
Identifying the terrestrial carbon benefits from ecosystem restoration in ecologically fragile regions
شناسایی فواید کربن زمینی از ترمیم اکوسیستم در مناطق شکننده محیط زیست-2020
Ecosystem restoration is an urgent and vital measure to restore degraded land in ecologically fragile regions. The terrestrial carbon sequestration capacity is important to indicate the effectiveness of ecosystem restoration, which has attracted the interest of many researchers. Ecologically fragile regions cover a large area in China, but few studies have focused on the carbon benefit of ecological restoration in these regions. In this study, we investigated the spatial and temporal changes in the carbon benefit, indicated by net primary productivity (NPP), in ecologically fragile regions in China. We evaluated the contributions of ecological restoration and climate change to terrestrial ecosystem carbon sink changes. The results showed that the ecological restoration projects significantly improved the carbon sequestration capacity in most of the ecologically fragile regions. From 2001–2017, the annual NPP of the entire study region was 460.1±5.4 Tg C yr−1, and more than 70 % of the ecologically fragile region experiencing a significant (p<0.05) increase. The effect of ecological restoration projects significantly intensified and was the main driver of the NPP growth in 87 % of the study region. The land use and land cover (LULC) change pattern indicates that the restoration project-induced conversion of agricultural land contributed to nearly 10 % of the total carbon sequestration after 2010. However, some extreme climatic conditions weakened the effectiveness of ecological restoration projects, highlighting the need for stricter management. Finally, this study identified the key area for effective ecological restoration in ecologically fragile regions in China.
Keywords: Carbon sequestration | Ecological restoration project | Ecologically fragile region
Studies of stress and displacement distribution and the evolution law during rock failure process based on acoustic emission and microseismic monitoring
بررسی استرس و توزیع جابجایی و قانون تکامل در طی فرآیند شکست سنگها بر اساس انتشار صوتی و پایش ریزگردها-2020
The evolutions of stress and deformation inside of rock is highly important in studies of the rock failure mechanism but is difficult to obtain via the traditional stress measurement methods due to limited measuring points. Thus, studies of the stress and displacement evolution within rock were conducted based on acoustic emission (AE) monitoring in laboratory experiments. The differences in the distributions and evolution characteristics of the stress field and deformation field before caving in a deep stope were also examined based on insitu microseismic (MS) monitoring. The results show that the distributions of micro-cracks, apparent stress and deformation inside the rock are highly consistent and can reflect the spatial-temporal evolution characteristics of the stress field and deformation field within the rock. The accumulated apparent volume is more accurately than the strain to reflect the changes in inelastic deformation inside the rock. Based on in-situ MS monitoring, MS activities were found to be closely related to blasting disturbances during the caving process. Before a caving of the deep stope, the distributions of stress and displacement showed obvious differences, reflecting the loosening process of the rock mass. The non-uniformity and the differences in the stress and deformation can deepen the understanding of the rock (mass) failure process.
Keywords: Rock fracture | Acoustic emission (AE) | Microseismic (MS) | Stress field | Displacement field
The Data Visualization of Large Scale AIS Trajectories Data on Hadoop
تجسم داده ها در مقیاس بزرگ داده های مسیر AIS در Hadoop-2020
Abstract—With the establishment of Automatic Identification System(AIS) networks, maritime vessel trajectories are becoming increasingly available.The visualization of AIS trajectories data is an effective way on large scale spatiotemporal data analysis and is critical for real time applications ranging from military surveillance to transportation management. In this paper we uses the real AIS data as experimental data and uses Hadoop as data processing and storage,presents a dynamic visualization of global marine AIS data and local sea area situation.A multicharts visualization model is presented, where the characteristics of complex ships in port area can be analyzed.
Keywords: visualization | AIS | large data | Hadoop
Delineating urban hinterland boundaries in the Pearl River Delta: An approach integrating toponym co-occurrence with field strength model
ترسیم مرزهای مناطق شهری در دلتای رود مروارید: رویکرد ادغام همزمان وقایع توپومی با مدل مقاومت میدانی-2020
Urban development requires the support of its surrounding areas. Accurate identification of urban hinterlands can help to scientifically evaluate strength and potential of urban development. The field strength model is regarded as an effective way to identify hinterlands, but the revision of friction coefficient has still not reached a consensus. With the application of big data in urban planning, it is possible to improve the field strength model. Toponym co–occurrence data, as a timely data source directly obtained from the Internet, can be used to reflect the spatiotemporal changes in urban connections, and provide an approach to quantifying the friction coefficient for the division of urban hinterlands. In this study, a new approach was developed by integrating toponym co–occurrence and improved field strength model. We considered the Pearl River Delta urban agglomeration as a case and identified the urban hinterland of each city. The results showed that the friction coefficient among cities fluctuated within a range of 1.25–2.50, the urban hinterlands were no longer confined to their own administrative divisions, and there was fierce competition with other cities. In particular, the urban hinterland of Guangzhou was 3699 km2 larger than its actual administrative area. In addition, the proposed approach was more reliable in urban hinterland identification compared with the traditional fixed friction coefficient method. This study provides an improved field strength model based on toponym co–occurrence, which can identify urban hinterlands more accurately and objectively as well as promote the application of big data in urban planning.
Keywords: Urban hinterland | Toponym co–occurrence | Improved field strength model | Pearl River Delta
The varying patterns of rail transit ridership and their relationships with fine-scale built environment factors: Big data analytics from Guangzhou
الگوهای مختلف تفریحی حمل و نقل ریلی و روابط آنها با عوامل محیطی ساخته شده در مقیاس خوب: تجزیه و تحلیل داده های بزرگ از گوانگژو-2020
Investigating the varying ridership patterns of rail transit ridership and their influencing factors at the station level is essential for station planning, urban planning, and passenger flow management. Although many studies have investigated the associations between rail transit ridership and built environment, few studies combined spatial big data to characterize the built environment factors at a fine scale and linked those factors with the varying patterns of rail transit ridership. In this study, we characterized the fine-scale built environment factors in the central urban area of Guangzhou, China, by integrating multi-source geospatial big data including Tencent user data, building footprint and stories, points of interest (POI) data and Google Earth high-resolution images. Six direct ridership models (DRMs) based on the backward stepwise regression method were built to compare the different effects between daily, temporal and directional ridership. The results indicated that number of station entrances/exits and transfer dummy, were positively associated with rail transit ridership, while connecting bus station sites and the parking lots were not significantly related to ridership. Population density and common residences land were found to be dominating factors in promoting morning boarding & evening alighting ridership, which implied that these two factors should be focused on to encourage commuting-purpose rail transit usage. However, the indistinct effect of urban villages on rail transit ridership suggested planners to pay more attentions on urban regeneration at the pedestrian catchment areas (PCAs) with urban villages. High employment density and a large FAR were suggested at the employment-oriented areas owing to their importance in promoting rail transit ridership, especially the morning alighting & evening boarding ridership. Moreover, educational research land use significantly affected weekday ridership while sports land use positively influenced weekend ridership, which suggested planners to pay more attention on the non-commuting trips. The different influencing mechanisms of various types of rail transit ridership highlighted the need to consider land use balance planning and trip demand optimization in highly urbanized metropolises in developing countries.
Keywords: Rail transit ridership | Big data | Fine-scale | Built environment | Guangzhou
Dynamic resource allocation during reinforcement learning accounts for ramping and phasic dopamine activity
تخصیص منابع پویا در طول حساب های یادگیری تقویتی برای فعالیت دوپامین ramping و مرحله ای-2020
For an animal to learn about its environment with limited motor and cognitive resources, it should focus its resources on potentially important stimuli. However, too narrow focus is disadvantageous for adaptation to environmental changes. Midbrain dopamine neurons are excited by potentially important stimuli, such as reward-predicting or novel stimuli, and allocate resources to these stimuli by modulating how an animal approaches, exploits, explores, and attends. The current study examined the theoretical possibility that dopamine activity reflects the dynamic allocation of resources for learning. Dopamine activity may transition between two patterns: (1) phasic responses to cues and rewards, and (2) ramping activity arising as the agent approaches the reward. Phasic excitation has been explained by prediction errors generated by experimentally inserted cues. However, when and why dopamine activity transitions between the two patterns remain unknown. By parsimoniously modifying a standard temporal difference (TD) learning model to accommodate a mixed presentation of both experimental and environmental stimuli, we simulated dopamine transitions and compared them with experimental data from four different studies. The results suggested that dopamine transitions from ramping to phasic patterns as the agent focuses its resources on a small number of rewardpredicting stimuli, thus leading to task dimensionality reduction. The opposite occurs when the agent re-distributes its resources to adapt to environmental changes, resulting in task dimensionality expansion. This research elucidates the role of dopamine in a broader context, providing a potential explanation for the diverse repertoire of dopamine activity that cannot be explained solely by prediction error.
Keywords: Prediction error | Salience | Temporal-difference learning model | Pearce-Hall model | Habit | Striatum
The geography of human activity and land use: A big data approach
جغرافیای فعالیت های انسانی و استفاده از زمین: یک رویکرد داده های بزرگ-2020
The application of location-based social media big data in urban contexts offers new and alternative strategies for understanding city liveliness in developing countries where traditional census data are poor. This paper demonstrates how the spatial-temporal distribution of Chinas Tencent social media usage intensities can be effectively used as a proxy for modelling the geographic patterns of human activity at fine scales. Our results suggest that the spatially-temporally contextualized nature of human activity is dependent upon land use mixing characteristics. With billions of social media data being collected in the virtual world, findings of this study suggest that land use policies to delineating the density, orderly or disorderly geographic patterns of human activity are important for city liveliness.
Keywords: Big data | Human activity | Land use