Search

The primary objective of this study is to predict the short-term metro passenger flow using the proposed hybrid spatiotemporal deep learning neural network (HSTDL-net). The metro passenger flow data is collected from line 2 of Nanjing metro system to illustrate the study procedure. A hybrid spatiotemporal deep learning model is developed to predict both inbound and outbound passenger flows for every 10 minutes. The results suggest that the proposed HSTDL-net achieves better prediction performance on suburban stations than on urban stations, as well as generating the best prediction accuracy on transfer stations in terms of the lowest MAPE value. Moreover, a comparative analysis is conducted to compare the performance of proposed HSTDL-net with other typical methods, such as ARIMA, MLP, CNN, LSTM, and GBRT. The results indicate that, for both inbound and outbound passenger flow predictions, the HSTDL-net outperforms all the compared models on three types of stations. The results suggest that the proposed hybrid spatiotemporal deep learning neural network can more effectively and fully discover both spatial and temporal hidden correlations between stations for short-term metro passenger flow prediction. The results of this study could provide insightful suggestions for metro system authorities to adjust the operation plans and enhance the service quality of the entire metro system. [ABSTRACT FROM AUTHOR]

In recent days, there has been a noticeable surge in demand for high-quality rice. However, the influences of salinity on the quality and starch properties of high-quality rice remain unclear. Three high-quality rice cultivars (Nanjing 9108, Nanjing 5055, and Nanjing 46) were studied to investigate the responses of grain quality to salt stress. There were three treatments, including a control zero salt level (0 g·kg−1, CK), and two salt levels of 0.1 g·kg−1 (0.1% salt stress, T1) and 0.2 g·kg−1 (0.2% salt stress, T2). The study involved the assessment of the appearance, milling, cooking, and eating qualities of rice. We also conducted an analysis of pasting properties, an evaluation of starch thermal properties, and an examination of the fine structure of amylopectin. The findings suggest that as the level of salt stress increases, the yield of rice gradually declines, which is primarily due to a significant reduction in the total spikelet number and the ratio of filled grains. Compared with CK treatment, the appearance and milling quality of rice were significantly improved within the T1 treatment. In addition, the protein concentration and amylose concentration were significantly decreased, the gel consistency was significantly increased, and the cooking and eating qualities were improved. In terms of starch properties, the peak viscosity, breakdown value, infrared ratio (1022/995), and short-chain-length amylopectin ratio increased significantly, while the setback value, pasting temperature, gelatinization enthalpy, relative crystallinity, and infrared ratio (1045/1022) decreased significantly. When comparing T2 with CK, the appearance quality and cooking and eating quality had deteriorated, and the milling quality was improved. The changes in the structural and physicochemical properties of starch were opposite to those in the comparison between the T1 treatment and the CK group. Accordingly, we propose that moderate salt stress has the potential to enhance rice quality, even though there may be a slight decrease in yield. This indicates that it is feasible to cultivate high-quality rice in saline–alkali beach areas. [ABSTRACT FROM AUTHOR]

Nitrogen (N) fertilizer is a critical element that affects rice yield. However, its effects on dry matter accumulation (DMA), N accumulation, and their physiological mechanisms with grain yield and N utilization efficiency still lack in-depth study. Three large-scale japonica rice varieties—Jinxiangyu 1, Nanjing 46, and Huaidao 5—were used in two field experiments with varying N fertilizer application rates to examine grain yield and N utilization efficiency. The results showed that: (1) In the range of 0~360 kg ha−1 total N application rate (TNAR), the rice yields of the three cultivars were maximum under the TNAR at 270 kg ha−1. The optimal TNAR for the highest yield of Jinxiangyu 1, Nanjing 46, and Huaidao 5 were calculated based on quadratic regressions with values of 305.5 kg ha−1, 307.6 kg ha−1, and 298.0 kg ha−1, and the corresponding yields were 10.3 t ha−1, 10.6 t ha−1 and 10.2 t ha−1, respectively. The N utilization efficiency decreased gradually with the increase in TNAR, and the recovery efficiency decreased from 35.7~38.19% to 29.61~31.59%. (2) The yield was significantly positively correlated with DMA and N accumulation from the heading stage (HD) to the maturity stage (MA). The DMA and N accumulation of HD-MA were significantly positively correlated with leaf photosynthetic rate, non-structural carbohydrate (NSC) accumulation in stems, root oxidation activity, zeatin (Z) + zeatin riboside (ZR) contents in roots, and nitrate reductase (NR) and glutamate synthase (GOGAT) activity in HD. (3) In the range of 0~216 kg ha−1 panicle N application rate (PNAR), the rice yield was maximum under the PNAR at 108 kg ha−1. The optimal PNAR for the highest yield of Jinxiangyu 1 was calculated based on the quadratic regression with values of 139.5 kg ha−1, and the highest yield was 9.72 t ha−1. The leaf photosynthetic rate, NSC accumulation in stems, root oxidation activity, Z + ZR contents in roots, and NR activity in leaves in rice were higher under 108 kg ha−1 PNAR. Excessive application of panicle fertilizer reduced the above physiological indicators and rice yield. The above results showed that optimizing N fertilizer could increase the leaf photosynthetic rate, NSC accumulation in stems, root oxidation activity, Z + ZR contents in roots, and NR activity from HD to MA, which was beneficial to improving DMA and N uptake during HD-MA, thus improving grain yield and N utilization efficiency in rice. [ABSTRACT FROM AUTHOR]

Globally, the use of electric vehicles, and in particular the use of electric buses, has been increasing. The city of Nanjing leads China in the adoption of electric buses, supported by city policies and infrastructure. To lower costs and provide a better service, vehicle selection is crucial, however, existing selection methods are limited. Accordingly, Nanjing Bus Company developed a test method based on road tests to select a bus. This paper presents a detailed description of the test method and a case study of its application. The method included an organization structure, selection of eight test vehicles (four 10 m length, four 8 m length) from four brands (a total of 32 test vehicles), selection of indicators and selection of routes. Data was collected from repeated drives by 65 drivers over an 8-week period. Indicators included power consumption, charging duration, failure duration and driving distance. It is concluded that the road test method designed and conducted by the Nanjing Bus Company provides a good framework for the selection of pure electric buses. Furthermore, subsequent experience with selected buses supports the validity and value of the model. [ABSTRACT FROM AUTHOR]