Deep Spatio-temporal Adaptive 3D Convolutional Neural Networks for Traffic Flow Prediction

Traffic flow prediction is the upstream problem of path planning, intelligent transportation system, and other tasks. Many studies have been carried out on the traffic flow prediction of the spatio-temporal network, but the effects of spatio-temporal flexibility (historical data of the same type of time intervals in the same location will change flexibly) and spatio-temporal correlation (different road conditions have different effects at different times) have not been considered at the same time. We propose the Deep Spatio-temporal Adaptive 3D Convolution Neural Network (ST-A3DNet), which is a new scheme to solve both spatio-temporal correlation and flexibility, and consider spatio-temporal complexity (complex external factors, such as weather and holidays). Different from other traffic forecasting models, ST-A3DNet captures the spatio-temporal relationship at the same time through the Adaptive 3D convolution module, assigns different weights flexibly according to the influence of historical data, and obtains the impact of external factors on the flow through the ex-mask module. Considering the holidays and weather conditions, we train our model for experiments in Xi’an and Chengdu. We evaluate the ST-A3DNet and the results show that we have better results than the other 11 baselines.

Dominating lengthscales of zebrafish collective behaviour

Collective behaviour in living systems is observed across many scales, from bacteria to insects, to fish shoals. Zebrafish have emerged as a model system amenable to laboratory study. Here we report a three-dimensional study of the collective dynamics of fifty zebrafish. We observed the emergence of collective behaviour changing between ordered to randomised, upon adaptation to new environmental conditions. We quantify the spatial and temporal correlation functions of the fish and identify two length scales, the persistence length and the nearest neighbour distance, that capture the essence of the behavioural changes. The ratio of the two length scales correlates robustly with the polarisation of collective motion that we explain with a reductionist model of self–propelled particles with alignment interactions.

Spatiotemporal Associations between Local Safety Level Index and COVID-19 Infection Risks across Capital Regions in South Korea

This study aims provide understanding of the local-level spatiotemporal evolution of COVID-19 spread across capital regions of South Korea during the second and third waves of the pandemic (August 2020~June 2021). To explain transmission, we rely upon the local safety level indices along with latent influences from the spatial alignment of municipalities and their serial (temporal) correlation. Utilizing a flexible hierarchical Bayesian model as an analytic operational framework, we exploit the modified BYM (BYM2) model with the Penalized Complexity (PC) priors to account for latent effects (unobserved heterogeneity). The outcome reveals that a municipality with higher population density is likely to have an elevated infection risk, whereas one with good preparedness for infectious disease tends to have a reduction in risk. Furthermore, we identify that including spatial and temporal correlations into the modeling framework significantly improves the performance and explanatory power, justifying our adoption of latent effects. Based on these findings, we present the dynamic evolution of COVID-19 across the Seoul Capital Area (SCA), which helps us verify unique patterns of disease spread as well as regions of elevated risk for further policy intervention and for supporting informed decision making for responding to infectious diseases.

A crosscorrelation methodology for in vivo pharmacokinetic study by the trans-scale fluorescent system

Conventional single-organ-isolation-based pharmacokinetics study is short of time-course information and exists considerable inaccuracy due to the inter-individual differences and characteristic imparities between in vivo and ex vivo tissues/cells. The in vivo time-course and multi-organs study of model drugs in living subjects could afford precise spatio-temporal correlation. Herein, a revolutionized trans-dimensional fluorescence system was home built, with the macro-level detection part for simultaneous pharmacokinetic study in different organs, and one confocal imaging needle for micro-level visualizing cellular uptake of drugs with super-high resolution (0.472 μm). Correlating these simultaneous acquired trans-scale data, an innovative physiologically-based pharmacokinetics (PBPK) model was firstly created for predicting drug disposition in other species. Its accuracy and reliability was firmly supported by the high consistent predicted-data with the real-measured data in mice and in human, respectively. This study provides an innovative methodology and revolutionized instrument for in vivo real-time advancing assessment of druggability.

Revisiting regulatory decoherence: Accounting for temporal bias in a co-expression analysis reveals novel candidates controlling environmental response

Transcriptional Regulatory Networks (TRNs) orchestrate the timing, magnitude, and rate of organismal response to many environmental perturbations. Regulatory interactions in TRNs are dynamic but exploiting temporal variation to understand gene regulation requires a careful appreciation of both molecular biology and confounders in statistical analysis. Seeking to exploit the abundance of RNASequencing data now available, many past studies have relied upon population-level statistics from cross-sectional studies, estimating gene co-expression interactions to capture transient changes of regulatory activity. We show that population-level co-expression exhibits biases when capturing transient changes of regulatory activity in rice plants responding to elevated temperature. An apparent cause of this bias is regulatory saturation, the observation that detectable co-variance between a regulator and its target may be low as their transcript abundances are induced. This phenomenon appears to be particularly acute for rapid onset environmental stressors. However, exploiting temporal correlations appears to be a reliable means to detect transient regulatory activity following rapid onset environmental perturbations such as temperature stress. Such temporal correlation may lose information along a more gradual-onset stressor (e.g., dehydration). We here show that rice plants exposed to a dehydration stress exhibit temporal structure of coexpression in their response that can not be unveiled by temporal correlation alone. Collectively, our results point to the need to account for the nuances of molecular interactions and the possibly confounding effects that these can introduce into conventional approaches to study transcriptome datasets.

A Dynamic Statistical Subseasonal Forecast Model for OLR Over Tropical Pacific Region

How to improve the subseasonal forecast skills of dynamic models has always been an important issue in atmospheric science and service. This study proposes a new dynamical-statistical forecast method and a stable components dynamic statistical forecast (STsDSF) for subseasonal outgoing long-wave radiation (OLR) over the tropical Pacific region in January-February from 2004 to 2008. Compared with 11 advanced multi-model ensemble (MME) daily forecasts, the STsDSF model was able to capture the change characteristics of OLR better when the lead time was beyond 30 days in 2005 and 2006. The average pattern correlation coefficients (PCC) of STsDSF are 0.24 and 0.16 in 2005 and 2006, while MME is 0.10 and 0.05, respectively. In addition, the average value of PCC of the STsDSF model in five years is higher than MME in 7–11 pentads. Although both the STsDSF model and MME show a similar temporal correlation coefficient (TCC) pattern over the tropical Pacific region, the STsDSF model error grows more slowly than the MME error during 8–12 pentads in January 2005. This phenomenon demonstrates that STsDSF can reduce dynamical model error in some situations. According to the comparison of subseasonal forecasts between STsDSF and MME in five years, STsDSF model skill depends strictly on the predictability of the dynamical model. The STsDSF model shows some advantages when the dynamical model could not forecast well above a certain level. In this study, the STsDSF model can be used as an effective reference for subseasonal forecast and could feasibly be used in real-time forecast business in the future.

Acoustic surveillance for respiratory diseases: a prospective analysis of cough trends using artificial intelligence.

Syndromic surveillance for respiratory disease is limited by an inability to monitor its protean manifestation, cough. Advances in artificial intelligence provide the ability to passively monitor cough at individual and community levels. We hypothesized that changes in the aggregate number of coughs recorded among a sample could serve as a lead indicator for population incidence of respiratory diseases, particularly that of COVID-19. We enrolled over 900 people from the city of Pamplona (Spain) between 2020 and 2021 and used artificial intelligence cough detection software to monitor their cough. We collected nine person-years of cough aggregated data. Coughs per hour surged around the time cohort subjects sought medical care. There was a weak temporal correlation between aggregated coughs and the incidence of COVID-19 in the local population. We propose that a clearer correlation with COVID-19 incidence could be achieved with better penetration and compliance with cough monitoring.

Extreme precipitation on consecutive days occurs more often in a warming climate

Extreme precipitation occurring on consecutive days may substantially increase the risk of related impacts, but changes in such events have not been studied at a global scale. Here we use a unique global dataset based on in situ observations and multi-model historical and future simulations to analyse the changes in the frequency of extreme precipitation on consecutive days (EPCD). We further disentangle the relative contributions of variations in precipitation intensity and temporal correlation of extreme precipitation, to understand the processes that drive the changes in EPCD. Observations and climate model simulations show that the frequency of EPCD is increasing in most land regions, in particular in North America, Europe and the Northern Hemisphere high latitudes. These increases are primarily a consequence of increasing precipitation intensity, but changes in the temporal correlation of extreme precipitation regionally amplify or reduce the effects of intensity changes. Changes are larger in simulations with a stronger warming signal, suggesting that further increases in EPCD are expected for the future under continued climate warming.