Predictability is an essential challenge for autonomous vehicles(AVs)’safety.Deep neural networks have been widely deployed in the AV’s perception pipeline.However,it is still an open question on how to guarantee the perception predictability for AV because there are millions of deep neural networks(DNNs)model combinations and system configurations when deploying DNNs in AVs.This paper proposes configurable predictability testbed(CPT),a configurable testbed for quantifying the predictability in AV’s perception pipeline.CPT provides flexible configurations of the perception pipeline on data,DNN models,fusion policy,scheduling policies,and predictability metrics.On top of CPT,the researchers can profile and optimize the predictability issue caused by different application and system configurations.CPT has been open-sourced at:https://github.com/Torreskai0722/CPT.
Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather and climate phenomena.In the past few decades,dynamical numerical models have been the primary tools for predictability studies,achieving significant progress.Nowadays,with the advances in artificial intelligence(AI)techniques and accumulations of vast meteorological data,modeling weather and climate events using modern data-driven approaches is becoming trendy,where FourCastNet,Pangu-Weather,and GraphCast are successful pioneers.In this perspective article,we suggest AI models should not be limited to forecasting but be expanded to predictability studies,leveraging AI's advantages of high efficiency and self-contained optimization modules.To this end,we first remark that AI models should possess high simulation capability with fine spatiotemporal resolution for two kinds of predictability studies.AI models with high simulation capabilities comparable to numerical models can be considered to provide solutions to partial differential equations in a data-driven way.Then,we highlight several specific predictability issues with well-determined nonlinear optimization formulizations,which can be well-studied using AI models,holding significant scientific value.In addition,we advocate for the incorporation of AI models into the synergistic cycle of the cognition–observation–model paradigm.Comprehensive predictability studies have the potential to transform“big data”to“big and better data”and shift the focus from“AI for forecasts”to“AI for science”,ultimately advancing the development of the atmospheric and oceanic sciences.
This paper provides a robust test of predictability under the predictive regression model with possible heavy-tailed innovations assumption,in which the predictive variable is persistent and its innovations are highly correlated with returns.To this end,we propose a robust test which can capture empirical phenomena such as heavy tails,stationary,and local to unity.Moreover,we develop related asymptotic results without the second-moment assumption between the predictive variable and returns.To make the proposed test reasonable,we propose a generalized correlation and provide theoretical support.To illustrate the applicability of the test,we perform a simulation study for the impact of heavy-tailed innovations on predictability,as well as direct and/or indirect implementation of heavy-tailed innovations to predictability via the unit root phenomenon.Finally,we provide an empirical study for further illustration,to which the proposed test is applied to a U.S.equity data set.
WONG Hsin-ChiehCHUNG Meng-HuaFUH Cheng-DerPANG Tian-xiao
Although the principles of synthetic biology were initially established in model bacteria,microbial producers,extremophiles and gut microbes have now emerged as valuable prokaryotic chassis for biological engineering.Extending the host range in which designed circuits can function reliably and predictably presents a major challenge for the concept of synthetic biology to materialize.In this work,we systematically characterized the cross-species universality of two transcriptional regulatory modules—the T7 RNA polymerase activator module and the repressors module—in three non-model microbes.We found striking linear relationships in circuit activities among different organisms for both modules.Parametrized model fitting revealed host non-specific parameters defining the universality of both modules.Lastly,a genetic NOT gate and a band-pass filter circuit were constructed from these modules and tested in non-model organisms.Combined models employing host non-specific parameters were successful in quantitatively predicting circuit behaviors,underscoring the potential of universal biological parts and predictive modeling in synthetic bioengineering.
In order to quantify the influence of external forcings on the predictability limit using observational data,the author introduced an algorithm of the conditional nonlinear local Lyapunov exponent(CNLLE)method.The effectiveness of this algorithm is validated and compared with the nonlinear local Lyapunov exponent(NLLE)and signal-to-noise ratio methods using a coupled Lorenz model.The results show that the CNLLE method is able to capture the slow error growth constrained by external forcings,therefore,it can quantify the predictability limit induced by the external forcings.On this basis,a preliminary attempt was made to apply this method to measure the influence of ENSO on the predictability limit for both atmospheric and oceanic variable fields.The spatial distribution of the predictability limit induced by ENSO is similar to that arising from the initial conditions calculated by the NLLE method.This similarity supports ENSO as the major predictable signal for weather and climate prediction.In addition,a ratio of predictability limit(RPL)calculated by the CNLLE method to that calculated by the NLLE method was proposed.The RPL larger than 1 indicates that the external forcings can significantly benefit the long-term predictability limit.For instance,ENSO can effectively extend the predictability limit arising from the initial conditions of sea surface temperature over the tropical Indian Ocean by approximately four months,as well as the predictability limit of sea level pressure over the eastern and western Pacific Ocean.Moreover,the impact of ENSO on the geopotential height predictability limit is primarily confined to the troposphere.
Ming ZHANGRuiqiang DINGQuanjia ZHONGJianping LIDeyu LU
Employing the nonlinear local Lyapunov exponent (NLLE) technique, this study assesses the quantitative predictability limit of oceanic mesoscale eddy (OME) tracks utilizing three eddy datasets for both annual and seasonal means. Our findings reveal a discernible predictability limit of approximately 39 days for cyclonic eddies (CEs) and 44 days for anticyclonic eddies (AEs) within the South China Sea (SCS). The predictability limit is related to the OME properties and seasons. The long-lived, large-amplitude, and large-radius OMEs tend to have a higher predictability limit. The predictability limit of AE (CE) tracks is highest in autumn (winter) with 52 (53) days and lowest in spring (summer) with 40 (30) days. The spatial distribution of the predictability limit of OME tracks also has seasonal variations, further finding that the area of higher predictability limits often overlaps with periodic OMEs. Additionally, the predictability limit of periodic OME tracks is about 49 days for both CEs and AEs, which is 5-10 days higher than the mean values. Usually, in the SCS, OMEs characterized by high predictability limit values exhibit more extended and smoother trajectories and often move along the northern slope of the SCS.
