An adaptive big data weather system for surface transportation

Siems-Anderson, Amanda; Walker, Charles F.; Wiener, Gerry; Mahoney, William P.; Haupt, Sue Ellen

doi:10.1016/j.trip.2019.100071

Cited by 17 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 demonstrates the DICast post-processing methodology, which is representative of the many other systems currently being used. DICast has evolved over time to include additional machine-learning methods and has been shown to dramatically improve forecasts across multiple weather-dependent applications including road conditions [16], precision agriculture, wind and solar energy [17][18][19][20], among others. Now, many commercial weather companies and national centres employ AI-based post-processing methods [21].…”

Section: (A) Forecast Improvements With Aimentioning

confidence: 99%

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Haupt

Chapman

Adams

et al. 2021

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

The most mature aspect of applying artificial intelligence (AI)/machine learning (ML) to problems in the atmospheric sciences is likely post-processing of model output. This article provides some history and current state of the science of post-processing with AI for weather and climate models. Deriving from the discussion at the 2019 Oxford workshop on Machine Learning for Weather and Climate, this paper also presents thoughts on medium-term goals to advance such use of AI, which include assuring that algorithms are trustworthy and interpretable, adherence to FAIR data practices to promote usability, and development of techniques that leverage our physical knowledge of the atmosphere. The coauthors propose several actionable items and have initiated one of those: a repository for datasets from various real weather and climate problems that can be addressed using AI. Five such datasets are presented and permanently archived, together with Jupyter notebooks to process them and assess the results in comparison with a baseline technique. The coauthors invite the readers to test their own algorithms in comparison with the baseline and to archive their results. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

show abstract

Section: (A) Forecast Improvements With Aimentioning

confidence: 99%

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Haupt

Chapman

Adams

et al. 2021

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

show abstract

“…citizen science data (Chapman et al, 2017;De Vos et al, 2017, 2019aNipen et al, 2019), and measurement from moving vehicles (Anderson et al, 2012(Anderson et al, , 2019) have been stored in the databases of national centres alongside conventional observations. Such observations should be treated carefully on their own (Bell et al, 2015), but are valuable because the immense amount of data points leads to a redundancy of neighbours to validate the measurements.…”

Section: Motivationsmentioning

confidence: 99%

TITAN automatic spatial quality control of meteorological in-situ observations

et al. 2020

View full text Add to dashboard Cite

Abstract. In science, poor quality input data will invariably lead to faulty conclusions, as in the spirit of the saying “garbage in, garbage out”. Atmospheric sciences make no exception and correct data is crucial to obtain a useful representation of the real world in meteorological, climatological and hydrological applications. Titan is a computer program for the automatic quality control of meteorological data that has been designed to serve real-time operational applications that process massive amounts of observations measured by networks of automatic weather stations. The need to quality control third-party data, such as citizen observations, within a station network that is constantly changing was an important motivation that led to the development of Titan. The quality control strategy adopted is a sequence of tests, where several of them utilize the expected spatial consistency between nearby observations. The spatial continuity can also be evaluated against independent data sources, such as numerical model output and remote sensing measurements. Examples of applications of Titan for the quality control of near-surface hourly temperature and precipitation over Scandinavia are presented. In the case of temperature, this specific application has been integrated into the operational production chain of automatic weather forecasts at the Norwegian Meteorological Institute (MET Norway). Titan is an open source project and it is made freely available for public download. One of the objectives of the Titan project is to establish a community working on common tools for automatic quality control, and the Titan program represents a first step in that direction for MET Norway. Further developments are necessary to achieve a solution that satisfies more users, for this reason we are currently working on transforming Titan into a more flexible library of functions.

show abstract

“…Based on research on autonomous or non-autonomous cars, on different communication technologies, on decentralized and centralized connectivity [45,46], we have concluded that there is a rich cluster of information and interaction produced between vehicles and other road entities. In the Solution section, we are going to explore a dynamic visualization [47] of road information in terms of predictive weather conditions [48], visibility [49,50] and outdoor illumination [51,52] and potential sun glares [53,54] at the future moment of passing through that area, with markings on possible hazards [55,56], for a better trip planning. We chose this kind of information compared to the better-known real-time crowd sourced [57] traffic data, as an example of a novel cluster of visualized road information.…”

Section: Connected Cars and Smart Transport Infrastructurementioning

confidence: 99%

Ubiquitous Computing: Driving in the Intelligent Environment

et al. 2021

View full text Add to dashboard Cite

In the context of hyper-connected cars and a growing heterogeneous digital ecosystem, we wish to make the most of the data available from the various sensors, devices and services that compose the ecosystem, in order to propose a proof of concept in-vehicle system that enhances the driving experience. We focus on improving the driving experience along three main directions, namely: (1) driving and trip planning, (2) health and well-being and (3) social and online activities. We approached the in-vehicle space as a smart interface to the intelligent driving environment. The digital data-producers in the ecosystem of the connected car are sources of raw data of various categories, such as data from the outside world, gathered from sensors or online services, data from the car itself and data from the driver gathered with various mobile and wearable devices, by means of observing his state and by means of his social media and online activity. Data is later processed into three information categories—driving, wellness, and social—and used to provide multi-modal interaction, namely visual, audio and gesture. The system is implemented to act in response to the trafficked information on different levels of autonomy, either in a reactive manner, by simple monitoring, or in a proactive manner. The system is designed to provide an in-vehicle system that assists the driver with planning the travel (Drive panel), by providing a comfortable environment for the driver while monitoring him (Wellness panel), and by adaptively managing interactions with their phone and the digital environment (Social panel). Heuristic evaluation of the system is performed, with respect to guidelines formulated for automated vehicles, and a SWOT analysis of the system is also presented in the paper.

show abstract

An adaptive big data weather system for surface transportation

Cited by 17 publications

References 15 publications

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

TITAN automatic spatial quality control of meteorological in-situ observations

Ubiquitous Computing: Driving in the Intelligent Environment

Contact Info

Product

Resources

About