ClearFlow

Motivation

The societal challenge we address is  poor quality air conditions in Swedish cities. Pollutants from carbon-based fuel engines are detrimental to all urban lives creating a environmental challenge for the next decades. Children are particularly at risk, as brain development is inhibited by sub-micron particles. Timely, new bypass routes are being built in northern Stockholm, and we will capture the effect of these new roads within the 2 years of ClearFlow. The news value of the problem is “does road traffic contribute to poor air quality in Stockholm, if so, when, where and to what degree?”.

The market conditions are rife for a public-leaning air quality measurement platform and deployment. Although there are projects and sensors, there is no cheap, open-sourced, cellular-ready platform dedicated to measuring air quality.  The energy saving potential is significant, as we use small single board sensors. They can run on an external 5V source, a la mobile power packs, or even solar power. The processing platform in Luleå, housed in an energy efficient environment, with energy saving measures, i.e. using the local temperatures.

The environmental relevance is that pollutants from heavily used transport paths, not least the roads in Stockholm. Internet-driven deliveries of packets are delivered in diesel-powered vehicles. Second, winter studded tyres contribute to air particulates.  Third particulates also come from factories in eastern europe. Background 2.5/5/10 PM values need to known to eliminate their effect. ClearFlow delivers a Swedish system using the Urban ICT arena to measure pollutants and correlate to local traffic. The solution can be deployed in any city, but ClearFlow focuses on the environmental impact on Stockholm due to the nearby E4. It will deliver an open-source operating system, platform, data. We will dissemination knowledge and lessons using experts in road traffic, communications, measurements and data processing.

Background

The current need is a cheap, communications-enabled air quality sensor. Many sensors exist, but are either expensive, hard to deploy, need significant power requirements, or are neither cellular nor IP-enabled. The KTH designed 500 SEK sensor fulfills these requirements [1].

There is also a need for open high quality data that follows data governance guidelines [2]. Therefore, fusing the air quality with society-useful sources in this case real-time traffic flow increases data value.  Additional sources, such as the weather conditions and complementary particle measurements still elevate ClearFlow’s streamed data. Following governance guidelines and Data Readiness [3] will maximise our fused data value.

Our own experiences are the Vinnova-funded GreenIOT project which developed air quality sensors and deployed in Uppsala [1].  Also Vinnova-funded FFI Big Automotive Data Analytics BADA [2] and POST [3] projects analysed traffic flow in the Stockholm area.  UrbanICT is an currently running testbed in Kista [3],

Figure 1: ClearFlow fuses sensor and public data for value to city residents

Problem statement

Reporting air pollutants in medium-sized Swedish cities depends on [challenge]:

  1. Correlating vehicles to pollutants, accounting for background pollution [CO2 challenge]
  2. Inferring and learning traffic flow patterns [traffic challenge]
  3. Fusing streamed data from multiple sources [platform challenge]
  4. AI algorithms to couple model and measurements [algorithmic challenge]
  5. Including the weather into correlation [metrological challenge]
  6. Presentation of results (including cost) to public authorities and public [visualization challenge]

Expected Results

  • Correlation with road traffic
  • Data as a service
    • Weather
    • Background pollution
    • IVLs competence : include (account for) Asphalt and brake particles

 

Significant differences to other air quality measuring projects

  1. Much lower cost sensor
    1. Around 70 Euro per sensor
  2. Advanced IP networking
    1. Swedish based operating system (Contiki)
    2. IP stack (KTH)
  3. Data fusion at novel cloud-based system
    1. Multi-tenancy allows actors’ data to be ring-fenced

References

[1] The GreenIOT project, started 2015, completed 2018,  https://goo.gl/9FXVFA.

[2] Urban ICT arena http://www.urbanictarena.se

[3] The Viable Cities project, will start 2018, completed 2021, https://goo.gl/Abmf55.

[4] mqtt protocol being used currently (CoAP)

[6] Neil D. Lawrence, Data readiness levels, 2017, https://arxiv.org/abs/1705.02245.

[7] HopsWorks: a platform for fast, secure, multi-tenancy data sharing and protection.

[8] M. Neumann, I. Marsh, B. Bjurling, A. Al-Shishtawy, A. Holst, Algorithms for Data Mining and Machine Learning in BADA, Big Data Infrastructure, 2017 (available from http://bada.sics.se).

[9] Mobile Millennium project, Berkeley, http://traffic.berkeley.edu/

[10] Polson et. al, Deep Learning for Short-Term Traffic Flow Prediction, https://arxiv.org/pdf/1604.04527.pdf

[11] Particulate matter, air quality and climate: lessons learned and future needs https://www.atmos-chem-phys.net/15/8217/2015/acp-15-8217-2015.pdf

[12] Kartläggning av partiklar i Sverige – halter, källbidrag och kunskapsluckor

https://www.smhi.se/polopoly_fs/1.13480!/meteorologi_144.pdf

[13] https://biendata.com/competition/kdd_2018/

[14] https://www.microsoft.com/en-us/research/project/urban-air/

[15] https://en.wikipedia.org/wiki/LoRa

[16] KTH live measurements http://lab-pc.ssvl.kth.se:9876/

[17] TrV live measurements http://resmonster.se/dash/s/pages/mcs.php (old page, not available)