Maguire Submission VAST Mini-Challenge 2

May we post your submission in the Visual Analytics Benchmark Repository after VAST Challenge 2017 is complete? YES

Questions

1 Characterize the sensors’ performance and operation. Are they all working properly at all times? Can you detect any unexpected behaviors of the sensors through analyzing the readings they capture? Limit your response to no more than 9 images and 1000 words.

Between-sensor correlations

If things were working as I'd expect, most sensors should have a correlation with each other for similar chemicals given their proximity. For instance, sensors at 5 and 9 should be giving similar values for the same, but this doesn't seem to always be the case.

Noise at Sensor 7

Monitor 7 seems to have much more noise than sensor 8 which is close by.

Noise at Sensor 3

Sensor 3 seems to have much more variability than the other sensors around it.

Sensor 4 Behaviour

Sensor 4s baseline is increasing constantly for all chemicals in December.

General sensor performance

In this view we can see how well, with some basic hierarchical clustering, sensors are performing across months, and across weeks for detection of different chemicals. We can see some sensors cluster together nicely, but in some periods, many have periods of increased noise. We would expect more consistent behaviour between sensors and to have those closer spatially, closer in the clusters also.

2 Now turn your attention to the chemicals themselves. Which chemicals are being detected by the sensor group? What patterns of chemical releases do you see, as being reported in the data? Limit your response to no more than 6 images and 500 words.

Dumping of hazardous chemicals early hours

We can see here that 2 harmful chemicals in particular, Chlorodinine and Methylosmolene are being emitted in to the environment constantly. There appears to be a concerted effort by the parties involved to emit Methylosmolene (purple) in particular in larger quantities between approximately 11pm - 5am. Additionally, Chlorodinine is being emitted through the day but some peaks can be seen in the early hours with the blue dots.
We can also see that AGOC-3A is detected more during the day than late at night, and that Appluimonia is detected at fairly constant levels throughout the day.

Shifts in where outliers are being detected

3 Which factories are responsible for which chemical releases? Carefully describe how you determined this using all the data you have available. For the factories you identified, describe any observed patterns of operation revealed in the data. Limit your response to no more than 8 images and 1000 words.

In the following analyses we look at the extremes of the data as indicators for who is emitting most of a particular chemical.

Methylosmolene producer

It would appear that the highest amount of Methylosmolene are being produced by Kasios given the intersections shown with the wind direction and monitoring stations. It seems likely however that Indigo Sol have also released this chemical. We only consider here releases above 20 PPM.

Chlorodinine producer

Chlorodinine seems to be being produced by Roadrunner.

AGOC-3A producer

The patterns would suggest that Kasios is the main producer of AGOC-3A, but Radiance also seems to create some of this chemical.

Appluimonia producer

Appluimonia occurs constantly in the data, and it's readings are fairly low. Here we plot those with the highest readings and can see that it's probably persistent in the environment anyway. See the activity on sensor 3 for example, it's not possible that this could come from a factory since the wind direction would have blown the particles away.

For the larger values we've seen for Appluimonia, it appears that they come from Indigo sol, with some signal to suggest output from Radiance.