ISSS608 2016-17 T3 Assign ASMIT ADGAONKAR conclusion

Recap/Summary of the overview provided by the Challenge setters:

• AGOC-3A can be considered less harmful in front of Methylosmolene or Chlorodinine
• Chlorodinine is quite harmful when inhaled or swallowed or through sensory organs
• Appluimonia emits odor and may not be termed harmful but can certainly affect quality of life.
• Methylosmolene is quite a toxic chemical to the extent that it was strictly regulated in the manufacturing sector and Liquid forms of Methylosmolene are required by law to be chemically neutralized before disposal.

Key Findings/Conclusions

Sensors

Monitor# 5 has failed to collect readings for Methylosmolene((by far one of the most harmful chemicals from the lot) at 12 pm in April, 6 am in August and at 8 am in December. In contrast, the monitor has actually gone on to record those numbers and assign it to AGOC-3A chemical. Similarly, it can be seen that Monitor#1 has failed to capture readings at midnight for all the chemicals for atleast 2-3 days in each of the months.

Light Air and Light Breeze have contributed to about 30-40% of the readings during day time (6 am to 6pm) whereas during night time (6pm to 6 am), gentle breeze seems to have increased it contribution to the readings for all sensors and for all chemicals, making light air, light breeze and gentle breeze as the major contributors for the readings. Based on the wind activity for the month of April, It can be inferred that the wind was strong enough to blow away the chemical readings on sensor 4. The wind activity sort of decreased in August and December, leading us to relate the cause of higher readings on sensor #4.

Sensor 6 is the closest sensor for all the factories and sensor 9 is farthest for Kasio and RoadRunner, whereas sensor 1 is farthest for Radiance and Indigo. A clustered tree that split the sensors into 3 clusters(based on their proximity to the factories) was utilized to infer that the sensor 6 is clearly the most closest to the factories whereas average proximity of sensor 5,9,7,4 fall in the same cluster/distance and sensor 3,8,2,1 fall in the last cluster of sensors that can be considered as sensors in the far reach of the factories. A general hypothesis can be framed to expect that the sensors in the close proximity would show higher pollutant readings. However, building a similar tree map for the readings of the sensors revealed that sensor 5 which relatively falls in close proximity of the factories demonstrates quite low readings in the month of April. The contribution of sensor 5 somehow picks up a bit in the month of the August and December, however given that sensor 5 has already been picked by us in point 1 of the above paper, it is clearly a matter to investigate. Further segregation of sensor 5 contribution by day and night time reveals that the readings falls even low during night time and night time is clearly the time where methylosmolene(by far one of the most harmful chemicals from the lot) is getting detected. Is this tampering of the monitor?

It can be inferred that the wind direction has largely been in the north-west direction and hence sensor 3 and 4 have managed to show readings on the higher side, with the exception of senor 4 readings for the month of April where the wind was too strong for it to capture sizable readings. On the other hand, even when the wind was flowing in the north/north east direction, sensor 5 and sensor 9 have repeatedly shown lower readings and hence demand further investigation.

A calendar map helped us understand the extent of pollutants that exists in the park as a whole. Besides, it revealed the times (2nd/6th April, 4th/7th August,2nd Dec at 12:00 AM) at which no reading was recorded by the sensors at all. This clearly demands further investigation to understand whether these were maintenance periods managed by the sensor administrators, and if these were indeed maintenance periods then it would be good to understand the approach that was followed to arrive at those specific dates. Based on the data provided and with the help of the above calendar map or area charts of the readings for the chemicals, it can be observed that the last couple of days of every month have relatively been quiet periods for pollutant readings. It would be worth suggesting the sensor administrators to see if these days can be utilized for any required downtime for the sensors. In addition, the hour of the downtime can be moved to sometime in the start of the evening as we wouldn’t want to miss out on methylosmolene(a very harmful chemical) readings whose activity increases as the night progresses and midnight is pretty much a peak time for it get captured.

Chemicals

It can be seen that all the chemicals are largely captured during their day times or business hours (6 am to 6pm), however Methylosmolene exhibits a different pattern by which it gets captured largely during night hours (6pm to 6 am). It would be worth investigating if this pattern of Methylosmolene combined with its night time exhibition is influenced by the sensors capability to capture that chemical when there is no sunlight or is it being released by the factories specifically at night time.

AGOC-3A is largely getting emitted middle of the month (say 13-16th of each month). It clearly demands further investigation on why this pattern is coming across. Has it got to do with the factories performing certain maintenance activity or goods processing cycle that causes this? Can factories be advised to alter their activity to try and balance the emissions across weeks or days to have the chemical reading fall well within an acceptable range ?

Appluimonia is seen getting captured regularly on monitor 3, noticeably when the wind has been in the opposite direction of the factories. It would be worth investigating if there are any other external factors in the park(other than the factories emission themselves) that are causing this to happen.

Responsible Factories

A tableau dashboard featuring air plumes at each of the sensor points and depicting the direction and speed of the wind coming from 16 directions with the corresponding plumes or the wind fans reach for each of the factory points have been utilized to capture the factories that could be possibly emitting any or all of those harmful chemicals. Based on these findings, we can infer that:

• Appluimonia is largely being emitted by Indigo.
• Chlorodinine is being emitted by RoadRunner.
• Methylosmolene is largely being emitted by Kasio, however RoadRunner can also be investigated for its Methylosmolene emissions.
• AGOC-3A is largely emitted by Kasio and RoadRunner.