IS428 2017-18 T1 Assign Yorisan Khosugi

Overview

Mistford is a mid-size city is located to the southwest of a large nature preserve. The city has a small industrial area with four light-manufacturing endeavors. Mitch Vogel is a post-doc student studying ornithology at Mistford College and has been discovering signs that the number of nesting pairs of the Rose-Crested Blue Pipit, a popular local bird due to its attractive plumage and pleasant songs, is decreasing! The decrease is sufficiently significant that the Pangera Ornithology Conservation Society is sponsoring Mitch to undertake additional studies to identify the possible reasons. Mitch is gaining access to several datasets that may help him in his work, and he has asked you (and your colleagues) as experts in visual analytics to help him analyze these datasets.

Mitch Vogel was immediately suspicious of the noxious gases just pouring out of the smokestacks from the four manufacturing factories south of the nature preserve. He was almost certain that all of these companies are contributing to the downfall of the poor Rose-crested Blue Pipit bird. But when he talked to company representatives and workers, they all seem to be nice people and actually pretty respectful of the environment.

In fact, Mitch was surprised to learn that the factories had recently taken steps to make their processes more environmentally friendly, even though it raised their cost of production. Mitch discovered that the state government has been monitoring the gaseous effluents from the factories through a set of sensors, distributed around the factories, and set between the smokestacks, the city of Mistford and the nature preserve. The state has given Mitch access to their air sampler data, meteorological data, and locations map. Mitch is very good in Excel, but he knows that there are better tools for data discovery, and he knows that you are very clever at visual analytics and would be able to help perform an analysis.

The Task

General task

The four factories in the industrial area are subjected to higher-than-usual environmental assessment, due to their proximity to both the city and the preserve. Gaseous effluent data from several sampling stations has been collected over several months, along with meteorological data (wind speed and direction), that could help Mitch understand what impact these factories may be having on the Rose-Crested Blue Pipit. These factories are supposed to be quite compliant with recent years’ environmental regulations, but Mitch has his doubts that the actual data has been closely reviewed. Could visual analytics help him understand the real situation?

The primary job for Mitch is to determine which (if any) of the factories may be contributing to the problems of the Rose-crested Blue Pipit. Often, air sampling analysis deals with a single chemical being emitted by a single factory. In this case, though, there are four factories, potentially each emitting four chemicals, being monitored by nine different sensors. Further, some chemicals being emitted are more hazardous than others. Your task, as supported by visual analytics that you apply, is to detangle the data to help Mitch determine where problems may be. Use visual analytics to analyze the available data and develop responses to the questions below.

The specific tasks

1. Characterize the sensors’ performance and operation.
a. Are they all working properly at all times?
b. 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.

2. Now turn your attention to the chemicals themselves.
a. Which chemicals are being detected by the sensor group?
b. 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.

3. Which factories are responsible for which chemical releases?
a. Carefully describe how you determined this using all the data you have available.
b. 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.

Answers

Qn 1. Sensors' performance and operation

Qn 1.a. Are the sensors working properly at all times?

A brief look at the sensor data shows that readings are recorded every hour every day over the course of three months, namely April, August and December. To answer this question, we have to find out if there are readings captured for every 1-hour interval for every one of the 9 sensors, as it should be, throughout the entire 3-month recording period. To confirm this, a Gantt view chart can be made in Tableau from the Sensor Data excel file in the Assignment Data provided. This can be done by adding the Dimensions/Measures to parts of the representation as specified below and creating the chart.

Add to	Dimension/Measure
Columns	Hour, Day
Rows	Month, Monitor
Marks (Colour)	Monitor

As can be seen in the chart above, there is some missing data as indicated by the missing squares (not including those on 31st April as April only has 30 days). Specifically, there is no reading recorded at 12 a.m.(Hour 0) on the following dates:

a. 2nd and 6th April by all monitors
b. 2nd August by all monitors except Monitor 3, and 4th and 7th August by all monitors
c. 2nd December by all monitors, and 7th December by all monitors except Monitors 6, 7 and 8

All other hours of each recorded day, not shown in the image above, have no missing readings. The missing readings indicate the times that the sensors were not working properly. It can therefore be concluded that it is untrue that the sensors were working fully at all times.

The missing readings are all at 12 a.m., and within the first week of each month. Therefore, one likely reason is that the staff in charge of the monitors may be setting up or testing the monitors at that time. It is also possible that they are performing checks after the first few days of readings or making adjustments due to errors found, and are doing so as early as possible to affect as few readings as possible.

Qn 1.b. Can you detect any unexpected behaviors of the sensors through analyzing the readings they capture?

To assess the readings from a broader overall perspective, a line graph can be plotted using Tableau. For good readability and reduced clutter, the hours have been excluded to produce visualizations which go no more specific than daily summed readings. This can be done by adding the Dimensions/Measures to parts of the representation as specified below and creating the graph.

Add to	Dimension/Measure
Columns	Month, Day
Rows	Reading
Filters	Month
Marks (Colour)	Monitor

In addition, trend lines are added to provide an idea of the overall trend of the readings of each monitor.

The above is the graph for the month of April. From this visualization, the following observations can be made:

1. Each monitor has differing trends. All monitors have a rather consistent unchanging trend, except for Monitor 6, which has a decreasing trend.

2. By looking at the trend lines, it can also be seen that the monitors have differing average levels. It is clear that Monitor 3 (red line) has the highest values of readings in general compared to the rest. This may be because monitor 3 is located in an area which picks up a higher amount of chemicals on average, even with differing speeds and directions of wind. Or, monitor 3 could be situated very near one or more factories, which may also have high rates of production and hence release more chemical waste.

3. The readings captured can be rather consistent on some monitors, and be very erratic on others. For example, Monitor 3 (red) recorded fairly consistent readings, with only 2 minor spikes in value on 7 and 17 April. On the other hand, Monitor 6 (yellow) recorded extremely erratic readings, with huge spikes on 2, 6, 9, 15, 21 and 25 April. This might be because monitors such as monitor 3 are less reliant on wind to pick up chemicals due to location or other factors (hence the stable readings), while monitors such as monitor 6 require wind that is strong or in a specific direction to record significant readings (hence the erratic readings).

4. The most noticeable spike is on 15 April, where readings on three monitors recorded extremely high readings, namely monitors 6, 7 and 8 (highest reading of the month, at 277.0). This may indicate that one or more factories was releasing an extremely large amount of chemicals into the environment on 15 April.

Next, a look at a visualization similar to the above, but of all three months in one comprehensive view, is observed below.

From this obervation, the following observations can be made:

1. In the month of August, monitor 3 (red) once again recorded the highest average readings for the month, but it was superceded in December by Monitor 4 (turquoise) which recorded much higher readings than monitor 3 in that month. This may be because the production levels of a factory situated near Monitor 4 happened to be much higher that month, resulting in a subsequent surge in chemical output picked up by monitor 4. This is also supported by the fact that from the gradient of the trend lines, Monitor 4 shows an increasing trend in readings in both August and December, and from the vertical position of the trend lines, has readings steadily increasing across the three months (one of the lowest in April but second highest in August, and highest among all monitors in December). These pieces of evidence may mean that the factory (or factories) near Monitor 4 may be embarking on a year-long expansion project.

2. The highest reading among all three months was 600.7, recorded on 13 August on monitor 3, much higher than the second highest, at 421.7 recorded on monitor 4 on 18 December. This could be because on 13 August, a factory (or factories) situated near monitor 3 released, in one go, the highest amount of chemicals ever in the span of the 3 recorded months.