Difference between revisions of "ISSS608 2017-18 T3 Assign Alejandro Llorens Moreno Visualization"

From Visual Analytics and Applications
Jump to navigation Jump to search
 
(7 intermediate revisions by the same user not shown)
Line 68: Line 68:
 
<th>Visualization</th>
 
<th>Visualization</th>
 
<tr>
 
<tr>
−
<td> <b>1.Campers </b>
+
<td> <b> 1. Sampling Distribution </b>
−
<br>Fig 7 provides the yearly visitor traffic calendar for the campers. The campers visited the reserve more often from May to Aug, possibly because this is the warm period of the year. The highest traffic of campers was observed in July 2015. There is a drastic drop in the campers, especially extended campers, from Q4 2015 onwards, which could be attributed to the colder weather.  </td>
+
<br> The figure provides a clear view of missing samples in key locations. Also a very uneven sampling distribution across locations. This is a cause of major concern. We can clearly see that are missing values for samples in Achara, Decha and Tansanee. Plus a very low level of samples taken in those sites. At the same time, we can appreciate a high level of samples in Boonsri, Chai, Kannika, Sakda specially in a range of years from 2005 to 2009. Why this sudden increase in samples? </td>
−
<td>[[File:gyf_updated8.png|700px|center]]</td>
+
<td>[[File:Sampling3.JPG|500px|center]]</td>
 
</tr>
 
</tr>
 
<tr>
 
<tr>
−
<td> <b>2. Rangers Trend </b>
+
<td> <b> 2.Methylosmoline count is limited </b>
−
<br>Fig 8 below reveals weekly activity pattern for rangers. In 8.1, the heatmap was configured to show the average stay duration for the rangers at various gates. We noticed the rangers would stay for extended durations at camping 8 (Mondays, 10am to 14pm) as well as gate 2 & rangerstop 1 (Mondays 6am – 11am, Wednesdays 13 – 16pm). The rangers could be doing inspection or maintenance works at this these locations. Looking at the reserve map, we can observe that ranger stop 1 and camping 8 are both located at the “dead ends” of the reserve, with no paths extending beyond them – it is likely that these two locations are surrounded with floras whereby periodic maintenance is required.
+
<br>Methylosmoline is the major contaminant chemical. However, there are only 3 years of samples: 2014, 2015 and 2016. The sampling distribution of Methylosmoline is very different for the locations. This is a cause of concern.
  
−
<br>In Fig 8.2 we could see the rangers gathered at the rangerbase and gate 8 (which is in close proximity to the ranger base) on Thursdays 14pm. It could be an indication that the weekly ranger meetings were held on Thursdays 14pm at the rangerbase.</td>
+
<td>[[File:Boxplot2.JPG|300px|center]]</td>
−
<td>[[File:gyf_updated9.png|600px|center]]</td>
 
 
</tr>
 
</tr>
 
<tr>
 
<tr>
−
<td> <b>3.Service Trucks</b>
+
<td> <b>3.Other chemicals have very uneven distributions in different locations </b>
−
<br>Fig 9 below shows the weekly movement pattern for service trucks at various gates. We noticed that there were a higher number of service trucks moved pass the “connecting path” on Thursdays, at two prominent timings: 1am and 16pm. This might be the scheduled delivery/pick up hours for the service trucks. </td>
+
<br> The figure shows Sulfides and Sulfates distributions of samples taken by location, as we can see they are very differently distributed with outliers clearly marked in locations like Chai or Boonsri </td>
−
<td>[[File:gyf_updated10.png|600px|center]]</td>
+
<td>[[File:Boxsulfides.JPG|300px|center]]</td>
−
</tr>
 
−
<tr>
 
−
<td> <b>4. Sightseeing coaches</b>
 
−
<br> <br>Lastly, Fig 10 shows the weekly movement pattern for sightseeing coaches. The sightseeing coaches seemed to be bringing the visitors to the reserve on fixed days and hours, as the darker blocks on the heatmap tend to appear in regular intervals. For example, the coaches tend to visit the reserve at below timings: 
 
−
<br>-Fridays & Sundays 3am <br>-Thursdays & Sundays 11am <br>-Sundays 16pm <br>-Mondays 22 pm </td>
 
−
<td>[[File:gyf_updated11.png|600px|center]]
 
 
</tr>
 
</tr>
 +
 
</table>
 
</table>
  
Line 103: Line 97:
 
<tr>
 
<tr>
 
<td>
 
<td>
−
<br>I have created a control chart to represent outliers in 1,2 or 3 standard deviations and show specific outliers in the data. Of particular concern is the contaminant chemical Methylosmoline. The user can select a specific chemical and explore outliers in the control chart.
+
<br> A major cause of concern is the average values of Methylosmoline in locations nearby the dumping site. I have created a control chart to represent outliers in 1,2 or 3 standard deviations and show specific outliers in the data. Of particular concern is the contaminant chemical Methylosmoline. The user can select a specific chemical and explore outliers in the control chart.
 
<td>The figure below shows the outliers of 1 standard deviation of Methylosmoline in two locations: Kohsoom and Somchair
 
<td>The figure below shows the outliers of 1 standard deviation of Methylosmoline in two locations: Kohsoom and Somchair
 
[[File:Concern.JPG|500px|center]]</td>
 
[[File:Concern.JPG|500px|center]]</td>
Line 113: Line 107:
 
</tr>
 
</tr>
  
 +
<tr>
 +
<td> Extreme Outliers analysis: I have performed several analysis in different chemicals for all locations. My analysis helps identify outliers that are positive even 3 standard deviations of the average (extreme). We can spot them in different locations at specific times. This is worth an in depth analysis per location to understand the meaning of these significant outliers.
 +
<td>
 +
[[File:Ultimo.jpg|500px|center]]</td>
 +
</tr>
 
</table>
 
</table>
  

Latest revision as of 20:47, 8 July 2018

Wildlife.jpg VAST Challenge 2017:Mystery at the Wildlife Preserve

Background

Methodology

Answers

Conclusion

 


Insights and answers to questions

Trends: Do you see any trends of possible interest in this investigation?

Patterns Visualization
1. Hight levels of Methylosmoline detected ”


There’s a sharp increase in Methylosmoline levels in 2016 in both Kohsoom and Somchair. Averages increase sharply in the 4 quarters of 2016. This is of particular concern because it’s the contaminant agent. This requires more investigation. In all samples of Methylosmoline for all quarters the measurement is of 130 approx for Somchair and 50 for Kohsoom. This is considerably higher than the average of 22.32 in Kohsoom and 53.50 in Somchair for the last 3 years.

Methyl.jpg
2.Water temperature has been increasing
Water temperature is cyclical and warmer in the months from June to September (summer). However, in 2016 there’s a higher average water temperature in all locations. To be specific, in 1998 the average water temperature in all locations was 12.95 degrees. While in 2013 is 13.89, in 2014 is 14.79, in 2015 is 14.09 and in 2016 is 14.74 degrees. Global warming and other external causes can obviously affect this measurement, however, it’s worth exploring further..
Watertemp2.jpg
3.There's been drastic changes in Sulfates


We can see a clear trend in the years after 2007 until 2012 when the average measurement for Sulphates is lower for all locations. But specifically in Kohsoom , Somchair and Busarakhan.

SulfatesAlex2.JPG
4.Other chemical changes


TLooking at Arsenic, Iron and Aluminium, we can determine there’s a huge release of these heavy metals: Arsenic in 2009 for all locations and specifically in 2010 for Kohsoom. Aluminium in Q2 2009. Iron in Q3 2003. Phosphorus peaks in different locations in 2006, 2009, 2014. This is a clear sign of drastic changes in soil or water. It's worth investigating all chemical changes.

Otherchemicals.JPG

Anomalies: What anomalies do you find in the waterway samples dataset? How do these affect your analysis of potential problems to the environment? Is the Hydrology Department collecting sufficient data to understand the comprehensive situation across the Preserve? What changes would you propose to make in the sampling approach to best understand the situation?

Patterns Visualization
1. Sampling Distribution
The figure provides a clear view of missing samples in key locations. Also a very uneven sampling distribution across locations. This is a cause of major concern. We can clearly see that are missing values for samples in Achara, Decha and Tansanee. Plus a very low level of samples taken in those sites. At the same time, we can appreciate a high level of samples in Boonsri, Chai, Kannika, Sakda specially in a range of years from 2005 to 2009. Why this sudden increase in samples?
Sampling3.JPG
2.Methylosmoline count is limited


Methylosmoline is the major contaminant chemical. However, there are only 3 years of samples: 2014, 2015 and 2016. The sampling distribution of Methylosmoline is very different for the locations. This is a cause of concern.

Boxplot2.JPG
3.Other chemicals have very uneven distributions in different locations
The figure shows Sulfides and Sulfates distributions of samples taken by location, as we can see they are very differently distributed with outliers clearly marked in locations like Chai or Boonsri
Boxsulfides.JPG

Causes of concern: do any of your findings cause particular concern for the Pipit or other wildlife? Would you suggest any changes in the sampling strategy to better understand the waterways situation in the Preserve?


Causes of Concern Visualization


A major cause of concern is the average values of Methylosmoline in locations nearby the dumping site. I have created a control chart to represent outliers in 1,2 or 3 standard deviations and show specific outliers in the data. Of particular concern is the contaminant chemical Methylosmoline. The user can select a specific chemical and explore outliers in the control chart.

The figure below shows the outliers of 1 standard deviation of Methylosmoline in two locations: Kohsoom and Somchair
Concern.JPG
Suggestions for sampling strategy: i suggest some changes in the sampling strategy: 1. More diligent sample taking in specific dates, for example every monday and thursday of the week (instead of random samples) 2. I suggest focusing on 3 groups: a main group comprising - Boonsri - Kohsoom - Busarakhan - Chai and Kannika. A second group comprising joined locations in the river like 1. Achara 2. Somchair 3. Sakda. A third group comprising: 1. Decha and 2. Tansanee. This way one could understand the impact of 1 contaminated location extending to other locations down the rivers.
Waterways Final.jpg
Extreme Outliers analysis: I have performed several analysis in different chemicals for all locations. My analysis helps identify outliers that are positive even 3 standard deviations of the average (extreme). We can spot them in different locations at specific times. This is worth an in depth analysis per location to understand the meaning of these significant outliers.
500px
Retrieved from ‘https://wiki.smu.edu.sg/1718t3isss608/index.php?title=ISSS608_2017-18_T3_Assign_Alejandro_Llorens_Moreno_Visualization&oldid=8289’