Fishing for Answers

Michael Wang
Posted on Jul 29, 2019


Topic: 11 years of North Atlantic Fishery catch reports from the ICES cross-referenced with IUCN endangered species list.

Why care about fish? 

Fisheries often aren't the first things that come to mind when we think of our modern world; so why should we care about them? 

  1. Fishing is a cornerstone of the global food industry. Not simply in the form of direct human consumption (which is projected to continue growing into 2050 (Comtrade 2019)), but in the production of fish meal (accounting for ~50% of fish use) which is fed to grow our livestock (chicken and pork). 
  2. Environmental biomarkers: in the context of our changing planet, fish populations and sustainability show fish as a key biomarker to track and measure the impacts of our collective impact on the planet.   

The Story of Newfoundland Cod

By Lamiot - Own work, CC BY-SA 3.0,

What if we didn't monitor fishing? A parallel story located in the Northwestern Atlantic tells a chilling tale. In Newfoundland, the cod industry was booming and expanded rapidly in the 1950's as new technologies like deep sea trawling, radar assisted fishing, and enhanced tracking techniques helped fishermen catch more fish than ever before. While there was a short term windfall, ultimately the natural cod population was not able to support such demand and began to fall precipitously. By the time the government stepped in and declared a moratorium on cod fishing in 1992, the biomass of the Northwest Atlantic cod had fallen to 1% of former levels. This ultimately led to the biggest industrial closure in Canada causing 35,000 people to lose their jobs overnight. The sister species of this cod is one of the fish I look at in this exploratory study on fishing in the northwest Atlantic. 


The data come from reporting for the Food and Agricultural Organization (FAO) of the United Nations. Fish catch is reported in tonnes of live fish weight over the period of 2006 - 2017 and broken down by country, species, area, etc. Because the data did not include endangered species status, I merged another data table containing conservation status (7 stages from Least Concern to Extinct) from the International Union for Conservation of Nature (IUCN) to perform further analysis on the dataset. 


Fishing Nations

During the Exploratory data analysis, I found that Norway was the dominant fishing nation in the region, followed by Russia and Iceland. Though notably, there were a number of Asian nations around the world that also fished in this Northwest Atlantic area suggesting profitable fish there or the possible exhausting of their own fish stocks closer to home. The rate of capture of most of these European nations seemed fairly consistent and grew with the time. 


Endangered Status 

After appending the endangered status to my data, I found that most of the species that were recognized on the IUCN Red List were of the Least Concern category. Not surprisingly, worldwide fishing policies have been enacted since the Newfoundland fishing industry collapse to limit the amount of overfishing in threatened areas. However, I found it notable that over 25% of the fish caught in this area was considered "Vulnerable." Upon further inspection, I found that the cod population (sister species to the Canadian cod) was among the vulnerable category. 

Yearly Progression

While some species did not show an increase in catch rate over time,  some of the species with the largest overall capture volume (by weight) did show increases in their rate of being harvested. This combined with the increased demand for fish over the past few years would require researchers to carefully monitor fish stocks (data for which is more scant than capture rates) to make sure populations remain at a sustainable level. By exploring the plots, it is possible to identify the changes in fishing catch over time by country or by species. 

Future Directions

This project served as an early exploratory look at the fisheries of the Northwestern Atlantic. Based on what the data suggest, the next steps would be to conduct surveys on the current stocks of each of these vulnerable fish species and compare them over time with their catch rate over the years. Additionally, this further analysis could reveal useful life cycle information to precisely measure the time frame that juvenile fish become adults and replenish the populations. With careful management and data analysis, we can ensure that the fisheries of the world can supply us with jobs and food for generations to come.


Shiny App:

About Author

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp