Using Big Data and Computer Learning in the Lab

[April 2020]

Hi! My name is Oliver Allen, but most people call me Mel. I’m a second year student studying Computer Science and Math with a minor in Art History, and I also play marimba when I’m not studying or writing programs. I started working at the Critical Food Studies Lab in January of 2019 doing basic statistics, but now I am focused on applying my skills in computer science and machine learning to analyze data surrounding food justice and sustainability.

I started the semester by working with Lab Director Angela Babb to create a dataset of average food consumption and nutrient profiles to assist in analysis of the Thrifty Food Plan calculation. The Thrifty Food Plan is the basis of how the USDA allocates Supplemental Nutrition Assistance Program (SNAP) benefits to over 42 million people annually, but the latest released calculation was done with data from 2001, which is nearly 20 years old. In order to perform a relevant analysis of the Thrifty Food Plan calculation we needed an updated dataset of food consumption and relevant nutrient profiles for each of the foods in the USDA Dietary Guidelines for Americans. I had to approximate the dataset used by the USDA with something built from publically available data, so I ended up downloading all of the responses to the National Health and Nutrition Examination Survey (NHANES) for 2015-2016 and working with the data in R to separate it into each of the age-sex groups specified by the Thrifty Food Plan. Each row was a food group (for example provolone cheese, roast beef, Dippin’ Dots, etc.) and there were two columns representing national consumption data and then information on the food’s nutrient profiles. Eventually we had a dataset that could at least in part approximate the one used for the Thrifty Food Plan calculation and facilitate further analysis of the USDA’s model.
In the latter half of the semester I worked to apply machine learning techniques to data about behavior surrounding switching to a sustainable diet. I used data from a survey given by the Sustainable Food Systems Science research group at IU to approximately 500 heads of households in Indiana, and I implemented a machine learning model to predict behavior around switching to a sustainable diet from demographic data. I also used this model to analyze which demographic features are most important when deciding whether a person will switch to a sustainable diet or not, or whether they will switch gradually over time versus switching quickly due to an event or crisis. I built additional models for each of these problems to further analyze the influence of each feature in the prediction, and I hope to continue looking into applications of machine learning with data around food security and sustainability to gain insight into why people make the choices they do surrounding food and diet. 

Presentation: Leuthart, Kassandra, Laxmi Palde, Nicholas Monroe, Oliver Allen, Kathleen Lich, Angela Babb and Daniel Knudsen. 2019. Farm Justice and Parity Pricing. Paper presented at the Annual Meetings of the American Association of Geographers, April 3-7, Washington, D.C. 

Babb, A., Czebotar, K., Allen, OM. (2021) Bloomington Food Access Report. 

Food Deserts of Central Indiana

[April 2019]

My work in the Critical Food Studies Lab has revolved around understanding food deserts in Central Indiana. A large part of my work is “tool-based”, meaning I apply many different Geographic Information Systems (GIS) techniques in order to discover and illuminate trends not easily appreciated within large datasets. Additionally, my work revolves around applying mathematical principles to the challenge of food deserts. Overall my work is data based, with large importance being placed on the interpretation and manipulation of data.

Much of the work I performed this fall was concerned with data mining and database building. Geographically, my research location consists of a two-county ring surrounding Marion County, Indiana.  In these counties, census tract data were collected concerning population sizes and each census tracts geographically weighted center. From the population data, a “W-Matrix” was built to address the population size of each census tract. From the centroid data, a “D-Matrix” was built to analyze the time it would take to drive from each centroid to every other centroid. In order to create the D-Matrix, I used a network analysis tool in ArcMap (the program I use to perform my GIS tasks). In ArcMap, there is a series of network analysis tools that perform a variety of functions.  As the name suggests, each network analysis function is dependent on a “network” of sorts in order to perform each said analysis. For my work, I used a “network” of streets and centerlines consisting of every street and centerline in North America.

For my analysis, I elected to use an OD cost matrix. This tool is ideal for the D-Matrix due to the values it accumulates. The OD cost matrix accumulates both time and distance values between two points. The OD cost matrix draws “lines” based on the network given accumulating data on the distance and time it would take to traverse these “lines”. The lines form a matrix but they are in actuality routes that carry data, very similar to the routes seen in Google Maps for example. In ArcMap, all constraints were lifted with the exception of what vehicle I would use. Each time was calculated using a single occupancy vehicle. And so through performing the OD cost matrix a network of lines was created. A line is produced traveling from each centroid to every other centroid. With a total of 530 census tracts, the OD cost matrix consisted of 280,900 lines. Now that’s a lot of lines! From those lines, I extracted all the time data and created a time database within Excel. From the time database, all the data is synthesized into the D-Matrix.  The D-Matrix is rather large; keep in mind its 530 by 530 census tracts, a total of 280,900 data points. In order to synthesize the D-Matrix in a quick and easy manner, I used an OFFSET function within Excel. I also tried to build and use a macro for this but found the OFFSET function to be simpler and much more user-friendly. For those unfamiliar with Excel or the OFFSET function, it is a tool that moves columns or rows of data into a matrix. Rather than copying and pasting 530 columns of data, the OFFSET formula will do it quickly and easily. If you are having trouble moving columns of data into a matrix, much like I was, here is an example of the formula I ended up creating: =OFFSET(drv_tms!$F$2:$F$279842,COLUMN()-COLUMN($D$4)+((ROW()-ROW($D$4))*(ROWS(drv_tms!$F$2:$F$279842)/529)),0,1,1) From the D-Matrix I then created an “S-Matrix” which is concerned with various time limits or constraints The S-Matrix is a binary analysis of the D-Matrix. It analyzes the time it takes to travel from each centroid under certain time limits. The time limits I used for the S-Matrix were 5, 10, 15, 20, 25, 30, and 35 minutes. Again the S-Matrix is binary, meaning, for example, with the 5-minute time constraint, if the travel time was under 5 minutes a “1” was used to represent that line. If the travel time was over 5 minutes a 0 was used. Binary for this example is just true and false, 1 being true and 0 being false. From these three matrices, my next step is to create covering models and running said models through solver.

Blog: Food insecurity among older Americans

[June 2020]

I’ve been working with the Critical Food Studies lab since October of 2019; while most of my work at the lab has been assistive, from data digging to paper reviewing, I am also positioned between the critical food studies lab and the Sustainable Food Systems Science team. I am currently working with the “Complex Food Provisioning Strategies and Food Insecurity among Low-Income Older Americans” project. Our main research objectives are determining what food insecurity looks like in older Americans, how different times of the year (as well as changes throughout their lives) affect food security, and what food programs around local and rural south-central Indiana exist and how they might be improved.
As part of this work, I was involved in attending focus groups in 4 different counties with service providers and seniors in the area, and from these groups I gained a better understanding of how food insecurity affects seniors. One major finding I have taken away from the focus groups is how physical barriers affect food insecurity, including personal health issues (like mobility or chronic diseases) as well as physical access (for example transportation); Other important issues came up, such as the financial accessibility of food and how living alone affects eating habits. Through all these and other obstacles, however, seniors in south central Indiana have adapted to these common food insecurity issues by supporting each other in number of ways, including sharing meals and rides, learning how to adapt to income differences through stretching food, sales, and the use of food pantries, meal sites, and SNAP. Lastly, we gained information on the problems and recommendations of local assistance programs, including the loss of meal sites, rules that restrict services, and critiques of the quality of foods offered in these programs.
After attending these focus groups my work involved creating summaries and transcribing the audio for further analysis, and headway into the next phase of the project: coding the transcripts through Nvivo and working with a smaller team to compare findings and outline the main themes of the focus groups. As we have wrapped up the focus groups our next phase involved creating and sending out surveys to a larger population of older Americans in rural Indiana.
In the midst of creating the survey, COVID-19 hit Indiana and our team decided to include questions relevant to circumstances before and during the COVID-19 crisis to better understand the impact the virus has on food security amongst seniors. We hope to gain more information through the survey answers as well as the post-survey interviews we plan to conduct this summer. While working with this team I have learned many new skills like qualitative analysis of transcripts, holding focus groups, and creating a survey; I hope to continue gaining skills as we further our research this summer and fall.

Publications

Nantz, Erica L., Maxx B. Millstein, Hannah F. Davis, Kayla H. Kaplan, Kamila Czebotar, Angela M. Babb, Laxmi Prasanna R. Palde, Thaddeus Grantz, and Daniel C. Knudsen. 2020. "A commodity-based, continuous surface approach to defining food deserts: An example from rural South-Central Indiana." Local Environment. https://doi.org/10.1080/13549839.2020.1845638. 

Kayla H. Kaplan, Kyle J. Kirk, Kathleen M. Lich, Laxmi Prasanna R. Palde, Christopher Van Allen, Erica L. Nantz, Kassandra R. Leuthart, Scott M. Robeson, Hannah F. Davis, Jordan Blekking, Brian P. Healey, Kamila Czebotar, Angela M. Babb, and Daniel C. Knudsen. Accessibility to emergency food systems in south-central Indiana evaluated by spatiotemporal indices of pressure at county and pantry level. Nat Food 1, 284–291 (2020). https://doi.org/10.1038/s43016-020-0079-9 

Babb, A., Czebotar, K., Allen, OM. (2021) Bloomington Food Access Report. 

Understanding Historical Agricultural Trends in Indiana

[March 2019]

My research with the Critical Food Studies Lab over the past year has primarily consisted of collecting and analyzing historical data on agriculture in Indiana. These data come from the USDA’s Census of Agriculture. Approximately every five years, the census collects information about farmland, farmer demographics, crop and livestock production, and the associated economic costs and gains.
During the fall semester, I gathered data on the production of specialty crops, namely fruits, vegetables and nuts. I used these data in tandem with a list of all farmers’ markets in the state, collected by Kassandra Leuthart. My goal was to determine whether there exists a correlation between specialty crop production and the existence of farmers’ markets in Indiana at the county level. Through statistical analysis, I concluded that that relationship does not exist. What I found was simply that crop production has decreased overall in Indiana, while farmers markets continue to grow in popularity. This implies that the emergence of farmers’ markets does not rely on an increase in local specialty crop production.
This semester I collected data on the age, sex and race of farm operators in Indiana. I am using this information to perform statistical and spatial analysis that will help food scholars understand the historic and geographic patterns that exist in these demographic data. So far, I have found an increase in the average age of farmers since the 1980s. I have also seen an increase in the number of female and racial minority farmers starting around the 1990s. These numbers reveal that farming in Indiana has become more diverse in the past few decades, albeit by a relatively small amount. Using mapping software in my analysis will allow me to look at patterns both temporal and spatial. The insights gleaned from this research will provide food scholars with a better picture of who manages farmland in Indiana, and where they are located.
I am also currently working with Green Camino, a local compost collection company. Green Camino collects and composts household food waste, helping Bloomington residents divert their organic waste from traditional waste streams and reduce their carbon footprint. Work that Hannah Gruber and I performed using GIS helped the company match their existing customer addresses to their corresponding city sanitation route, which will allow the company to plan their future pickup routes in coordination with trash and recycling collection. It was rewarding to be able to use my spatial analysis skills to do work that aided a local business. I hope to continue to collaborate with Green Camino to do surveying and story mapping work that will help them expand their customer base.

BIPOC farmers in Indiana

[March 2021]

Hey everyone! My name is Isabella DeMarco and I am a Sophomore here at IU studying International Studies and Environmental and Sustainability Studies. I joined the Critical Food Studies lab this January 2021 and have really enjoyed getting to know other individuals passionate about the intersection of food and social justice. 
    At the beginning of Fall 2020 I was admitted into the Sustainable Scholars program run out of the IU Office of Sustainability. I was assigned to a project working alongside the amazing faculty members, Dr. Angela Babb, Dr. Julia Valliant, and Dr. Kurt Waldman, all affiliated with Sustainable Food Systems Science. Our project is designing an antiracist research platform to study racial equity within the Indiana agricultural system. 
    Although the project is constantly evolving, we intend to produce an annotated bibliography and a collection of pilot interviews with African American farmers in Indiana. The annotated bibliography will include a list of literature on the historical and present day experiences of BIPOC farmers in Indiana. The pilot interviews seek to decipher what is being left out of research on Black farmers in Indiana, and also give us insight into what needs to happen in future research regarding the topic. 
    As expected, the annotated bibliography process has been less fruitful than we would have hoped. Using the PSALSAR literature review method, we have found that many sources available on search engines such as Google Scholar, ProQuest, the Indiana University Libraries and many other databases do not specifically address our research topic. There is literature on racial discrimination within the United States agricultural system as a whole; however, few sources focused on this issue in Indiana exists. 
    This notion has been brought up in the pilot interviews with Black farmers from around the state. We have currently interviewed five farmers, and each have echoed the claim that there is a severe lack of research into racial discrimination of BIPOC farmers in Indiana. Although the research community may not yet be aware of or acknowledge the underlying issues these farmers have faced in the past and are still facing now, every individual I spoke with is involved with one or more projects promoting BIPOC individuals and communities in agriculture. 
Owning land and farming for these African American individuals serves a form of resistance and resilience. Learning about these individuals farming stories has been incredibly enlightening and uplifting, but it also underlines the crucial need for their stories to be heard and the oppressive system to be changed and exposed. I look forward to continuing to learn more about how research can contribute to addressing this need for justice. 

History of diversity and effects of discrimination in the Indiana food system

[October 2021]

Hi all! My name is Lucy Lippman, and I’m a junior at IU studying mathematics, economics, geography, and French. I’ve been passionate about sustainability since my high school environmental science class, and joining the Critical Food Studies lab during my sophomore year has shown me how just and local food systems coexist with environmental sustainability in the state. 
Last fall, I was admitted into the Sustainability Scholars program, and I worked with Dr. Shellye Suttles, Dr. Angela Babb, and Claire Frohman on a paper exploring the history of diversity and effects of discrimination in the Indiana food system. Specifically, I’ve been looking at metrics from the Bureau of Labor Statistics (BLS), the Census, the Department of Agriculture (USDA), and other national agencies for data on food system employment and food assistance program participation by race, ethnicity, and gender.
For the most part, the methodology I’ve been following comes from a document by the Michigan State University (MSU) Center for Regional Food Systems. To understand trends in food system employment across demographics, a lot of MSU’s metrics revolve around wages. Unfortunately, relevant data on wages and demographics are published only nationally, not at a regional or state level. To best understand employment trends by race, gender, and ethnicity in Indiana, we created the Specific Occupation Adjusted Percentage (SOAP) Index to illustrate the difference between the percentage of a demographic in an occupational field and the percentage of that same demographic in the entire Indiana labor force. For instance, in 2010, 3.37% of all workers in food preparation and serving-related occupations, as defined by BLS, were Black men, while Black men made up 3.13% the Hoosier labor force at that time. The resulting SOAP index is -.24%. The small magnitude denotes no large difference between the Black male composition of the workforce and of food preparation and serving-related occupations, while the negative signage indicates the given demographic is more represented in the Indiana workforce than in the specific occupation. Large magnitudes and positive signages represent the opposite. The SOAP Index evaluates for equity, presuming that an equitable employment system will not exhibit large differences between the composition of the labor force and the composition of workers in specific occupations. It assumes freedom of choice, of mobility, and of cultural axioms that would otherwise impact the demographic compositions of certain occupational fields. 
This semester, I’m continuing work on the diversity metrics paper, fine-tuning my work from last semester and making it more cohesive with Shellye’s, Angela’s, and Claire’s work on the subject. I’ve also joined Dr. Knudsen on a working paper observing service accessibility in the rural Indiana Uplands. I look forward to continuing with the Critical Food Studies Lab, researching inequity in Indiana. 

An inventory of institutional purchases in Indiana

[March 2020]

Hello! My name is Marie and I’m currently a third year student studying Environmental and Sustainability Studies with a concentration in Sustainable Food Systems. I’m also working toward certificates in Geographic Information Systems and Global French Studies.
Currently, I am researching institutional purchasing habits with my advisors, Jodee Ellett and Angela Babb. Last fall a survey was sent out through qualtrics to Indiana institutions such as K-12 schools, universities and colleges, hospitals, and correctional facilities. The survey included questions about how many people the institutions feed as well as how much money they spend annually. The survey then inquiries about local food purchasing and how often institutions are considering where their food is coming from. At this point, two rounds of the survey have been sent out and we are analyzing the results.
In Indiana, 90% of food sales come from out of state purchases. That is to say, only 10% of the food that we eat was grown or processed in Indiana. The money that we are spending on food is not stimulating Indiana’s economy. This statistic is especially shocking considering over three fifths of the land in Indiana is agricultural land. The purchasing of food by K-12 schools, universities, hospitals, and other institutions is incredibly important. For example, more than one million lunches are served in Indiana K-12 schools each day. Considering this enormous purchasing power, a shift in where purchased food is grown would have a substantial impact.
Oftentimes, institutions are unaware of how to source food locally. When you are concerned with feeding over 5,000 people each day, it seems a bit cumbersome to switch up where you source your food from. Hopefully this research highlights the opportunities for farmers and institutions to work together. Of course, this could be catalyzed through government policy. Considering this research is modeled after research done on institutional purchasing in Vermont, the possibility exists for Indiana institutions to be incentivized to prioritize purchasing local food. 

White supremacy at the Bloomington community farmers market

[February 2021]

Hello all! I’m Isis, a senior at IU, doing research in the Critical Food Studies lab. As a new lab attendant, I've been honored to work alongside incredible mentors and students who have introduced me to critical issues involving the food system, especially in Southern Indiana.   As Black History Month comes to an end, I want to share about a journal article I am helping to write. The “White Supremacy at the Bloomington Community Farmers Market” piece, coauthored by Dr. Angela Babb and Megan Betz, details issues pertaining to the local food and agriculture system in Southern Indiana, as well as the residents of Bloomington.
 
   The goal of our article is to discuss the presence of white supremacy within the local food system, beyond the specific and significant issues that arose with the Bloomington Farmers Market in 2018. The appearance of white supremacy is part of a larger, painful history of systemic racism, which has colonized the food system and facilitated even greater food insecurity. The introduction of hate groups, inspired by white supmacist beliefs, has left marginalized residents of Bloomington feeling unsafe.
 
   One of the topics we also plan to elaborate on within the paper includes nostalgia surrounding farmers markets and local food. Nostalgia in the food system continues generational knowledge, at times nostalgia removes historical relevance. Agriculture, and the food system within the United States, historically has been shaped by Indigenous and Black communities. After colonization, food began to be taken over by Europeans, who did not respect the land. Now, many of those who are leading farmers are typically descendants of those colonizers and settlers, taking away space and land opportunity from BlPOC (Black, Indeginous, People of Color).
 
 Other topics in the paper include public safety regarding the presence of hate groups affiliated with white supremacy, first amendment protections, and attention to community hate groups. Overall, the research for the article has involved readings to understand white supremacy in Southern Indiana, as well as coding content for Nvivo and retaining useful information for dismantling white supremacy in the local food system.
 
   Looking to find ways to unsubscribe from and dismantle white supremacy? Thanks to diligent community members such as Dr. Angela Babb, farmers markets with the purpose of equality and accessibility have created a safe space for marginalized community members to buy local food. Examples of these markets in the community include the Peoples Market and the Plant Truck.