The novel coronavirus pandemic has disrupted the global food supply chain and productivity. According to the response of the local government, the locking down policy and international trade prohibition is applied to control the domestic infection cases. Although this action is necessary, it also provides the side effect of slowing down to achieving the sustainable development goals (SDGs) about zero hunger. The peoples which sensitive to food security will be starved in the short term because of stocking up foods. In the long run, the farmers and food-related industries cannot operate the business normally and directly affect the amount of product.
Berners-Lee, Kennelly, Watson, and Hewitt (2018) has stated that global food production is sufficient to meet the nutrient needs of humans in 2050. Although the food manufacturing sector can provide a satisfying amount, this fact is still opposed to the global starving situation. One of the problems is caused by the low efficiency of the delivery and processes in agricultural markets. The food was lost around 30% from the overall during transportation to final customers. (Gustavsson, 2011) According to the supply chain of Poland dairy products, as the case study of Lipińska, Tomaszewska, and Kołożyn-Krajewska (2019), the challenges are to maintain food quality, redesign packaging method and storage environment (e.g., carbon dioxide, air moisture, and sterilization), and breakthrough the commercial limitation. (e.g., the cost of utility and manpower that were used in the factory)
One of the possible solutions is the accelerating cycle of the food business. The modern technologies, such as machine learning, can manage the product stocks and match up the company to buyers. The central market is less significant because of the changing lifestyle of customers. The individual orders and customer’s needs become an opportunity to decrease food loss and accomplish the well-life being by using innovative stock management. According to the online food retailing study in Germany (Delfmann, Albers, Müßig, Becker, Harung, Schöneseiffen, Skirnevskiy, Warschun, Rühle, Bode, Kukwa & Vogelpohl, 2014), the shifting of food storage technology to grocery, farmers, and customers effect to the demand in the online food market. The estimated model presents that the market would grow up to 38% within five years and yielding 1.6 billion USD in Germany and makes the customer access to the food easier.
The purposed algorithm will assist local government in seeing a prospective food production, agricultural area, and international food trade. It will help the government to target and match business overseas to gain food based on the need of regional peoples. In this way, food chain management will be improved and maintain food security during the COVID-19 crisis. Furthermore, the government can apply the idea to a different scale and using the advantage of the program for both intercity and intracity levels.
This project obtained data from various resources. There are three categories of information including agricultural data, economic data, and geographical data. These three types of data were combined to create the record for the supply and demand for food around the world. Economic data includes information for world populations. Geographical data is about the cities of the world. Lastly, agricultural data is about an amount of food produced, climate data, and the use of the land around the world.
First, we made a system that can calculate the regional food supply using the information from two sources: namely FAOSTAT (giving the standard amount of 166 different types of food produced in each country by year), U.S. DEPARTMENT OF AGRICULTURE (showing the amount of energy-per-unit-weight for each type of food). Calculating those two data, we got the calories produced in each country. Also, our system used the Groundwater storage (GLDAS_CLSM025_DA1_D v2.2) data, MODIS in the most recent year, and GISS Surface Temperature Analysis (v4) for looking if there is an emergent situation, such as rapid-and-unexpected heat in a region, we will know the loss of ability to produce food in that area and notice that we need to support food in that area.
Second, we calculated the demand for food in each country using the data of the populations in different countries from World Bank, and the amount of calories that a person needs. This data matched with the supply data described above to name the countries that can produce more than consume and the countries that consume more than produce.
Third, after we collected the number of food surplus or deficit for the cities around the world, we gathered the position of the cities from Simple Maps. Then, we calculated the distances between all cities to roughly estimate the cost of transportation as we want to lower the cost of food.
In summary, the steps for developing our project are as follows:
The presentation file of the Food Fill Algorithm can be founded here.
Document References
[1] Berners-Lee, M., Kennelly, C., Watson, R., & Hewitt, C. (2018). Current global food production is sufficient to meet human nutritional needs in 2050, provided there is radical societal adaptation. Elem Sci Anth, 6(1), 52. DOI: 10.1525/elementa.310
[2] Gustavsson, J. (2011). Global food losses and food waste. Rome: Food and Agriculture Organization of the United Nations (FAO).
[3] Lipińska, M., Tomaszewska, M., & Kołożyn-Krajewska, D. (2019). Identifying Factors Associated with Food Losses during Transportation: Potentials for Social Purposes. Sustainability, 11(7), 2046. DOI: 10.3390/su11072046
[4] Delfmann, W., Albers, S., Müßig, R., Becker, F., Harung, F. K., Schöneseiffen, H., Skirnevskiy, V., Warschun, M., Rühle, J., Bode, P., Kukwa, C. & Vogelpohl, N. (2014). Concepts, challenges and market potential for online food retailing in Germany. Faculty of Management, Economics, and Social Science. University of Cologne.
Database References
[1] Groundwater storage (GLDAS_CLSM025_DA1_D v2.2) - distinguish drought areas that make land unprofitable for planting.
Link: https://giovanni.gsfc.nasa.gov/giovanni/#service=TmAvMp&starttime=&endtime=&dataKeyword=Ground%20water%20storage
[2] MODIS - provides data for land usage around the world. We use python programming to extract the pixels in photos from this database to acquire the amount of land in each category.
Link:https://modis.gsfc.nasa.gov/
[3] GISS Surface Temperature Analysis (v4) - provides a temperature map around the world. If there is a rapid-and-unexpected heat in a region, we will know the loss of ability to produce food in that area and notice that we need to support food in that area.
Link: https://data.giss.nasa.gov/gistemp/station_data_v4_globe/
[4] FAOSTAT - provides standard data about the number of food each country can produce yearly in more than 150 categories.
Link:http://www.fao.org/faostat/en/#home
[5] CountryPopulation - learn how much food calories each area needs.
Link:https://data.worldbank.org/indicator/SP.POP.TOTL
[6] Calorieper-personperday
Link:https://ourworldindata.org/food-supply
[7] Foods to Calories - calculate total calories a country can produce.
Link:https://fdc.nal.usda.gov/fdc-app.html#/food-details/485474/nutrients
[8] CountryBorder - observe all the adjacent countries that sending food is easier.
Link:https://github.com/geodatasource/country-borders/blob/master/GEODATASOURCE-COUNTRY-BORDERS.CSV
[9] Main cities around the world (Capital) - identify hubs for food transportation.
Link:https://simplemaps.com/data/world-cities
[10] Latitude and Longitude of the cities in the world - collect all main cities to estimate distances between two cities.
Link:https://simplemaps.com/data/world-cities
[11] Country code - This data is -or-three digit codes that represent countries’ names. We use it because each country’s name is very long
Link:https://datahub.io/core/country-codes
[12] Global Population Data - observing the population number in each country.