Ancora indeciso? Non esitare, entra e scorri tra le immagini dei centinaia di nuovi annunci giornalieri che le migliori escort di Milano pubblicano sul nostro sito. Solo pochi clic ti separano dal…
A Succinct exploration of the possible impacts of data science on the twelfth (12th) Sustainable Goal Development in the current West African setting.
Marie Curie alleged that “You cannot hope to build a better world without improving the individuals. To that end, each of us must work for his own improvement and, at the same time, share a general responsibility for all humanity, […]”(BrainyQuote, n.d.)
Responsibility is a concept that may sometimes seem foreign. It appears rather easy to deny it than to accept its impacts on our lives.
The twelfth (12th) of the seventeen (17) Sustainable Development Goals (SDGs) for 2030 is specified as follows “Responsible consumption and production”. It is important to understand that ensuring sustainable consumption and production patterns can only be possible if, every single inhabitant of the planet earth, participates in the improvement of the current food, production, and supply chains, within their reach. It is not solely the duty of economically developed countries or large and transnational companies, but it is equally the duty of every household across the world.
The focus of this article will be the following sub-goals :
· 12.3 “By 2030, halve per capita global food waste at the retail and consumer levels and reduce food losses along production and supply chains, including post-harvest losses.”
· 12.5 “By 2030, substantially reduce waste generation through prevention, reduction, recycling, and reuse.”
· 12.a “Support developing countries to strengthen their scientific and technological capacity to move towards more sustainable patterns of consumption and production.”
(“SDGs .:. Sustainable Development Knowledge Platform,” n.d.)
By focusing on these targets, this article seeks to explore how technology mainly data science and machine learning, can be used to address food waste along the food, production, and supply chains.
According to the Newfood magazine, with all things being equal and considering the worldwide growing population is estimated to reach 9.8 billion people in 2050. Taking into account the changing diets because people divert more and more from a rich plant-based diet to a rich meat produce diet, the world will need 69% more food calories in 2050 than in 2006. (“Feeding the world: Food security as a global challenge,” n.d.)
However, there is knowledgeably no more new land to exploit unless we also exploit forest land which cannot be considered as a responsible and sustainable pattern. Additionally, the increasing urbanization might even cut down the current hectare’s numbers of land available for agriculture.
Another conflict is that the current agriculture level itself is a source of concern with regards to the target 12.a because the patterns of production are not sustainable.
Having established that the intensification of agriculture on existing land may not be the more sustainable solution, this article will now consider how the reduction of food waste may be proven more viable.
It is estimated that up to 50% of the total food weight is wasted every year. (“Feeding 9 Billion | National Geographic,” n.d.) Many emergent countries, who deals with an extreme level of poverty -that is people living with less than $1.25 a day- are in Sub Saharan Africa. However, the quantity of food produced in this region of the world is enough to feed the whole continent. This stresses the need to address food losses and waste in Sub-Saharan Africa. The diagram below demonstrates that in Sub-Saharan Africa about 160 kilograms of food is wasted each year and roughly 93.75% of this waste happens at the production to retail level. This is called Post-Harvest Loss (PHL) as it occurs anywhere between the farms and the consumer’s plate namely at harvest, drying, cleaning, etc. It can be explained by many factors such as poor storage practices, questionable infrastructures as well as by losses happening during the transportation from farms to retail places such as markets.
It can be inferred that depending on a country’s level of development, food waste occurs at different points of the supply chain. The diagram below confirms this assumption. There is clearly a need to adopt a different food waste reduction strategy depending on the region of the world considered.
With respect to Sub-Saharan Africa (SSA) and more specifically West-Africa, we will use case studies to understand the root causes of food loss while making insightful recommendations.
People in SSA and South Asia “only” waste six (6) to eleven (11) kilograms of food per person a year as opposed to Europe and North America where the waste is estimated at 95 to 115 kilograms a year per person. One can then establish that, in West -Africa, food waste is not the main issue, but the real problem remains the food loss.
Food loss is essentially caused by the poor functioning of the production and distribution patterns within the supply chain as well as by the institutional and legal framework. (Scope, Solutions, & Solutions, n.d.)
It is estimated that the yearly post-harvest grain losses in Sub-Saharan Africa (SSA) could feed 48 million people. It is, thus, important to understand the level at which the loss mainly occurs.
From the supply chain emissions diagram emerges three main points where food loss in Africa needs to be addressed, namely storage, transport, and processing.
However, one area that has not been tackled in this diagram is the fact that the harvest itself presents a challenge in West Africa. Indeed, when the harvest season starts, in the case whereby there may be a low labor availability, some food products get lost. According to the “Loss-Reducing Rice Thresher in Six West African Countries” case study, a non-negligible (about 33%) amount of rice products rots in the field in the absence of enough workers. (Scope et al., n.d.)
There are also time constraints on the harvest of each food product that sometimes incite farmers to leave some of their products unharvested. (Sheahan & Barrett, 2017)
Furthermore, the produce handling during harvest such as with bare hands and thus transferring oil substances to the products can likewise generate food losses. All these factors equally reflect on food loss quantity even before getting to the storage conditions in West Africa.
Having established that the first step to address is the harvest, we can now focus on the storage conditions.
First, in this context, storage conditions essentially mean the on-farm storage that ensues before the grower consumes the product or sells it. To increase the shelf life of fresh products such as most grains, some vegetables, and fishes, it is common practice to dry it in most West African cooperatives. These drying practices however heavily rely on sun exposure in the open and enhance the accumulation of mycotoxins during storage.
The traditional storage infrastructures often used are open timber platforms or shelters called “ewe” barn in Ghana and are made of natural materials. Even in the case whereby modern storage structures are available, power outage and meteorological conditions might also affect the harvest.
The second level where PHL most likely occurs is during transportation. According to the World Bank study, Sub-Saharan Africa has the lowest road network densities in the world which is worsened by the fact that most roads are inadequately surfaced. (World Bank, 2011) Undoubtedly, this poor road network is one of the main reasons why transportation generates significant food loss. However, other logistics factors also pertaining to the “transportation step”, such as the high cost of transportation, the absence of intermediate storage facilities and so on are also to be considered.
Thirdly, the processing step has also be proven responsible for some of the Post- Harvest Losses detected in SSA. There are two aspects in which processing might affect the viability of the produce. On one hand, modern practices such as small-scale milling can cause quality degradation of the food products, on the other hand, rough handling and processing can make the products less attractive to the consumers based on aesthetic characteristics. (Scope et al., n.d.; Sheahan & Barrett, 2017)
Even though Kenya is not a West African country, the “Analyzing The Banana Supply Chain In Kenya Leads To Partnerships And Investment” represents an interesting case study for the purpose of this article. As a matter of fact, the Kenyan banana supply chain was deemed inefficient after noticing that 95% of the bananas sold were grade two (2) bananas. Grade two (2) means that the bananas were likely presenting some internal and external defects. This grade is said to be a better fit for local and short distance market. This means that because of some issues within the supply chains, mainly storage conditions, in this case, Kenyan bananas are supposedly unsuitable for a demanding international market. This study also highlights how data availability can make a huge difference in SSA. Indeed, the weak points of the supply chain were identified after four (4) weeks of scrutinization from the production all the way to the retail points. This analysis later generated some funding, partnership, and investment in the banana supply chain in Kenya.
Another relevant study when it comes to storage practices in Africa and more specifically in West Africa is the “TRADITIONAL STORAGE PRACTICES ON THE QUALITY OF MAIZE A CASE STUDY IN THE SHAI OSUDOKU DISTRICT IN THE GREATER ACCRA REGION”. This thesis examines how one of the largely grown and consumed grains throughout West Africa gets lost or loses most of its nutritional value because of poor storage practices. Despite maize being the seventh (7th) agricultural products when it comes to value production and thus contributing to the Ghanaian economy, its storage losses account for 20% of the total grain loss. Reducing this number could help greatly to meet the target 12.3. (Abass et al., 2014; Aggrey, 2015)
After examining the storage issue, the next step in the supply chain is the transport. This next step also intricately depends on the precedent as proven by the “Milking The Demand For Dairy In Kenya” study. The milk demand is steadily increasing in developing countries thus, Kenyan farmers have been expecting to respond to this demand by an increase in their production levels. However, this might not be the most effective solution because for their milk to be adequate to distant markets, they also need to ensure that the milk shelf life is increased. Thus, before shipping they also need to tackle the way the milk is stored, process -need for pasteurization or similar process- and shipped. (Scope et al., n.d.)
Taking a closer look at the “Loss-Reducing Rice Thresher in Six West African Countries” case study, the manual threshing methods — a processing technique employed on rice- are accounting for up to 35% of the rice post-harvest losses in Senegal. This data did not only serve as a basis to understand this specific point of loss in the supply chain but also helped to design an appropriate solution for the Senegalese farming market. This solution once implemented was able to save up to the third of the rice harvest usually lost. What is even more compelling is that, once, this solution was approved, its deployment was not only limited to Senegal but was also requisitioned for six other West African countries.
Drying is one of the main food preservation techniques used in West Africa. However, the traditional way has been proved to make products prone to contamination, hence, resulting in food loss. The “Innovative Fish Processing Technology In Senegal” is a case whereby, after examining the shortcomings of the currently available solutions, the introduction of a new equipment was simultaneously able to significantly reduce food losses and encourage women empowerment in Senegal. (Scope et al., n.d.)
To solve these problems, technology, as outlined by the target 12.a, can be a very useful tool.
Data Science coupled with Machine learning, a field of Artificial Intelligence, can be used to train specific models with algorithms on the available data or with new data set in the case whereby data has not been previously collected. The data required here can be the date of sowing and harvest, time spent by the food product in the open air, time spent in a storage facility or warehouse, the temperature of the warehouse as well as its humidity level amongst others. Using this data, the optimum harvest and storage condition can be determined to prevent and reduce food waste. The outcome can be used to advise farmers on what type of food products to plant at a given season, after how many days the products should be harvested, when to sell the products as well as how to improve the storage conditions. This data can also help with prediction, prevention, and limitation of post-harvest diseases and pest outbreaks.
Computer vision, another field within both the Artificial Intelligence (AI) and the machine learning domains can also be a very useful tool when combined with deep-learning. This would help to determine when the product may go bad which would in the long run, efficiently reduce both food losses and waste.
At the consumer level, this system can encourage individuals to buy some products that do not meet their aesthetic standards but are still suitable for consumption. Knowing that a product is ripened but not bad when consumed within a time range, known before buying, can also invite customers to buy products that they might just have discarded otherwise.
Irani et al’ s paper supports the assumptions, previously made, that data availability along with deep learning can make a revolutionary difference in the current worldwide food loss setting. As a matter of fact, their research on small data to big data in Qatar, confirms that data collected from various stakeholders of the food supply chain such as commercial food consumers, retailers, etc, once organized in a cause-effect model and passed in a Fuzzy Cognitive Map (FCM), provided great insights into the food losses scenarios. This research is said to be evidence that could be of use to policymakers. (2018)
For an efficient implementation of data science in the agricultural sector of Ghana and West Africa in general, some measures- ensuring reliability, conformity, as well as an effective and constant data collection- need to be taken.
As inferred by Sheahan and Barret’s paper there is a significant gap of knowledge when it comes to knowing the actual depth of Post-Harvest loss in Sub Saharan Africa (SSA). Their research proves that the literature currently available on PHL in SSA is unfortunately quite sparse. They attribute this gap mainly to the unavailability of data and the fact that we do attribute PHL to some specific points within the food supply chain but, we have no substantial knowledge of what is happening and some of the difficulties that farmers and other actors of the supply chain are experiencing may remain unknown. ( 2017)
To certify that the inclusion of data science can make a considerable change in the West African agricultural setting and thus, reduce subsequently the worldwide food loss and waste numbers, three major steps may be taken.
Firstly, West Africa through the Economic Community of West African States (ECOWAS) union can make policies to encourage data collection. It is important to know exactly how much is produced and how much is wasted at each point of the supply chain. It is proven that the “lack of reliable primary data is a major hurdle for quantification of food loss in developing countries”. (Scope et al., n.d.)
The Food and Agriculture Organisation (FAO) does have some data but there are insufficient. As emphasized earlier in this article, responsible consumption is not the burden of a person, an organization or region but it is the duty of all. The government can pass laws and facilitate the data collection but in the end, it is up to everyone in a given community to ensure that the necessary data are gathered.
Secondly, when it comes to transportation losses, one can deduce that taking care of the food alone will not yield the intended result of the twelfth (12th) SDG. There is also a need to invest in road infrastructures, regional integration, cold chains and the development of more temporary shelters along the supply chain.
Thirdly, there is a need to create an enabling environment through government-level commitment as part of their annual budget, public-private partnership as well as the development of new policies. An example of such a policy would be one to encourage ad-hoc relationships through possibly a lighter taxation scheme for organizations that are getting most of their food supply in a region close by. This would help to build a better, longer and trustworthy relationship between growers and retailers.
The implementation of such measures in the interest of ECOWAS and local governments given that the availability of data helps to design a better solution for local markets that relatively yields a rapid return on investment (rice, milk, fish??). Better handling and processing which would arise from the data can also lead to more profit because the grains would not lose most of their nutritional value which will eliminate the need to fortify the grains later. This will also give West African cereals a better market value and the possibility to respond to the demand of more distant and foreign markets.
In conclusion, this article has attempted to adhere to the DFID (Department For International Development) Sector Theory Of Change model applied to the reduction of food loss and waste in West Africa.
It does not pretend that applying data science is the only viable solution to achieve a responsible consumption and production but wishes that it may be the first step to truly understand the root causes, of the waste and loss as well as the weak points of the supply chain in order to design effective solutions and support new and more comprehensible policies.
Aggrey, K. (2015). Traditional Storage Practices on the Quality of Maize: A Case Study in the Shai Osudoku District in the Greater Accra Region, (10397135), 1–2.
Scope, T., Solutions, C., & Solutions, O. I. (n.d.). The Scope of the Challenge 3 Solutions and Opportunities 5 Integrating Solutions-A Food System Approach 10 Case Studies 11 Photo credit: Front cover image-CCAFS.
Passadas as festas e as comilanças , certamente a resolução de comer de um jeito mais saudável entrou entre suas metas . Porém, dependendo das jacadas em que você se enfiou nas últimas semanas…
In order to suggest that a program may or may not be working as designed, we tend to expect our quantitative evidence to carry a high level of statistical significance. We also tend to look for large…
Most people that know me know that eventually, I’m going to start sending my paycheck directly to Apple. I’ve been hooked since the iPod nano, and I’m completely unashamed about it. I pride myself in…