top of page
Search

Sci4Teens Competition: Engineering 13-15 Gold Award

Implementation of Precision Agriculture in Underdeveloped Countries

Abstract

Over the past few decades, agricultural resources have decreased greatly. By 2050, global demand for agricultural products is estimated to increase by 70% (Kocian and Inrocci 2020). In order to balance this disproportionate ratio of agricultural resources to demands, many underdeveloped countries are now considering precision agriculture, a technique that integrates the latest technology with data analysis (Soma, Shaheer, Zeba, and Arun 2020). By analyzing vast amounts of data, precision farming may prove to be useful in agrarian countries. This allows for conservation of resources and farmers to become more educated and improve the DSS (Decision Support System), a computerized system intended to help farmers make better decisions.


Data Collection and Analysis of Terrain

Recent technologies such as drone mapping and digital imaging devices have increased the collection of data in precision agriculture. As a result, systems can more accurately spot patterns and adapt from prior experience, a key factor of machine learning (Tsouros, Bibi, and Sarigiannidis 2019). Deep learning, a type of machine learning, then performs predictions on such large scales of data (Desai, Chandra, Balasubramanian 2020). In machine learning, many recent applications available in precision farming use deep learning in order to monitor resources (Peggy Connolly, Ruth Ann Althaus, and Robert Boyd Skipper 2015). An example is the use of orthomosaic maps, such as Google Earth, which displays the amount of vegetation in each area (see fig. 1). Farmers can use this to keep track of high density areas and efficiently distribute seeds.




Fig. 1. Measurement of Crop Stress

Satellite Imaging Corporation, Airbus Defence & Space,



Conservation of Resources

Large collections of data and its analysis can be applied to conserve resources. For example, irrigation path-planning robots are used to create intricate irrigation routes. This in turn causes less water to be lost in the process because the irrigation path-planning robot takes into consideration many factors. These include the distance to the target point of the path, condition of surrounding obstacles, and the degree of regional drought. In order to create the irrigation routes, the robot evaluates these factors and plans out the first path using the Bayesian formula, which predicts the probability of an outcome occurring based on previous outcomes. Next, the robot uses this data, while adapting to surroundings and optimizing landmarks, to plan the subsequent paths. This process in turn leads to the creation of organized irrigation routes (see figure 2).

Fig. 2. The Framework of the Algorithm., Minghan Chen,

arxiv.org/abs/2003.00676.


Improvement of DSS and Education of Farmers

In addition to conserving resources, analyzing data through precision farming can help improve the DSS (Decision Support System). Introducing farmers to precision farming applications, such as mobile apps, helps promote basic tech literacy. This is significant since many farmers in rural areas have access to mobile phones, but have not been sufficiently educated to understand available services within those phones, such as apps (Khandare 2015). Through this increased mobile connectivity and information, farmers can more easily work together with markets to purchase inputs and sell harvests. An example is the e-Granary app, which connects farmers to peers and marketplaces, allows them to sell their harvests in bulk, while predicting profit trends (Eastern African Farmers Federation 2020). This helps the farmers maximize their profit andimprove their connectivity. Overall, this process of educating farmers in different ways provides them with critical information and resources that can be used to construct a stronger DSS.


Conclusion

Through the detailed analysis of data, in terrain, conservation of resources, and improvement of DSS through education of farmers, precision agriculture helps to bridge the gap in food insecurity in rural areas. Although technology may take a long time to introduce, the many benefits of precision agriculture outlined in the applications of mobile apps, site mapping, and portable robots, should encourage underdeveloped countries to adopt this form of agriculture.


References:

Balasubramanian, Vineeth N et al. “Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey.” Advanced Computing and Communications (2020): n. pag. Crossref. Web.


Chandra, Akshay L, et al. “Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey.” ArXiv.org, 18 June 2020, arxiv.org/abs/2006.11391.


Connolly, Peggy, et al. “Big Farma.” Markkula Center for Applied Ethics, Santa Clara University, 1 May 2015,

www.scu.edu/ethics/focus-areas/technology-ethics/resources/big-farma-prescriptive-planting/.


Khandare, Shyam. “THE EDUCATIONAL PROBLEMS OF FARMERS IN INDIA.” International Journal of Development Research, vol. 5, no. 01, ser. 2973-2975, 2015. 2973-2975.


“Mobile Phones Are Transforming African Agriculture.” Farm Radio International, 8 Nov. 2018, farmradio.org/mobile-phones-transforming-african-agriculture/.


Soma, Mahesh Kumar, et al. “Precision Agriculture in India- Challenges and Opportunities.” SSRN, 14 June 2019, papers.ssrn.com/sol3/papers.cfm?abstract_id=3363092.


(EAFF), Eastern African Farmers Federation. “e-GRANARY - Digitally Aggregating Farmers for Market in East Africa - WFO-OMA.”


WFO, WFO-OMA Via Del Tritone, 102 , 6 May 2020,

www.wfo-oma.org/frmletter-1_2020/innovative-ideas-frmletter-1_2020/e-granary-digitally-aggr egating-farmers-for-market-in-east-africa/.


26 views0 comments

Recent Posts

See All
bottom of page