data-driven farming

Digital ecosystems for agriculture practices: Towards a data-driven farming

Agriculture is considered the bedrock of sustainability of any economy. Varying from country to country, agriculture plays a significant role in long-term economic growth and structural transformation. Agricultural practices were limited to crop production earlier but in the last two decades, it has transformed to production, processing, distribution of crops, marketing, and livestock products. Majorly agricultural activities serve as the basic source of livelihood, accelerating the GDP, contributing as a source of national trade, reducing unemployment, providing raw materials to other countries for production, and thereby developing the economy. “Because when farmers thrive, the entire economy thrives”. 

In the present scenario and earlier, smallholder farmers in all under-developed economies are continuously facing the problems of crop perishing, inventory management issues due to over-production of crops, storage and maintenance problems, soil management, crop management, disease management, and weed management, etc. Looking over these issues, there is a concurrent need to take the agriculture system into phenomena that will bring solutions to these problems and increase production and productivity thereby transforming them into tech-farming specifically the data-driven farming focused to increase yield, reduce the cost, and mitigate the risk. 

So, the technology used can provide actionable data so farmers and governments can enrich economies through increased crop yields and healthier livestock. As a result of this, there occurs a need to focus globally on the environment, corporate and farmer understanding of digital technologies and how to apply them to achieve real and measurable value. So, it could be transformed one day into “data-driven farming becoming the new normal”. 

To accomplish and implementation for the process of data-driven farming, the system needs to be enabled by other technological advances which include robotics, big data analytics, availability of cheap sensors and cameras, drone technology, internet-of-things, and even wide-scale internet coverage on geographically dispersed fields. So, there occurs a need for proper analysis of soil management data sources such as weather, temperature, moisture, and historic crop performance to be taken into consideration. AI systems provide predictive insights into which crops to plant in a given year and when the optimal dates to sow and harvest in a specific area, thus improving the crop yields and decreasing the use of water, fertilizers, and pesticides. With the implementation of AI technologies, the impact on natural ecosystems can be reduced, and worker safety may increase, which in turn will keep food prices down and that will help in ensuring the food production will keep pace with the increasing population. The process of implementing the computational systems of AI and the points of discussion which holds 

specific values consists of the digital ecosystems and software solutions, architectural design needed for the solution, sources of data in the agricultural system, advanced or predictive analytics used in the system, precision agriculture, robotics or automation in agriculture. 

Among the points assembled above, the most prominent holds the sources of data in agriculture. The data sources may be satellite images, images taken from drones, sensors, smartphones, and robots. The drones in agriculture will help in soil and crops monitoring, weed identification, wildlife monitoring, and disaster management. The data collected through the use of the internet of things in agriculture detects the process of diagnosis of disease, crop yield analysis presenting smart data and synchronizing it to the data collected as a result of soil erosion, field monitoring, early detection of pests or diseases, etc. Among these, the most common model that can be considered to be thought of as deriving value from analytics is the descriptive, diagnostic, predictive, and prescriptive spectrum which are useful in transforming data into actionable information through different sorts of computational analytics and requires different degrees of human information processing. 

In descriptive analytics, computation is used to provide data or information to humans to process and allows to condense big data into the smaller pattern, and a more authenticated summary of information. An example may be analytics in agriculture that produce a high spatial-resolution field map to indicate variations in quality and quantity. 

In diagnostics, computation produces a relationship between datasets. For example, relationships between nutritional components of animal feed and milk yields or meat quality. 

Predictive analytics provides a variety of statistical methods, modeling, data mining, and machine learning techniques to forecast and simulate what scenarios will be considered in the future. An example would be predicting when crops are likely to be mature enough for harvesting. 

Computations in prescriptive analytics are done to make or take recommended actions necessary to achieve predictive outcomes or effects of each decision. 

There are many more emerging AI capabilities in agriculture. The concept and deployment of improved diagnostics, improved predictions, precision agriculture systems, robotics and autonomous systems (RAS), supply-chain traceability can lead to smart irrigation with the highest level of pest control or eradication, etc. In the coming years, the population is expected to reach more than nine billion globally by 2050 which will consequently require an increase in agriculture production by 70% to fulfill the demand. Only about 10% of this increased population may come from unused lands and the rest should be fulfilled by current production intensification. The present strategies which are identifying agricultural 

production require high energy inputs and market demand high-quality food. Robotics and autonomous systems (RAS) are going to set to transform global industries. 

The future trends of major disruptive significance under computing and technology will see the evolution of Artificial General Intelligence (AGI) and the future of labor, economics, and agriculture. The others are innovations in blockchain and quantum computing. Specifically to agricultural science, deep genomics, and genetic engineering going to play a crucial role. The future of encryption technologies and long-term security, pervasive centralized data collection, and ubiquitous surveillance going to build up. 

The article has been written by Ravi Kishor Ranjan, Academic Associate, Great Lakes Institute of Management, Gurgaon

Leave a Reply

Your email address will not be published. Required fields are marked *