Here's how the agricultural sector can solve its data problem

Food and nutrition security, skewed distribution of farmer incomes, natural disasters and climate change are severely impacting the sustainability of agricultural systems across the globe. Policy reforms are needed to correct these distortions, but innovative emerging technologies like artificial intelligence, machine learning, distributed ledger technologies, sensors and drones, can make a significant difference.

Emerging technologies need data, and it must be the right data, for the right purpose at the right time. This is how it can deliver maximum impact. Agricultural value chains comprise a complex system of stakeholders and activities. The enormity of the size and complexity of agricultural data, coupled with its fragmented nature, pose significant challenges to unlocking its potential economic value, estimated at $65 billion in India alone.

The wide span of agricultural data extends to land, soil, seed, crop, weather, pest, good agricultural practices, quality, market and logistics. Tools like mobile phones, sensors and satellites have made agricultural data collection more intensive and ubiquitous. Most of these datasets, however, remain siloed, and the systems managing them are not interoperable. Sharing data is limited.

The domain of digital agriculture does not have commonly accepted standards for creating, sharing, analyzing and integrating data. Issues such as lack of common vocabularies and use of different formats for collecting the data hinder data sharing.

Most agricultural data is dynamic. Real-time data is required to monitor crop health, adopt best agronomic practices, predict and mitigate pest and disease conditions and natural disasters, optimize the use of resources, overcome productivity plateaus, address the quality concerns of consumers and respond to dynamic or volatile market conditions.

One of the major challenges to realizing the promise of digital transformation of the sector is to be able to create, manage, interchange, and use the historic, real-time and predicted data of agriculture – simply and efficiently.

A huge economic and social opportunity can be unlocked if only the agriculture sector can solve its data problem, especially data interchange. With use of a variety of data such as weather, soil health and crop health, agribusinesses may be able to develop predictive models to provide personalized advice to farmers for growing a specific crop or on the amount of fertilizers/ pesticides to be used in a timely and efficient manner. It could also help to increase productivity and provide efficient market linkages, all through simple digital interfaces. It could lead to novel forms of collaboration and new business models for providing digital services.

As such, there is a need to promote standards-based interoperability, which enables multiple digital systems to exchange agricultural data in an automated manner with limited human intervention. The ease and speed of such an exchange of data, across domains and technologies, would spur the development of innovative solutions and lead to evidence-driven, prediction-based decision-making on the farm and in the market.

Most current efforts to develop standards of agriculture data are isolated and localized. The AGROVOC initiative of the United Nations' Food and Agriculture Organization addresses a part of the data problem by creating an exhaustive vocabulary of agricultural terms. There is also a need to develop an open data format for the automated interchange of agriculture data. A coordinated initiative of the industry is an attractive approach to develop such a format.

This could be developed using the established specifications such as JSON (JavaScript Object Notation), a widely used text format for storing and transporting data, and GeoJSON, an open standard format specifically for geospatial data. It is expedient to develop a format specific to agriculture data, that supports a wide range of apps and solutions to benefit the farmer and all the actors of the agriculture value chain.

The specification should enable representation of data in a technology-agnostic, machine-readable manner. Examples of agricultural data objects include farmer, land, soil, weather, crop, pest, yield, market, and consent. With time and adoption, the scope of the new agricultural data format can also be extended to address the data needs of the entire primary sector. Existing data standards like those relating to the classification of crops, seeds, locations, soils, weather and quality must be built into the proposed format to make its adoption easier.

The harmonized format will ensure that data is understood and interpreted identically across the agriculture sector. It will enhance coordination, trust, and governance across the entire agricultural value chain, both domestic and cross-border. For instance, an innovator may then be able to access consent-based data from different sources and process them together to create new value to the farmers in a responsible manner. It would accelerate the digitization of the agriculture value chain and proliferation of smart farming solutions. It can unlock the potential of the digital economy in agriculture, improving food security and enhancing the income of the farmer.

The discussion amongst public and private stakeholders on the topic of data collaboration will continue at the Annual Meeting 2023 on January 17 and will be livestreamed to the public. Join us on this link.