data-driven farming

“India Agricultural Platform” could transform India’s agriculture within a decade

Currently, agriculture utilises approximately 50% of India’s workforce, 90% of freshwater and 46% of land resources. However, despite the significant resources employed, the industry is barely able to generate 14% of our GDP. Given the long term neglect of agronomics, the only way to make progress is to “pole-vault” over deficiencies by injecting appropriate technologies and innovation on a massively parallel scale, and adopting holistic, transformative, “platform” thinking.

The “India Agricultural Platform” (IAP) will accelerate sectoral transformation

There is a visible need for an open, scalable, integrating platform, that democratises access to Agri information, credit, insurance and markets; incubates innovative business models; and enables better decision making.

The Indian Agricultural Platform (IAP) created by the eco-system, and regulated by a national public entity, is envisioned as an “enabling  framework of Data and Services (applications) around a data exchange”. It will be built around Agri use cases, while encouraging application and data interoperability using well defined interfaces.

Let us examine two illustrative use cases:

Use Case1: Agri Fintech Credit Assessment: Half our farmers, cannot get credit easily, because of incorrect or lack of land records and lenders have limited information for credit risk assessment.

Consider this scenario, leveraging the IAP for a credit use-case in the year 2024:

Selvam, a rice farmer with a two-acre farm near Madurai, logs into the IAP using retina scan, fills in a loan request in Tamil, attaches photos of himself and the farm. He accords consent for his data to be accessed from different entities (Govt, Start-ups, FPOs etc): Aadhaar, geo-location, three year’s crop type, yield and earnings.

This data flows in, completing Selvam’s application and providing visibility of his farming history to all potential lenders. To evaluate credit risk, they use the combination of geo-location along with Aadhar to extract Selvam’s farm credit history and details of all existing and completed loans. The automated process allows a majority of the lenders to approve/reject the loan online within minutes. Artificial Intelligence flags issues needing a clarifying phone call.

Selvam chooses a financial institution who pays the seed supplier directly, crediting the balance loan into Selvam’s regular bank crediting the balance loan into Selvam’s regular bank using the UPI interface and creating an autodebit for the month after harvest. The entire process is digital, with no paperwork. The bank also remits a small fee to the start-up(s) for providing Selvam’s cropping history.

Back in 2020, Selvam recalls filling several loan applications individually, spending money travelling to Madurai and loan sanctions took an average of two months. The IAP has reversed and democratised the process, giving him the power while lenders now bid for Selvam’s loan.

Comparing different offers transparently allows Selvam to choose wisely.

The IAP can facilitate this, as in Selvam’s example, by processing large data flows, triangulating data real-time, from several entities: a farm management start-up revealing cropping history, satellite data for estimated yield & water source, geolocation coordinates with Aadhaar helps a lender assess credit-risk. Data from several entities is processed in a “confidential computing” framework, masking raw data visibility across sources from one another – as well as from the final recipient of the credit assessment, i.e. the financial lender.

The signed loan papers along with the assessment documentation are stored in the Govt’s digital locker for auditability. The lender pays an assessment fee to the farm data providers, aiding their revenue stream. Using tools like video, voice, vernacular translation help facilitate farmer engagement.

Use Case2: Crop Price forecasting (Govt. decision making): Picture this real life scenario:

A Bihar Govt bureaucrat is trying to forecast tomato’s post-harvest prices to avoid the heartbreaking crisis last season when prices crashed due to a sudden glut. Tomatoes dumped on the road and farmer suicides attracted bad press. He pores over submissions from each district, showing crop-wise acreage and sowing week. From experience, he knows this data could be 2-3 months old, while tomato’s harvest in 3-4 months. He observes that gross crop acreage varies 15-25% across submissions and he suspects some districts fill in data without stepping out of the office.

Based on this, how can he forecast prices or take action? Should he believe the input suggesting Tomato acreage is 15% lower than the
previous cycle? How would the forecasted winter rains and colder weather impact tomato yield? He wishes he could advise farmers better because staggering sowing and harvesting by 1-2 weeks play a big role in smoothening market price swings.

But for that, he needs automated, real-time data.

To solve this problem, an enabling framework like the IAP will use multi-year, Agri Data-sets from multiple sources (government, enterprises, start-ups), seamlessly translating it into information and then into precisely actionable insight.

For instance, digital crop signature, from satellites, combined with AI, can reveal crop-wise acreage under plantation, by district within 4-6 weeks of planting. As the crop matures, it estimates crop yield, and then combined with acreage and processing capacity in proximity – likely post-harvest prices. The IAP also provides an alternate forecast by analysing aggregated seed sales data, district wise, from suppliers to predict acreage under tomatoes. Both estimates are correlated for accuracy.

Early price forecasts enable faster tactical actions avoiding price crashes, like helping stagger harvesting, or tying-up additional quantities with processing plants in advance. Powered by Artificial Intelligence (AI) & Data Analytics, IAP helps tactical and strategic decision making, leveraging aggregated insights from the farms to state/national levels.

Agri Data Interoperability: This kind of domain and application integration, requires seamless data interoperability across the Agri eco-system, with a focus on Data standardization, calibration and certification. The platform will have to reduce duplication by integrating data sources and a vast backend of new and existing applications: Govt’s eNam, ITC’s eChoupal, NCDEX’s NeML, APEDA’s TraceNet etc related to logistics, weather, supply-chain, warehousing, assaying, recommendation engines, etc.

India Agricultural Platform will incubate new “Data Partnerships”, Business models and Revenue streams:

Innovation impacts the entire agricultural value-chain:

Soil testing |Crop selection |Sowing | Irrigation | Yield estimation| Harvesting | Farm equipment | Farm operations & management incl. weed control & pesticide application | Price discovery | Sorting and Food processing).

This value-chain is rapidly becoming digital, leading to an increasing amount of live and realtime data being generated. Physical maps being digitized is an example, while another is through the multiplicity of payment and Agri trading platforms. In addition, there is a rapid increase in “machine-data” generated by precision farming applications:

  • Drones / UAV (e.g. real-time monitoring of farms enabling mapping, surveying, 3D modelling)
  • Satellites and remote sensing (e.g. providing direct farmer advisory, for yield estimation, early pest warning etc.)
  • Robotics (e.g. nutrient injection, harvesting, targeting high precision weed removal)
  • Automated Material Handling (e.g. harvesting equipment, grain/food processors)
  • Farm sensors and management (e.g. for soil moisture, water and nutrient injection)
  • Mobile cameras (e.g. for identifying pest, nutrient deficiencies)

This mountain of data, once anonymised, aggregated and processed can be re-purposed using AI on the IAP, for different use cases, raising yields, optimising national resources and doubling farmer income. The IAP enables a technical framework to harness this dataflow and facilitate “data partnerships” between Govt, Start-ups, Corporates, Research, Academia based on either  Created by The Agri Collaboratory: Transforming Agriculture. TAC Copyright. 25th 5 April 2021. direct or indirect business benefit. New innovative business models and partnerships will emerge across the value-chain (insurance, market access, assaying etc.) that help monetise data contributing to improved productivity and profitability of Agriculture and other sectors as well.

Given that similar challenges exist across the developing world, India will establish itself as a globally recognised Agri innovator.

Summary: Key benefits of the India Agricultural Platform (IAP):

1) “Market Facing”: Availability of several market aggregators on the IAP offers the farmer transparency enabling real time deal making.

2) “Advisory”: Integrated source of all information a farmer needs: (weather, crop-selection, pricing, etc), available through several advisory channels (govt or private; free or charged).

3) “Decision Making”: Multi-year, diverse data-sets, aggregated from farms up to district, state, national levels, improves strategic decision making by the Govt.

4) “Integration”: The IAP uses “Open APIs” to enable software application interoperability, creating a seamless Agri framework, allowing service providers to scale exponentially.


The author of the article is Nipun Mehrotra, Founder, The Agri Collaboratory

Leave a Reply

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