Google-backed Cropin launches AI tool to boost climate-smart agriculture

The Bengaluru-based company has launched 'akṣara', the agriculture sector's first purpose-built open-source Micro Language Model for climate-smart agriculture

Farmers and others involved in agriculture are struggling to meet the world's increasing demand for sufficient, safe, and nutritious food. This challenge is especially critical in the Global South, where farmers are increasingly vulnerable to changing weather conditions. Climate change is disrupting conventional agricultural practices, rendering existing knowledge impractical in the era of global warming. Factors such as irregular or extreme rainfall, unpredictable heatwaves, and increased pest and disease attacks affect farmers' practices, reducing agricultural yield, productivity, and profitability.

Cropin Technology, a global Agtech company, aims to bridge this gap by harnessing the power of generative AI (GenAI) to provide insights into modern farming practices, accurate information, and farm advisories. For example, it can suggest which inputs to use for crops like rice or maize under specific agro-climatic conditions or offer thousands of climate-smart agri-advisories on other topics.

To achieve this, the Bengaluru-based company launched 'akṣara', the agriculture sector's first purpose-built open-source Micro Language Model for climate-smart agriculture, built on Mistral’s foundation model. 'Akṣara' is designed to address the problems faced by the underserved farming communities in the Global South by removing barriers to knowledge. It can also empower anyone in the agriculture ecosystem to build frugal and scalable AI solutions for the sector.

The aim is to democratise access to digital technologies and empower agricultural stakeholders, developers, and researchers to tackle global challenges. These include food security, climate change, resource conservation—water and soil—and regenerative agriculture practices. The platform does this by providing access to contextual, factual, and actionable information.

“These models can potentially transform agriculture, paving the way for a new era of tech-driven farming in a sector that has traditionally seen limited technological advancement,” said Krishna Kumar, founder and chief executive officer, Cropin.

Kumar said that domain-specific AI models for agriculture are expected to attract significant investments, offering a practical and economically viable approach to food systems transformation.

“Akṣara reinstates our commitment to leading the tech-driven agricultural movement in the years ahead, significantly impacting small-scale farmers' lives,” said Kumar.

The first version of akṣara will cover nine crops viz. paddy, wheat, maize, sorghum, barley, cotton, sugarcane, soybean, and millets for five countries in the Indian subcontinent. These food crops collectively account for a substantial portion of the world's food requirements and are the staple food for the population in the global south.

“Recognizing the environmental impact of running large language models (LLMs), Cropin has meticulously compressed 'akṣara' into 4-bit from 16-bit by using QLoRA or Quantization and Low-Rank Adapters (LoRA), while still performing better than GPT-4 Turbo by almost 40 per cent on a set of test datasets as measured by the ROUGE or the Recall-Oriented Understudy for Gisting Evaluation scoring algorithm,” said Praveen Pankajakshan, Head - Cropin AI Labs.

The model ensures that the responses are factually relevant and brief while minimizing the compute and storage resource requirements.

This initiative also demonstrates Cropin's commitment to sharing knowledge, and ethical and responsible use of AI for agriculture. The Cropin AI team used Google's People + AI Guidebook and discussions with Google's Responsible AI team to help guide the model's design process. The aim was to ensure the model's alignment with key responsible AI principles, reduce biases, and promote the use of AI for sustainable agricultural practices.

“Smallholder farmers, especially those in the global south, are increasingly vulnerable to climate change. They desperately need access to modern farming tools, information, new package of practices, and climate-smart advisory,” said Sujit Janardanan, Chief Customer and Marketing Officer, Cropin. “What we are doing with akṣara is making that possible and making that knowledge and information, which is precise to their problem statement, accessible at their fingertips.”

This open-source initiative aims to support agronomists, agri-scientists, field staff, and extension workers. The goal is also to gradually extend the services to farmers in multiple languages, considering the need for local language support.

Cropin said that AI has the potential to transform agriculture, but challenges like access to large-scale structured data, expertise, and storage or compute infrastructure limit its adoption. Open-source projects like akṣara are crucial for wider AI use and speeding up innovation.

The company said that it started AI innovations in agriculture five years ago when many didn't even imagine AI applications in farming.

Out of the world's 600 million farms, Cropin said that five out of six are small, covering less than two hectares each. Despite operating on only about 12 per cent of agricultural land, these small farms produce roughly 35 per cent of the world's food. The goal is to enable AI investments to have a significant impact and to make it accessible to everyone in the ecosystem.