Google Launches AMED API to Support Indian Agriculture Sector

Google has unveiled new open-source AI innovations and initiatives aimed at profoundly strengthening India's agriculture sector and making AI models more sensitive to the country’s linguistic and cultural diversity. The company launched the Agricultural Monitoring and Event Detection (AMED) API that provides information on crops and field activity across India, empowering the ecosystem to build targeted solutions that support agricultural productivity and resilience. Researchers at Google DeepMind have also collaborated with IIT-Kharagpur to build localized datasets on India’s rich cultural tapestry as part of Google’s Amplify Initiative, aiming to help equip global Large Language Models with better linguistic and cultural context.

These developments build on Google's sustained investments and commitment to AI research that assist real-world impact across critical areas while also supporting India’s AI-focused ambition.

Speaking at a roundtable in Ananta, Google’s newest office in Bangalore, Dr. Manish Gupta, Senior Director for India and APAC at Google DeepMind said: “At Google, along with charting new frontiers in foundational AI, which forms the backbone of many of our launches in the Gemini era, we have continued advancing fundamental research that addresses some of the most pressing challenges facing humanity. We’ve been inspired by the solutions India’s innovators have unlocked with these capabilities, demonstrating AI to be a powerful catalyst for multiplier impact and unprecedented effectiveness. We remain committed to growing this momentum, and enabling the benefits of helpful and inclusive AI to reach everyone across India.”

Introducing Agricultural Monitoring and Event Detection API

Aimed at making agricultural practices more data-driven and efficient, and solutions for India’s agri sector more effective, AMED API, developed by Google Deepmind and Google Partnerships Innovation team, builds upon Google’s ALU API, and now leverages crop labels, raw satellite imagery and machine learning to assist crop monitoring and detection of agricultural events on fields across the country. The API details the type of crop on individual fields across India, as well as each field’s size and corresponding sowing and harvesting dates. The API even provides historical information about the agricultural activity in each field for the last three years. 

These insights can help the ecosystem build the next generation of AI-enabled solutions that significantly strengthen agricultural management on farms, contributing to addressing the specific needs of each crop - including the right soil and water conditions, growing habits, and climatic needs - as well as predicting harvest volume.

AMED API data is also refreshed nearly every two weeks, enabling the ecosystem partners leveraging AMED API access to continuously updated information that accounts for field-level changes.

AMED API builds on the Agricultural Landscape Understanding (ALU) Research API that the company launched last year. ALU API helps identify boundaries and acreage of fields, water bodies and vegetation. 

Alok Talekar, Lead, Agriculture and Sustainability Research Lead, Google DeepMind, said: “Our commitment to the sustainable growth of India’s agricultural sector deepens with every innovation. With AI research - and especially with AMED building on the foundation of ALU - we’re working on accelerating crucial shifts, transforming broad insights to granular, real-time data, so that increasingly impactful solutions not only translate into benefit for India’s farmers, but also bolster the nation against rising climate risks.” 

TerraStack, a startup incubated at IIT-Bombay, has used ALU API to build a rural land intelligence system to support rural lending, land record modernization, and determine the vulnerability of farms to climate risk, and is exploring AMED API for a rural lending use case. Aaryan Dangi, Co-founder and CEO, TerraStack has said: “These APIs are helping standardize and transform previously unorganized and unusable data into solutions for one of India’s most critical sectors. They enable us to build solutions that ultimately benefit India’s farmers, reducing friction in their path to access tools and resources that support not just their livelihoods, but the sustainability of the country’s agriculture ecosystem.”

Bringing Google’s Amplify Initiative for India

Google’s Amplify Initiative aims to bridge knowledge gaps within Large Language models by infusing more localized data, including different languages, dialects, and cultural nuances missing from current AI training. Collaborating with researchers at IIT-Kharagpur, the Amplify Initiative will build structured, hyperlocal and high-quality datasets on India’s rich linguistic and cultural diversity. Being freely available through open datasets, the Amplify Initiative will enable the global language developer ecosystem to better serve Indian language users in more meaningful and relatable ways.

The initiative collects and annotates data through a community-centric, expert-vetted approach, ensuring responsible practices, potential for bias, and appropriate annotation techniques are considered throughout the development process.

Amplify Initiative was piloted in Sub-Saharan Africa and has created an annotated dataset of over 8000 queries in seven African languages authored collaboratively with 155 experts, addressing a range of topics from chronic disease to misinformation.

In India, the local partner for the Amplify Initiative will begin building datasets related to specific issues, including in healthcare and safety, in multiple Indic languages.

Madhurima Maji, Lead Program Manager, Amplify Initiative for India at Google said: “AI models can be even more helpful with a deeper understanding of the vastness and complexity of the lived human experience. Through the Amplify Initiative, we are meticulously building the rich, hyperlocal context and cultural understanding that transforms raw information into profound knowledge. So that any and every Large Language Model can be fundamentally helpful and genuinely relevant to diverse realities.”

Dr. Mainack Mandal, Assistant Professor, IIT Kharagpur stated: “We’re thrilled to collaborate with Google on the Amplify Initiative, and open a new chapter in global AI development. We’ve been inspired by the results this initiative has achieved in Sub-Saharan Africa, and look forward to ensuring that the groundwork we lay here translates into AI which is more responsive to India’s incredible plurality.”

Amplify Initiative follows Google’s ongoing efforts to strengthen Indian language and cultural representation in AI models. with its flagship initiative, Project Vaani, also completing a key milestone. A collaboration with Indian Institute of Science, Project Vaani makes its Indic speech dataset open and freely available through India’s national language mission Bhashini, and through the open-source platform HuggingFace. Data collected during the initiative’s second phase has now started rolling out for public access. To date, Project Vaani has now contributed a total of nearly 21,500 hours of speech audio and 835 hours of transcribed speech across 86 unique languages, reflecting the contributions of over 112,000 speakers across 120 districts and 22 states available to help developers and researchers build applications and solutions relatable for India’s diverse communities.

Dr. Partha Talukdar, Language Research Lead, Google DeepMind added: “We’re committed to ensuring that the benefits of AI reach everyone across India through experiences and interactions that feel both natural and intuitive. We’re glad for partnerships through efforts like Project Vaani and Amplify Initiative. This support fuels our continued investments in language and culture research, and drives us to make our foundational models, on which India is building its AI ambition, more effective and efficient in processing Indian languages.”  

Google’s AI research and models have been deployed by stakeholders across the ecosystem to address a range of issues and challenges - from improving the effectiveness of maternal health information programs, to introducing efficiencies in patient care, development of agri-intelligence solutions helping safeguard global food supply chains, and even assisting India’s sovereign AI ambition.

Critically, the AlphaFold Protein Structure Database – built with the AI system developed by Google DeepMind which was recognized with a Nobel Prize winners to Sir Demis Hassabis and Dr John Jumper -- is now being used by over 150,000 researchers across India to advance progress on sensitive, long-standing issues, like autoimmune diseases, cancer, and more.

With collaborative innovation and an ecosystem-focused approach, Google looks forward to seeing the advantages of AI translate into positive impact across India.