ARTIFICIAL INTELLIGENCE IN AGRICULTURE

21st December, 2020

ARTIFICIAL INTELLIGENCE IN AGRICULTURE

Technology in Agriculture: The need

Humanity has come a long way over the millennia in how we farm and grow crops with the introduction of various technologies.

As the world population continues to grow and land becomes scarcer, people have needed to get creative and become more efficient about how we farm…

  • using less land to produce more crops and
  • Increasing the productivity and yield of those farmed acres.

In Indian context

When it specifically comes to India, our agriculture is faced with multiple challenges like high dependence on monsoon, resource intensiveness – heavy use of resources (water, inorganic fertilisers and pesticides), degradation of land and loss of soil fertility, and low per hectare yield, among others.

Agriculture continues to employ 49 per cent of the workforce and contributes to only 16 per cent of the country’s GDP. Improvement in agriculture would, therefore, positively impact the well-being of a very large section of the Indian population, apart from delivering food security to our country.

Feeding over a billion Indians on limited land resources is a big challenge ---- a task that requires technological intervention on a large scale, to enable a giant leap in agricultural productivity.

It is in this context that, AI can play a catalytic role in improving farm productivity, removing supply chain constraints and increasing market access. It can positively impact the entire agrarian value chain.

First thing first…

What is Artificial Intelligence?

Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The goals of artificial intelligence include learning, reasoning, and perception. Examples include: self-driving cars, virtual assistant etc.

Applications of AI

Scope of Artificial Intelligence in Agriculture

Use in weather forecasting

With help of Artificial Intelligence farmers can analyze weather conditions by using weather forecasting which helps them plan the type of crop can be grown and when should seeds be sown.

Soil health monitoring system

The type of soil and nutrition of soil plays an important factor in the type of crop is grown and the quality of the crop. Due to increasing, soil degradation and it’s hard to determine the quality of the soil. AI can help farmers in identifying the nutritional deficiencies and requirements in soil.

Case Studies

  • A German-based tech start-up PEAT has developed an AI-based application called Plantix. Plantix can identify the nutrient deficiencies in soil including plant pests and diseases by which farmers can also get an idea to use fertilizer which helps to improve harvest quality. This app uses image recognition-based technology. The farmer can capture images of plants using smartphones. We can also see soil restoration techniques with tips and other solutions through short videos on this application.
  • Trace Genomics is another machine learning-based company that helps farmers to do a soil analysis to farmers. Such type of app helps farmers to monitor soil and crop’s health conditions and produce healthy crops with a higher level of productivity.

Analyzing crop health

AI equipped drone can capture data from fields and then data is transferred via a USB drive from the drone to a computer and analyzed by experts from the Government’s agricultural department.

Captured images can be analyzed to produce a detailed report containing the current health of the farm. It helps the farmer to identify pests and bacteria helping farmers to timely use of pest control and other methods to take required action.

Precision Farming and Predictive Analytics

AI applications can help in accurate and controlled farming by providing farmers proper guidance about water management, crop rotation, timely harvesting, type of crop to be grown, optimum planting, pest attacks, nutrition management.

Even the last mile Farmer can get AI benefits, with tools as simple as an SMS-enabled phone and the Sowing App.

AI-enabled system to detect pests

AI systems use satellite images and compare them with historical data using AI algorithms and detect that if any insect has landed and which type of insect has landed like the locust, grasshopper, etc.

It can then send alerts to farmers to their smartphones so that farmers can take required precautions.

Agricultural Product Grading

Automated quality analysis of images of food products is an accurate and reliable method for grading fresh products (fruits, grains, vegetables, cotton etc.) characterized by color, size and shape.

The farmer can take an image on his phone and determine the product quality in real time, without any manual intervention.

Alerts on Crop Infestation

Farmers can click an image of their crop and use their solution to understand the pests, diseases, and foreign plants (weeds) growing in their farms. The solution uses deep learning and image processing models to identify any crop diseases or pest infestation in the crops. Along with the parameters, it gives recommendations on how that disease can be cured and prevented from increasing further.    

Detecting weeds

AI can effectively be used for differentiating between weeds and crop seedlings. It is one of the most efficient non-chemical ways of reducing weeds. For instance, digital imaging can be used to separate carrot from rye grass and fat hen.

Do you know?

  • Microsoft India in collaboration with ICRISAT (International Crops Research Institute for the Semi-Arid Tropics), has developed an AI Sowing App.
  • The app sends sowing advisories to participating farmers on the optimal date to sow crops. The farmers don’t even need to install any sensors in their fields or incur any capital expenditure. All they need is a feature phone capable of receiving text messages.
  • To calculate the crop-sowing period, historic climate data (spanning over 30 years from 1986 to 2015) for the specific area in Andhra Pradesh was analyzed using AI. To determine the optimal sowing period, the Moisture Adequacy Index (MAI) was calculated. MAI is the standardized measure used for assessing the degree of adequacy of rainfall and soil moisture to meet the potential water requirement of crops.
  • Microsoft has also partnered with United Phosphorous (UPL), India’s largest producer of agrochemicals, to create the Pest Risk Prediction App.
  • Today, these farmers across the Indian states of Andhra Pradesh and Karnataka wait to get a text message before sowing the seeds. In a few dozen villages in Telangana, Maharashtra, and Madhya Pradesh, farmers receive automated voice calls alerting them whether their crops are at risk of a pest attack based on weather conditions and stage of the crop.

Irrigation

AI helps in irrigating agricultural fields. It can monitor and analyze the soil moisture and other conditions, such as aridity or humidity in the surrounding atmosphere, and then open water valves to provide water to the fields automatically, without any human involvement.

AI can alert personnel in times of drought and can also help mitigate wastage of water by releasing it only when it is required. Moreover, illegal consumption of water can also be prevented.

Thus, as capital costs of technology decrease and the software capabilities of AI in agriculture increase, we will see a jump in efficiency and sustainability, which will eventually meet the world’s food needs.

Warehousing

Even after a good harvest, if the crops are not stored and taken care of, they may rot. Thus, good warehousing facilities are a must.

AI can help in deploying correct grain storage techniques by maintaining the appropriate temperature, pressure, and humidity conditions, by adjusting its analysis according to different types of crops.

It can also give real time information to the warehouse manager if there is any change in set parameters in the grain storage. Moreover, it constantly updates itself with the amount of grains remaining inside the warehouse so that they can be replenished.

Recent developments pertaining to AI in India

Initiatives by AI Industry

Recently, AI industry has joined hands with the government to develop an AI-powered crop yield prediction model to provide real-time advisory services to farmers.

The system aims to help increase crop productivity, enhancing soil yield, controlling the wastage of agricultural inputs and warning of pest or disease outbreaks.

This system uses remote sensing data provided by the Indian Space Research Organisation (ISRO), data from soil health cards, the India Meteorological Department’s (IMD) weather prediction and analysis of soil moisture and temperature etc. to give accurate information to farmers.

This project is being implemented in 10 aspirational districts in the country across Assam, Bihar, Jharkhand, Madhya Pradesh, Maharashtra, Rajasthan and Uttar Pradesh.

Initiatives by Start-Up companies

  • A startup has used data science, AI and machine learning algorithms, along with data sets from ISRO to assess --- damage to crops + compensation payable based on value of the damage that has taken place. Questions around what is being grown, what is the damage, what would the value of the damaged crops, are answered with reasonably high accuracy. 
  • An AI startup in India maps farmers’ zones in remote areas, answering questions like
  • who has been farming which land,
  • what is being grown,
  • what is the quality of soil on the land, with great accuracy.

Crop insurers, seed suppliers, state governments all want this data and it’s possible to build a business model around this as the data and information has value for everyone. 

  • Imaging and AI, traceability solutions are being developed for large scale quality testing and post-harvest produce handling and monitoring.
  • Data is helping to create platforms for price transparency to check malpractices in the supply chain.
  • Agricultural-Bots (ag-bots) and drones are being developed to ensure seamless execution of cultivation and harvesting.

Conclusion and Way Ahead

Use of AI in agriculture will improve farmers’ access to markets, inputs, data, advisory, credit and insurance.

Timely and accurate data coupled with analytics can help build a robust demand-driven efficient supply chain.

With the use of sensors, photographs through phones, IoT devices, drones and satellite images, agricultural data can be collected and matched with weather data, soil health card data, mandi prices and help build predictive models that can greatly enhance decisions about seeds, fertilisers, pesticides that are of critical importance in both pre-harvest and post-harvest stages.

Most of these AI models are low-cost and affordable and can add a lot of value to the agriculture ecosystem.

In a nutshell, greater use of AI would increase productivity by introducing precision agriculture.

However, in order to help these AI solutions scale, what is needed is to increase investments – both public and private – especially from venture capitalists.

In this context, the recently concluded Responsible AI for Social Empowerment Summit – RAISE – 2020 Summit has helped provide a platform for global stakeholders to come together to finalize the roadmap for using AI for public good.