How Artificial Intelligence is contributing to Cotton Farming
The agriculture and allied sectors are considered the bedrock of the Indian economy. This sector accounts for 18% of India’s gross domestic product (GDP) and 50% of its workforce. Due to the coronavirus outbreak, when almost every sector shut down, the Indian economy was affected severely. And GDP shrunk by 23.9% in the blink of an eye. In this situation, Agriculture was the only sector that managed to survive the slump and registered a growth of 3.4% in the first quarter of FY2020-21, shows provisional data by the National Statistical Office.
The cotton sector is one of the Agriculture Industry‘s largest sectors and it plays a vital role in the Indian economy. According to India’s Textile Ministry, around 5.8 million cotton farmers and 40-50 million people sustain their livelihood in related activities, such as cotton processing and trade. Cotton Corporation of India reveals India accounts for almost 37.5% of the global cotton area and contributes to 26% of the global cotton produce of 23.92 million metric tons.
The world needs to produce 50% more food by 2050, which cannot be achieved if only 4% of the land is under cultivation. The rising vulnerabilities, such as climate change, coupled with the risk of increased dependency on unsustainable agriculture practices, can lead to agricultural distress. On the other hand, every year, cotton farmers face heavy losses due to pests attacking their crops. Farmers of Indian state Maharastra in 2017 faced a loss of Rs 15,000 crores (US$2.1 billion), as pests attacked almost 50% of the crop.
Consequently, over 55% of pesticide in India is used in cotton farming. However, the over usage of these usage chemicals can damage the crop or compromise the quality.
As artificial intelligence (AI) and other disruptive technologies have been helping the agriculture industry in modernising agricultural activities and resolve issues, it also came up with a solution for cotton farmers to deal with pests-related problems. India-based research institute Wadhwani AI started searching for solutions in 2018 to help cotton farmers save their crops using artificial intelligence insights.
Conceptualisation and Data collection
The idea of using the artificial intelligence model was to determine how many pests are noticed in that area and send an advisory on pesticide usage. But, there was no preliminary field data available to train the model. Hence, the researchers had to create a special app to collect data.
Cotton farmers already use pheromone traps to catch pests and anticipate if there might be a massive attack. The data collection application suggested farmers click photos of pests caught in the traps on a white sheet of paper. They initially aimed to detect different bollworms that pose a significant threat to cotton crops.
“The team spent the initial few seasons gathering and observing the data to refine the model,” says Jerome White, Senior Researcher at Wadhwani AI. “The team had to ensure the model correctly recognises the type and number of pests in the picture to give accurate advice to the farmers.”
There were plenty of challenges to do that. Many farmers used phones that had snapped only low-resolution photos is the primary challenge. Another concerning problem was that the sheet they used as background might not be white; they might be using the camera flash, or the light wouldn’t be merely good enough. There was also an issue about differences in pests across the regions, Jerome cites.
The initial data collection started in 2018 from Maharastra. Last year, the Wadhwani AI team deployed an early version of the trained and validated model with more than 28,000 images.
Researchers compressed the model from 268MB to 5MB, keeping in mind that the app would be used primarily on low-end phones. They then used PyTorch Mobile to install it to an app that also worked offline.
As per the rules of farming authorities of India, the model now analyses images sent by farmers. It’s currently deployed in various districts of Indian states, such as Maharashtra, Gujarat, and Telangana.
Today, over 18,500 farmers are using the application, and every village has a lead farmer to communicate with the project’s co-ordinators and alert their fellow farmers about the notifications sent by the app. There are three levels of alert- green, yellow, and red. Based on the notification color, farmers use pesticides suggested in the app.
Maharastra’s summer experiment shows 150 farmers used the system and a 25% gain in the cotton crop. These results led the Maharastra and Telangana state government to expand the project into the next cotton growing season (June-November). Besides it, the researchers are working with the Better Cotton initiative (BCI), a global non-profit organisation that works for the betterment of cotton farmers, scaling this project worldwide.