India is the largest producer and the second largest exporter of cotton in the world. Yet, for the farmers raising cotton crop the year 2017 was horrendous. Reason? Nearly 50 per cent of their yield was destroyed following an attack by the pink bollworm. This happened despite cotton farmers using nearly 55 per cent pesticides in India for their crop. The problem is not availability of pesticides. It’s the early detection of pests. A large portion of the cotton crop in 2017 could have been saved if farmers were able to identify pests at an early stage of infestation. Wadhwani AI aims to change that.

Wadhwani AI is a non-profit organization based in Mumbai. The organisation says that it is dedicated to using artificial intelligence for social good. The company focuses on using AI in their field of health and agriculture.

Before we understand what how this startup is helping the small cotton farmers in India, it is important to understand what leads to a large infestation, such as the one in 2017, that destroyed the crop. Small farmers primarily depend on field staff or the extension workers appointed by the government for advice. These extension workers visit farming plots in every village where pest traps – that are essentially sticky paper where pests get stuck – are placed. They manually identify the pests and count them for infestation. They enter this data on their smartphones and send them to experts for advice. When the experts analyse this data, they send their advice for the farms with infestation.

This technique is not very efficient as it is not very reliable. It is also time consuming. This is where the artificial intelligence based model developed by the Wadhwani AI, which of late is backed by some of the expertise from Google, comes into picture.

nstead of the extension workers manually identifying and counting the pests, the workers just have to take a picture of the pest trap. The AI model working in the background then recognizes various pests and it gives on-spot advice to the farmers by processing the data collected in the cloud. This data also goes to the experts for further analysis.

While this method is efficient it can be rendered ineffective, especially in the areas with low connectivity. Wadhwani AI has solved that problem by compressing its AI model such that it can work on a basic smartphone. “We are quite excited to announce that we have just achieved model compression that makes this AI model small enough to put on a really basic smartphone and hence this can now actually work offline,” said Raghu Dharmaraju, vice president, products and program, Wadhwani Institute for Artificial Intelligence. He was talking about the details of the programme at Google’s Solve with AI conference in Tokyo last week.

What is interesting about this feature is that it is not available as a standalone, rather it is an open source model that is available to any agricultural program around the world.

“By augmenting human skills, we are able to help millions of farmers right from the beginning. That’s technology at scale,” he added.

That leaves us with just one question: How does Google help here? Wadhwani Institute for Artificial Intelligence is one of the 20 winners of the Google AI Impact Challenge 2018 that provides a funding of $20 million along with mentorship to all the winners so that they can complete the first phase of their operations and scale them further. The institute is also one of the three winners from the Asia Pacific region. Basically, Google is empowering this company to improve its product and scale it up such that it can reach to farmers across the country.

The post Google wants Indian farmers to use AI to find bugs in cotton crop, improve annual yield appeared first on Artificial Intelligence.

For thousands of years, the survival of farmers’ crops — and finances — have been inextricably linked to the weather. Whether growing corn on the plains of Nebraska or wheat in the mountains of southeastern Turkey, Mother Nature’s seemingly unpredictable temperament has forced farmers to find innovative ways of better understanding soil moisture, rainfall, and crop health throughout the ages.

One fact that doesn’t change, however, is that crops need water. And, whether they get it from natural rainfall or modern irrigation methods, crops need it consistently at key growing points to remain healthy and abundant.

In 2018, new technologies in agriculture are changing the stakes. Farmers, agronomists, and field researchers are turning to a superior set of tools to help them understand the complexities of moisture for their crops. And while conversations among growers still center around weather forecasts and local rain gauges, thanks to these virtual tools we now have a deeper understanding of current and future moisture conditions, and how they impact crops.

Models and data analytics not only recap what is already occurring between water and plants across expansive rows of corn, they can actually predict what will come in the hours, days and weeks ahead. This gives farmers and agronomists a chance to understand what is happening at field level, so they can build a plan that gives them a distinct advantage over the natural elements for the first time in history.

In the field, predictive modeling shows promise

While irrigation is not used in all areas of production agriculture, many parts of the country rely on it to grow crops. The need is especially great when it comes to specialty crops grown in regions where water is scarce, like California and Arizona. Even in the Midwest, where water is more available, the energy (such as electricity) needed to pump that resource to the crop can make the process too costly.

With a robust data set of ag-specific, hourly, and daily weather information going back several decades, there are tools available today that can help farmers and field researchers predict future outcomes by combining weather data with soil, crop, and grower-provided information. This data drives a series of models that look at the interaction between the plants, soil and weather, which can then be used to better predict when certain things are going to occur and what you can do about them to be a better manager.

And while in many cases high-quality sensing serves as a reliable method of data collection, the resulting information can then help to model future scenarios, eliminating the extensive need for physical probes or in-field sensors, and ultimately saving farmers precious time and money.

Models use robust data to improve decisions

Predictive models are only as good as the data they contain. This technology uses artificial intelligence and neural networking that work in much the same way as the human brain functions to execute decision making and operational functions across the body. These agricultural models get smarter and better as they ingest more data, learning from the processing and analysis churned out of prior information run through their frameworks. These advanced systems track complex sets of information gathered by various devices, including harvesters and other farm equipment, looking to identify any correlations and building crop models automatically. They work more quickly than traditional decision-support tools — and at a fraction of the cost.

This unique ability to manage critical information — to inform decision analysis in an automated system at both the atmospheric and soil levels — is a key advancement for farmers looking to improve their odds, but also for crop science companies. In fact, digital ag teams at several crop science companies are using predictive models to help deliver this more accurate, scalable data model to significantly more farmers, as well as to support the scientists’ own research and development efforts.

Better decisions boost farm confidence and profits

Annual electricity bills to run an irrigation system in the central part of the country can easily run to $50,000 or more. The stakes are much higher in the west, where water is scarce and sensitive crops are more valuable on a per-acre basis. In either case, more responsible use of water in agriculture is increasingly important to the farmer’s bottom line and to the sustainability of agriculture as a whole.

The true measure of success comes back to the same variables that drove farmers on the American plains to track weather and innovate irrigation systems in years gone by — a strong desire to be efficient with water and technology in support of a sustainable and economically viable crop.

Predictive modeling is transforming the way farmers make critical decisions about the lands they farm, leading to more sustainable and productive yields with less costly hardware involved. To drive the proliferation of this technology, predictive analytics companies have been partnering with international crop science companies, which cover many million hectares of farmland spanning multiple continents, in support of their R&D efforts, as well as the tools they develop for farmers. Ultimately, this means they can help a far greater number of farmers than if they only focused our efforts on working directly with the farmers themselves.

Like most innovations in machine learning, this technology is designed to constantly and consistently self-improve — whereby as each new crop year passes, more robust data is added to the model, training it to better respond and predict outcomes based on the latest atmospheric realities. This year’s observations may be the beginning of even better results to come, where weather, soil and crop information combine to unearth greater opportunities for farmers and consumers while saving precious time and money.

The post What roles will AI and machine learning have in feeding the world? appeared first on Artificial Intelligence.

Artificial intelligence will soon be powering robots that will essentially replace farmers to pick vegetables. Thanks to the global warming, the increasing demand in agriculture, and the lack of ample land for farming, robotics is the solution seem by many to meet the demand of the exploding global population.

An American startup, Root AI, is working towards the direction of making indoor farming the next big thing in agriculture where robots, and not humans, help produce and harvest the crop with maximum optimisation of resources.

One of the first inventions coming from Root AI is a mobile robot for indoor farming facilities. Using the cameras and sensors on it, the robot is capable of picking tomatoes the right way and assess the health of the crops, conduct operations such as pruning vines, observing and controlling ripening to cultivate crops, TechCrunch reported.

Root AI is expected to begin the pilot tests from 2019. Given that the US, and other parts of the world, are facing a labour shortage in farming, the concept of indoor farming with AI at the core is likely to gain popularity

The post Artificial intelligence will soon power robots; may replace farmers to pick vegetables appeared first on Artificial Intelligence.