Food & Agriculture


Artificial intelligence helps farmers spot diseased corn and soybean faster.

#artificialintelligence

If farmers want to know how healthy crops are, perhaps they shouldn't trust their eyes. Matt Free -- a manager at Evergreen FS, an agriculture company -- learned that lesson this year. His team provides crop protection services such as fertilizers and herbicides to farmers across Illinois. After a year-long test of a variety of new technologies, Evergreen FS found artificial intelligence could identify trouble, such as fungus growth and water shortages, in corn and soybean crops weeks before the naked eye would ever realize it. The tech, which comes from startup Ceres Imaging, offers farmers an AI analysis of photos taken from planes flying several thousand feet above fields.


Farmers spot diseased crops faster with artificial intelligence

#artificialintelligence

If farmers want to know how healthy crops are, perhaps they shouldn't trust their eyes. Matt Free -- a manager at Evergreen FS, an agriculture company -- learned that lesson this year. His team provides crop protection services such as fertilizers and herbicides to farmers across Illinois. After a year-long test of a variety of new technologies, Evergreen FS found artificial intelligence could identify trouble, such as fungus growth and water shortages, in corn and soybean crops weeks before the naked eye would ever realize it. The tech, which comes from startup Ceres Imaging, offers farmers an AI analysis of photos taken from planes flying several thousand feet above fields.


PODCAST: Machine Learning, AgTech and Tensorflow HPE Newsroom

#artificialintelligence

The age of highly accessible, open source machine learning tools is upon us. No longer niche, everyone -- from data scientists to Japanese cucumber farmers -- is using machine-learning technologies. But what is machine learning? Machine learning is exactly what it sounds like -- software that can learn to solve a problem. Using large sets of data, an algorithm can be trained to understand that data.


Three very different startups vie for "Robohub Choice"

Robohub

Three very different robotics startups have been battling it out over the last week to win the "Robohub Choice" award in our annual startup competition. One was social, one was medical and one was agricultural! Also, one was from the UK, one was from the Ukraine and one was from Canada. Although nine startups entered the voting, it was clear from the start that it was a three horse race – thanks to our Robohub readers and the social media efforts of the startups. The most popular startup was UniExo with 70.6% of the vote, followed by BotsAndUs on 14.8% and Northstar Robotics on 13.2%.


Spain Tests Artificial Intelligence to Manage Fly

#artificialintelligence

For the second consecutive year, Spain's agricultural ministry has launched a pilot experiment using artificial intelligence to predict the evolution of the olive fly. The experiment uses data collected on the olive fly by the Andalusian Plant Protection and Information Network (RAIF), a project of the Ministry of Agriculture, Fisheries and Rural Development. The data are analyzed and fed into an artificial intelligence model that can predict the fly's behavior up to four weeks in advance by using machine learning techniques. This method provides a valuable tool for olive farmers to better manage the pest by revealing the areas and dates of the greatest risk of infestation. This also allows for the more efficient planning and designing of measures to control the pest.


How Automation Will Transform Farming

#artificialintelligence

When Kyler Laird imagines the future of his 1,700-acre Indiana farm, he sees robots playing a major role. I need this technology because I really can't afford to hire anyone. Besides, finding a skilled operator who is willing to work 24 hours a day for three or four days a year is ludicrous," he says. "I can't hire that, but I can make that very inexpensively." For the last two growing seasons Laird, who has a master's degree in ag engineering, has developed autonomous machines to drill, harvest, and plant his crops.


Q&A: The state of machine learning, according to real humans

@machinelearnbot

Top use cases among ML adopters included image recognition, classification, and tagging (47 percent); emotion/behavior analysis (47 percent); text classification and mining (47 percent); and natural language processing (45 percent). Adam Wenchel: Not only is ML enabling Capital One to create more personalized, adaptable experiences for customers, but it's helping behind the scenes to improve operational efficiencies. ML has various applications across all of our core businesses, including call center conversation analysis, fraud detection and risk management, and robotic process automation (RPA). Gary Graves: InterActiveTel uses ML to understand what is happening on a phone call in real time. We use speech recognition, speaker identification, feature extraction, classification, forecasting, and sentiment analysis.


North Dakota Rules Set for Use of Controversial Weed Killer

U.S. News

Monsanto has sued Arkansas over dicamba bans in that state, but a court battle doesn't appear likely in North Dakota. The company says it prefers to work with states and will urge North Dakota officials to be flexible on the cutoff date if conditions warrant.


How (and Why) to Create a Good Validation Set

@machinelearnbot

An all-too-common scenario: a seemingly impressive machine learning model is a complete failure when implemented in production. The fallout includes leaders who are now skeptical of machine learning and reluctant to try it again. One of the most likely culprits for this disconnect between results in development vs results in production is a poorly chosen validation set (or even worse, no validation set at all). Depending on the nature of your data, choosing a validation set can be the most important step. Although sklearn offers a train_test_split method, this method takes a random subset of the data, which is a poor choice for many real-world problems.


Russia unveils SKYF heavy lift drones

Daily Mail

A new drone designed by Russian researchers is the hulk of the quadcopter world - and can carry a 400-pound (181-kg) payload and fly for up to eight hours. The multi-rotor, autonomous drone, called SKYF, was designed with logistics and agribusinesses companies in mind to create a air freight platform to help business carry out tasks. The vertical take-off and landing drone has applications in areas such as the aerial application of pesticides and fertilizers, seed planting for forest restoration and emergency situations for food and medicine delivery. The drone, designed by Russian company ARDN technology, has a maximum flight speed of 70 kilometers per hour (43.5 miles per hour) at a maximum height of 3,000 meters (9,843 feet) and has a positional accuracy of 30 centimeters (11.8 inches) The drone, designed by Russian company ARDN technology, has a maximum flight speed of 70 kilometers per hour (43.5 miles per hour) and is 5.2 meters (17 feet) by 2.2 meters (7.2 feet). It can fly at a maximum height of 3,000 meters (9,843 feet) and has a positional accuracy of 30 centimeters (11.8 inches).