Using AI to Monitor our Environment

An exciting new proposition from two students at the University of Toronto may hold the key to solving logistical problems in monitoring and addressing the state of Canadian rivers. Alberto Camacho and Patricio Córdova have developed a scheme named Drone River which utilises a three-pronged approach in order to provide better surveillance and analysis of river levels than ever before.

Their system relies upon three different components: firstly, an automated web service handles texts, emails, phone calls and social media updates to gather information about potential concerns in different areas of the river. Secondly, a network of sensors are distributed onsite along the river to collect real-time in-situ data, augmenting their knowledge of the potential problems. After the problem zones have been identified, drones are then deployed to perform basic reconnaissance by taking pictures, videos and water samples, before returning to base for the information to be processed.

The History of Environmental Monitoring

Studying our climate and our environment in order to better understand it and avoid natural disasters or problems has long been a part of our history. Indeed, thermometers, copper rain gauges and other similar instruments have been in use since Victorian times. Over the years, such technology has evolved to allow us to build up a detailed picture of the world around us, allowing for the proliferation of weather forecasting and disaster prediction.

As well as making our lives easier and more comfortable, these developments in monitoring technology have also helped to reduce death and destruction caused by natural disaster. For further information on the history of monitoring – especially with regards to monitoring rainfall – see the article Monitoring the Weather - More Relevant than Ever.

The latest leaps in technology and artificial intelligence have made environmental monitoring easier and more comprehensive than ever. The Drone River system has utilised various different advances in technology to address practical concerns faced by Canadian river monitoring bodies.

Solving Problems with AI

After speaking with Ottawa River conservation agents, Camacho and Córdova identified three key concerns in the industry. These were as follows:

• A shortage of manpower in dealing with calls relating to river problems
• Breaking through extensive red tape when dealing with conservation
• Accessing difficult-to-reach zones of the river to assess its status

“I knew that all of these problems could be addressed using existent artificial intelligence (AI) and drone technologies,” Camacho told Phys.org. “All we needed to do was to demonstrate that such a solution was feasible, effective and reliable.”

They achieved the solution by using an automated service to deal with the influx of phone calls, tweets, emails and texts, thus localising the problem. This knowledge was complemented by data gathered by a series of autonomous sensors placed at strategic distances along the river itself, while a team of drones were then employed to physically visit inaccessible sites and collect further information.

All of this data could then be relayed back to a central control centre, where the limited human resources could concentrate on interpreting it and taking appropriate action. As such, menial time-consuming tasks are relegated to AI and humans can make the most of their own expertise and maximise the use of their precious time.

Camacho and Córdova recently pitched their idea to Aquahacking, the Ottawa River summit, earlier this year.