Microsoft has offered support for six Australian projects focused on artificial intelligence (AI) to help solve issues related to water, agriculture, biodiversity, and climate change as part of the tech giant's AI for Earth program.
Australian recipients of assistance from the $50 million kitty include Monash University, Griffith University, Queensland University of Technology (QUT), InFarm, the Australian Wildlife Conservancy, and Bush Heritage Australia.
"The need for rapid action in Australia has been reinforced by recent environmental challenges including extended drought, dry-lightning triggered bushfires in Tasmania and Victoria, record high temperatures across the nation, Townsville's flood, and the devastation wrought to agriculture across the Top End by a combination of flooding rains and overnight low temperatures," Microsoft wrote in a blog announcing the funding.
The Faculty of Information Technology at Monash University is receiving assistance under the scheme for its project centred on mapping species distributions.
The team is using social network geo-tagged photos, making use of Azure cognitive services, to provide insight on certain ecological phenomena including insect pollinator distributions and flowering plant activity to understand how they are impacted by climate change.
QUT will be using Microsoft's assistance for its drone-based reef monitoring project, which is exploring how data collected by drones fitted with advanced sensors can be interpreted by AI to aid with the classification and restoration of coral.
The QUT team has built an AI system that interprets images captured by hyperspectral cameras mounted on drones to get a better understanding of the health of the reef.
Griffith University, meanwhile, is using Azure machine learning to develop a prediction model providing greater insights regarding carbon sequestration of green stormwater infrastructure.
The below ground carbon level prediction project, Microsoft said, integrates ecological data with AI to facilitate improved predictions regarding the urban carbon budget.
InFarm is using AI to help identify weed species in fallow fields, specifically those that are chemical resistant, with the Australian startup also using AI to provide application maps for use in autonomous, variable spray tractors.
The company's weed identification and classification project uses drones to survey fields, AI to interpret the images, and the resulting insight to allow targeted weed-spraying estimation that InFarm hopes can reduce farmers' herbicide costs by 95% and also rein in the amount of chemicals used overall.
Also aided through AI for Earth, conservation organisation Bush Heritage Australia and data scientists Jonathan Bourne and Anindya Basu are using Azure virtual machines to develop a species recognition algorithm to estimate the predator population on their properties, which can help predator detection and the protection of threatened species.
The project will see the team process data from 60,000 camera trap images.
Lastly, the Australian Wildlife Conservancy will be assisted in its feral and native fauna identification project, that uses AI and image recognition, to explore how animal identification from 90,000 camera trap images can be automated.
The six Australian projects are among the 230 spread across more than 60 countries which have received AI for Earth grants and support to date.
AI for Earth, launched in 2017, provides AI tools and skills that are focused on solving global environmental challenges. According to Microsoft, AI for Earth is designed to "harness technology to help mitigate and adapt to changing climates, ensure resilient water supplies, sustainably feed a population rapidly growing to 10 billion people, and stem the ongoing and catastrophic loss of biodiversity".
The funding is used to provide Microsoft Azure cloud computing resources, including AI tools and/or data labelling services, as well as access to training on data science, machine learning, and visualisation tools, the company explained.
"The world is seeing rapid advancements in cloud and AI solutions that are unlocking new possibilities to solve the world's most challenging problems. But the uptake of those solutions to understand and protect the planet is proceeding slowly, and as such, we are essentially flying blind when it comes to understanding how our planet is changing and how to best solve environmental challenges. AI can change that," Microsoft chief environmental officer Lucas Joppa said.
"Time is too short and current human resources are too few to solve urgent climate related challenges without the exponential power of AI. By putting AI in the hands of researchers and organisations we can use important data insights to help solve issues related to water, agriculture, biodiversity, and climate change."
Microsoft said at the end of 2018, half the power used by its data centres came from renewable energy and it should hit 60% by the end of 2019. Microsoft is aiming to cut its carbon emissions by 75% by 2030 and as part of that effort has raised its internal carbon "tax" to $15 per metric ton on all carbon emissions, which is nearly double the current rate for carbon emissions.