• This field is for validation purposes and should be left unchanged.
  • Earth.Org Newsletters

    Get focused newsletters especially designed to be concise and easy to digest

  • This field is for validation purposes and should be left unchanged.
SHOP Support

Agriculture accounts for around 70% of all water withdrawals globally according to the World Bank, and approximately 60% of that is wasted, largely due to inefficient applications according to the UN’s Food and Agriculture Organisation (FAO). With water increasingly valuable against the backdrop of a rising human population and climate change, can AI be used to prevent water wastage? 

Simple techniques like rainwater harvesting and wastewater recycling are already being used in many regions to reduce water consumption. And many farms have realised the benefits of replacing their surface and sprinkler irrigation systems with more efficient drip irrigation systems.

But there’s another technology that could provide much bigger benefits to farms the world over: Artificial Intelligence.

You might also like: Using Oysters as a Flood Defence Strategy

Global water stress map (Courtesy of TheCropSite)

How can AI solve climate change?

An Italian startup, Blue Tentacles, has come up with a “precision based” AI system that takes note of humidity, temperature, climate data and forecasts as well as satellite data to help farmers improve their irrigation practices whilst preventing water wastage and conserving energy.

In Japan, similar digital farming solutions collect data from soil and light sensors to advise on the quantity of water and fertilisers required. This is particularly useful to inexperienced farmers who might need help to improve productivity while reducing water consumption. These digital technologies are already being used by a number of large scale company run farms in Japan like GRA Inc, a strawberry farm that has gained a competitive edge by embracing technology.

A fuzzy logic system developed in Cordoba Spain, assesses and predicts the varying water needs of different users (for example, different crop growers in an association). This allows farming associations to not only manage water supplies more efficiently, but also to schedule maintenance and repair tasks, hire staff and manage electricity usage more effectively.

ConserWater tracks how water is distributed in a field using satellite and historical data. This allows users to fine tune their irrigation supply and also identify any leaks in the irrigation pipes. Their AI system can learn to identify damaged areas in a pipe without the need for manual inspection. It is a scalable solution working without ground sensors, and farmers would only need a desktop or a smartphone to access the data and receive notifications. Their products are being used by a 100+ farmers across the globe.

The fight to preserve freshwater extends beyond bucolic countryside hedges spilling into hydro-supply monitoring. UK-based United Utilities has partnered with Emagin to develop AI to manage their water networks and plan to test the technology on leakage reduction.

Similarly, WINT Water Intelligence in the US has developed an AI system to analyse water flow in residential and commercial buildings, identifying faults, waste and leaks and, if needed, shutting off a water supply to prevent damage. While this system has been designed for commercial facilities and manufacturing industries, similar solutions could be exported to the farming sector.

The agricultural sector is primed for disruption, from automating the analyses of aerial imagery of a field to identifying crop stress, weather forecasts and supply-chain optimisation. But how to ensure global wide-scale adoption?

Granular data collection for each farming zone is key and governments should facilitate it as much as possible. Data is the backbone for any AI system and the sooner it is collected the more historical data will be available for calculations.

Providing tools and training to farmers is equally essential. In 2017, when India collaborated with Israeli scientists and agronomists to establish drip irrigation in the country, teams of specialists educated local farmers through seminars and field visits to smooth the shift to new tools and practices.

Also in India, Microsoft collaborated with ICRISAT (International Crops Research Institute for Semi Arid Tropics) developing a predictive analytics app that calculated the best crop sowing date for maximising the yield. As a test case, farmers across seven villages were sent text messages with dates for sowing and other advice. Despite meager rainfall, farmers that used the app boosted their yields by 30%. When other farmers witnessed the results, they were also more likely to use the app themselves.

Introducing new methods and sophisticated machinery is expensive and would require tax breaks and financial support. This could come in the form of private sector grants like Microsoft’s AI for Earth Grant or through government policy. Funding would also be required to ensure adequate testing of the technology in the farms once it is developed.

Preventing water wastage  is not an intractable issue but whatever new AI tools or systems are devised, widespread public awareness and adoption should be a top priority. The OECD projects that Northeast China, Northwest India and Southwest USA are fertile grain belts supporting millions of people but also areas on the verge of imminent water scarcity.

Featured image by jcomp/ Freepik

Artificial Intelligence (AI) is a somewhat controversial concept in the age of rapid technological advancement and while it is changing the future of human productivity as we know it, it can also be used in climate science, aiding researchers who are fighting against the clock to mitigate the climate crisis. 

First came the machines. With their steamy puffs and oily gears they complemented and almost replaced manual work, yanking mankind into the industrial age. Now comes Artificial Intelligence, and with it a promise revolutionise all things human.

What is Artificial Intelligence?

Artificial Intelligence- or the ability of machines to learn and perform ever more complex tasks- is opening up endless possibilities for science. And climate change researchers have made it a weapon of choice.

Maria Uriarte and Tian Zheng from Columbia University and the Data Science Institute in London are using Artificial Intelligence to understand how tropical storms affect forests.

In October 2017, the most powerful storm to strike Puerto Rico since 1928 wreaked havoc across the nation, tearing up houses in its way and claiming over one thousand lives. It also strained the local ecosystem. Thousands of acres of the El Yunque National Forest lay in a battered state, with large trees uprooted and no more canopy to shield the soil from the torching Caribbean sun.

Forests play a key role in cooling the Earth’s climate by sequestering carbon from the atmosphere. When forests are damaged and trees decay, less carbon is stored, and more carbon remains in the atmosphere, exacerbating global warming.

If the cycle of damage and regrowth occurs more often as extreme storms become more frequent, some forests may never recover completely. Forest regeneration is thus closely linked to the carbon cycle and plays a key role in the dramatic shifts in climate of our age.

Uriarte and Zheng collected thousands of high-resolution photographs taken from satellites and planes of the affected areas in an effort to identify which tree species best weathered the storm and how factors like soil composition, erosion, slope and rainfall contribute to overall forest regeneration.

Remote sensing technology for environmental monitoring is usually paired with in-site calibrations to increase data accuracy. The team identified and mapped every single tree within a selected 40-hectare plot of damaged forest. Pairing this ground information with the satellite images, a purposely-built algorithm calculated what the various species of trees look like in the satellite and aircraft images.

The team then replicated this process onto a larger area and used the correlated data to improve the algorithm. This process of continuous refinement to obtain pattern recognition and correlations across vast amounts of data is at the core Artificial Intelligence.

You might also like: Artificial Corals: Improving the Resilience of Coral Reefs (part II)

Shredded trees in El Yunque National Forest, Puerto Rico. Photo by Mark Davis, USFWS.

Uriarte says her work could not be done without Artificial Intelligence- “there’s only so much that one can do on the ground… and then there are areas that are simply not accessible. The flyovers and the Artificial Intelligence tools are going to allow us to study hurricanes in a whole different way. It’s super exciting.”

Artificial Intelligence-based research grants are becoming more common, also thanks to the contributions of the private sector. The research was backed by Artificial Intelligence for Earth program, a USD 50$ million endeavour financed by Microsoft which is now supporting 60 research groups in over 20 countries. The programme has enabled researchers like Uriarte and Zheng to analyse remote-sensing data sets from Esri, a mapping and geospatial-analysis company, using Microsoft’s Artificial Intelligence algorithms and computing.

Other Climate Science Applications using Artificial Intelligence: Algorithms and Cloud Behaviour

Processing large amounts of data is particularly useful for increasing the accuracy of forecasting models. Claire Monteleoni from George Washington University is sharpening up climate change predictions with machine-learning techniques.

Her algorithms weigh the averages of over 30 climate forecasting models used by the UN-led Intergovernmental Panel on Climate Change (IPCC), the most important multilateral a multi-stakeholder body focussing on climate change. The new averages give added weight to predictions that prove to be more accurate and less weight to those performing historically poorly.

“These algorithms generate better results over time than the conventional approach that treats all models equally”, Monteleoni says. She is one of the growing number of researchers helping to pioneer the marriage of machine-learning techniques with climate change science, known as “climate informatics”.

Similarly, Pierre Gentine and his team at Columbia Engineering are overcoming one of the biggest challenges in climate modelling – how to adequately represent clouds and their atmospheric heating and moistening.

They used a deep neural network architecture – a form of machine learning – to compute the data and draw parallels between cloud forecasting models. They were able to dramatically refine the prediction capacity of cloud movement along with their moistening, heating and radiative features. Their success in capturing cloud behaviour improves predictions of the climate’s response to rising greenhouse gas concentrations.

Realistic climate simulations require huge reserves of computational power. New algorithms allow interactions in the atmosphere to be modelled more rapidly, without loss of reliability.

Too Complex To Be Trusted?

Deep neural networks have become ever more sophisticated and we are losing visibility into the reasoning process. The sheer multitude of variables and connections are so complex and beyond the cognitive absorption of any human being, that the results pose a concern of trust.

In its report Harnessing Artificial Intelligence for the Earth, World Economic Forum recommends that researchers continue to improve the reliability of Artificial Intelligence, while admitting that it represents the “ fundamental and most pervasive emerging technology of our time” and able to electrify and propel Earth studies into a new dimension of possibilities.

The burgeoning field of Artificial Intelligence-driven climate studies is one example of how a field of science is progressing leaps and bounds thanks to machine learning techniques. The much heralded “information age” where big data and the ability to digest it seem to underpin our every step forward has arrived. Welcome to the Fourth Industrial Revolution.

While Artificial Intelligence can be intimidating and frankly frightening, if used in climate science, it can be harnessed to benefit the future of humanity and the planet. 

Subscribe to our newsletter

Hand-picked stories once a fortnight. We promise, no spam!

Instagram @earthorg Follow Us