Earth Wise

A look at our changing environment.

You are here: Home / Archives for artificial intelligence

artificial intelligence

AI and the appetite for natural gas

By Leave a Comment

A recent survey of the plans of U.S. electricity utilities for meeting projected future demand indicates that they are looking to build twice as much natural gas capacity as they had anticipated just 18 months earlier.  The reason?  Data centers.  These warehouses full of computers that form the backbone of the internet are multiplying rapidly as companies are adding power-hungry servers for artificial intelligence. 

Data centers used less than 2% of U.S. electricity prior to 2018.  They consumed 4.4% in 2023.  By 2028, they are projected to use anywhere between 6.7 and 12%.  While overall electricity demand had been relatively flat for the past 20 years, now the power grid is scrambling to keep up.

The long-term plans of utilities have been favoring renewables for a while.  Previous industry-wide projections had 258 gigawatts of new wind and solar versus 102 gigawatts of new natural gas plants through 2035.  These plans showed that wind and solar could overtake natural gas as the country’s largest source of electricity by that year.  But newer plans adding additional generating capacity have mostly added new gas and very little renewables.

Utilities are leaning heavily on natural gas in part due to the inertia of regulatory actions that define the rate-setting process.  The grid is simply not set up to adapt to new technology and to deal with the unprecedented changes that data centers bring about.

Ultimately, the continuing reliance on natural gas will be an unfortunate burden on the consumer and on the environment.

**********

Web Links

Riding the High From Data Centers, the Grid Cannot Kick Its Gas Habit

Photo, posted January 23, 2023, courtesy of Aileen Devlin / Jefferson Lab via Flickr.

XXXXXXXXXXXXX

AI and energy

By Leave a Comment

MIT recently hosted a symposium on the subject of artificial intelligence being both a problem and a solution for the clean energy transition.

AI-powered computing centers are expanding rapidly, creating an unprecedented surge in electricity demand.  Electricity demand in the US had been relatively flat for decades but now these computing centers consume about 4% of the nation’s electricity.  Some projections say that this demand could rise to 12-15% in the next five years. 

The power required for sustaining some of the AI large-language models is doubling every three months.  The amount of electricity used by a single ChatGPT conversation is as much as it takes to charge a phone and consumes the equivalent of a bottle of water for cooling. 

The MIT symposium focused on the challenges of meeting these growing energy needs but also on the potential for AI to dramatically improve power systems and reduce carbon emissions. 

Research shows regional variations in the cost of powering computing centers with clean electricity.  The central United States offers lower costs due to complementary solar and wind resources but would require massive battery deployments to provide uninterrupted power.

Because of data center demand, there is renewed interest in nuclear power, often in the form of small modular reactors, as well as efforts in long-duration storage technologies, geothermal power, or hybrid approaches.

Artificial intelligence offers both great promise and great peril.  It will take real intelligence to steer it in the right direction.

**********

Web Links

Confronting the AI/energy conundrum

Photo, posted August 31, 2024, courtesy of Jefferson Lab via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

More efficient cooling for data centers

By Leave a Comment

Increasing reliance on digital technologies in general and artificial intelligence in particular are dramatically increasing the energy consumption of data centers.  Data centers consume far more energy per square foot than other commercial buildings.  By the year 2030, data center energy consumption in the US is projected to reach 9% of the country’s electricity generation. 

Computing hardware consumes large amounts of energy and generates large amounts of heat in the process.  Currently, cooling the equipment so it doesn’t burn out accounts for as much as 40% of a data center’s total energy use. 

Engineers at the University of California San Diego have developed a new cooling technology that could significantly improve the energy efficiency of data centers.  The technology makes use of a specially engineered fiber membrane that passively removes heat through evaporation.

The membrane has a network of tiny, interconnected pores that draw cooling liquid across the membrane surface using capillary action.  As the liquid evaporates, it removes heat from the electronics underneath.  No extra energy is required.

Tests of the membrane demonstrated record-breaking performance in removing heat from electronics and being able to withstand very high levels of heat flux.

The researchers say that the technology is still operating well below its theoretical limit, and with additional work, can lead to optimized performance.  The membranes will be integrated into cold plates, which are components that attach to power-hungry computing components to dissipate heat.  The team is also launching a startup company to commercialize the new cooling technology.

**********

Web Links

New Cooling Tech Could Curb Data Centers’ Rising Energy Demands

Photo, posted January 23, 2023, courtesy of Jefferson Lab via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Electricity demand from data centers

By Leave a Comment

Data centers are dedicated facilities containing computers and their related hardware equipment such as servers, data storage drives, and network equipment; they are the physical facilities that store digital data.  Data centers are one of the most energy-intensive building types, consuming 10 to 50 times more energy per floor space than a typical commercial office building.  With the explosive growth of artificial intelligence technology, data center energy use is expanding rapidly.

A new report by the Department of Energy’s Lawrence Berkeley National Laboratory outlines the energy use of data centers from 2014 to 2028.  The report estimates that data center load growth has tripled over the past decade and is likely to double or triple again by 2028.

Data centers consumed about 4.4% of total U.S. electricity in 2023 and are projected to consume between 6.7% and 12% of total U.S. electricity by 2028. Most of the increased power demand of data centers is due to the growth in AI servers.  Artificial intelligence requires increasingly powerful chips and intense, power-hungry cooling systems.

There have been revolutionary changes in artificial intelligence technology in just the past couple of years and its role in society has dramatically expanded.  With that expansion has come a dramatic change in the energy usage by the data industry and innovative solutions are needed to allow data centers to meet their growing demand for energy.

**********

Web Links

Berkeley Lab Report Evaluates Increase in Electricity Demand from Data Centers

Photo, posted August 31, 2024, courtesy of Aileen Devlin / Jefferson Lab via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

The year in energy

By Leave a Comment

Last year saw some major trends in the global energy sector. Perhaps the most dramatic was the shift to renewable power, which continued to outpace the projections of both financial analysts and industry experts.  2024 saw new highs in renewable installation, largely due to China, which accounted for more than half of all the solar power installed globally.  Huge solar installations also came online in California and Nevada during the year.  On the other hand, the amount of coal burning for the year also exceeded expert predictions, also largely due to China.

A second trend was increasing sales of electric vehicles, which reached a new high, although short of expectations.  A major driving force in EV sales is the dropping price of lithium-ion batteries, which fell by 20% in 2024.  Again, China was a major factor with roughly half of all its domestic vehicle sales being electric.

Coal’s decline is being slowed by the rising demand for electricity.  The increased use of electric heating and cooling along with the increasing use of EVs are major factors.  But the proliferation of energy-hungry data centers incorporating artificial intelligence capabilities is driving up the demand for power even more. 

Perhaps the clearest indication of the future for global energy comes from investors, who put about $2 trillion into clean energy last year.  That is twice as much as invested in oil, coal, and natural gas.

The history of energy has seen the Age of Coal and the Age of Oil.  By all indications, we are now heading into the Age of Electricity.

**********

Web Links

The Year in Energy in Four Charts

Photo, posted November 23, 2024, courtesy of Mussi Katz via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Approaching critical global temperature thresholds

By Leave a Comment

The Paris Climate Agreement is a global treaty adopted in 2015 to combat climate change by limiting global warming to well below 2°C above pre-industrial levels, while striving to keep it below 1.5°C.  But according to recent research, the planet is quickly approaching these critical thresholds. 

An international research team led by scientists from Colorado State University, Stanford University, and ETH-Zurich in Switzerland combined insights from 10 global climate models, and – with the help of artificial intelligence – found that regional warming thresholds are likely to be reached faster than previously thought.

In fact, the researchers found that most land regions will likely surpass the critical 1.5°C threshold by 2040 or even earlier.  Additionally, several regions are on track to exceed the 3.0°C threshold by 2060.  Regions including Central Europe, the Mediterranean, South Asia, and parts of sub-Saharan Africa are expected to reach these thresholds faster. 

The research team relied on transfer learning, a cutting-edge machine learning technique that leverages pre-trained models to tackle new, related tasks.

The research, which was recently published in the journal Environmental Research Letters, found that 34 regions are likely to exceed 1.5°C of warming by 2040.  Of those 34 regions, 31 of them are expected to reach 2°C of warming by 2040, and 26 of these 34 regions are projected to surpass 3°C of warming by 2060.

**********

Web Links

AI predicts that most of the world will see temperatures rise to 3C much faster than previously expected

Photo, posted February 23, 2011, courtesy of 2011 CIAT / Neil Palmer via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Artificial intelligence and lost oil wells

By Leave a Comment

There have been commercial oil and gas wells across the United States for 170 years.  Researchers estimate that there are between two and three million wells that have been abandoned.  There are hundreds of thousands of them, across 27 states, that are “orphaned,” meaning that they are uncapped, unproductive, and nobody is responsible to manage their leakage or pollution.

Many are undocumented orphaned wells – UOWs – that are not listed in formal records and are basically out of sight and out of mind.  Besides having nobody responsible for them, nobody even knows where they are.  But they are potential sources of oil and chemical leaks into nearby water sources and can send toxic substances like benzene and hydrogen sulfide into the air. 

Researchers are using modern tools like drones, laser imaging, and advanced sensors to try to locate UOWs.  But these wells are scattered over an area of more than three million square miles.

To better predict where to look for undocumented wells, researchers are combining historical topographic maps with artificial intelligence. The US Geological Survey has scanned 190,000 topographic maps made between 1884 and 2006.  AI is being used to find the symbols for oil and gas wells on the maps.  People can recognize these symbols easily, but there are just too many maps to look at.  The problem is equivalent to finding a needle in a haystack; there is just an awful lot of hay to look through.

Abandoned wells are a big problem and it will take lots of modern technology to try to solve it.

**********

Web Links

AI Helps Researchers Dig Through Old Maps to Find Lost Oil and Gas Wells

Photo, posted August 16, 2022, courtesy of Larry Syverson via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

A giant solar project for Google

By Leave a Comment

One of the largest solar projects in the US has recently come online in Texas.  Three solar farms built side-by-side in Buckholts, Texas by SB Energy can provide 875 megawatts of electricity, nearly the size of a typical nuclear power plant.  The project will supply the largest solar energy purchase ever made by Google and the electricity generated will be used to power its new operations in the area.  Google will use about 85% of the project’s solar power for data centers in Ellis County and for cloud computing in the Dallas Region.

In total, Google has contracted with clean energy developers to bring more than 2,800 megawatts of new wind and solar projects to Texas.  Google expects to spend $16 billion through 2040 to purchase clean energy for its global operations.

According to the International Energy Agency, data centers’ total electricity consumption could reach more than 1,000 terawatt-hours in 2026, which is more than double the amount used in 2022.  One terawatt-hour is enough energy to power 70,000 homes for a year.  So, it is not surprising that large technology companies are investing heavily in energy technologies.

Google, Amazon, and Microsoft have all recently announced investments in nuclear energy to power data centers.  These companies all have made commitments to seek sources of carbon-free electricity to power their data centers and their increasing efforts in artificial intelligence.  Because of the rise of artificial intelligence, the large companies are not meeting their commitments to reduce their carbon emissions and are needing to greatly increase their efforts to obtain clean power.

**********

Web Links

One of the largest solar projects in the US opens in Texas, backed by Google

Photo, posted March 27, 2016, courtesy of Ben Nuttall via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Big Tech and emissions

By Leave a Comment

Most of the well-known largest technology companies have established ambitious clean energy goals.  They are on record for achieving net-zero emissions for all their operations and supply chains in many cases by 2030.  As a result, they have been investing heavily in renewable energy in various ways.  Despite these lofty goals and sincere efforts, many of them are struggling to reduce emissions.  The reason is simple:  big data.

A good example is Google, which started investing in renewable energy in 2010 and since 2017 has been purchasing renewable energy on an annual basis to match the electricity consumption of its global operations. However, Google’s greenhouse gas emissions have increased nearly 48% since 2019.  This is primarily a result of data center energy consumption.

The expanding use of artificial intelligence technology is consuming large amounts of electricity.  For example, a single ChatGPT query uses nearly 10 times as much electrical energy as a traditional Google search.

Google is by no means unique in having this problem.  Microsoft’s carbon emissions have risen by nearly 30% since 2020.  Amazon is struggling to reach net-zero across its operations by 2040.

All of these companies are entering into large power agreements with renewable energy companies all across the country.  The AI arms race for more and more computational power is driving a race to install more and more large-scale renewable energy.   Power purchase agreements for solar power, wind power, and even geothermal power are becoming a major activity for most of the largest tech companies.

**********

Web Links

Can Google gobble up enough renewables?

Photo, posted February 12, 2023, courtesy of Geoff Henson via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

AI’s Environmental Footprint

By Leave a Comment

Artificial intelligence is everywhere these days.  Some say it is the biggest development since the discovery of fire.  There is a lot of hype regarding AI, and it will be a while before the hype is sorted out from the reality.  But one thing that is certain is that AI is resource-intensive and has a large environmental footprint.

AI use directly produces carbon emissions from its consumption of non-renewable electricity and is also responsible for the consumption of billions of gallons of fresh water.

Various forms of AI run on many types of devices, but the kind of AI we hear about the most – such as ChatGPT – requires specialized computer equipment that runs in large cloud data centers.  There are roughly 10,000 such centers worldwide and more are under construction.  Estimates are that electricity consumption from data centers will double between 2022 and 2026 to a total of 1,000 terawatts, roughly as much electricity as all of Japan uses.

These estimates include all data center activities, not just AI.  Most operators of data centers don’t reveal what percentage of their energy use comes from AI.  One exception is Google, which says machine learning accounts for about 15% of its data center energy use.

Data centers also consume a great deal of water to cool delicate electronics.  In 2022, Google’s data centers consumed about 5 billion gallons of fresh water.

AI has the potential to improve the efficiency of systems, improve climate models, and perhaps help develop new ways to help reduce humanity’s environmental footprint.  But at the moment, it represents an increasing burden on the environment that cannot just be ignored.

**********

Web Links

As Use of A.I. Soars, So Does the Energy and Water It Requires

Photo, posted January 23, 2023, courtesy of Aileen Devlin / Jefferson Lab via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Rivers And Climate Change | Earth Wise

By Leave a Comment

Our planet is heating up.  Scientists have concluded that the changing climate is primarily the result of increased greenhouse gas emissions from human activities.  Some of the effects of global climate change include thawing permafrost, rising seas, intensifying storms and wildfires, and warming oceans.   

According to a new study led by researchers from Penn State University, rivers are warming and losing oxygen even faster than oceans.  The study, which was recently published in the journal Nature Climate Change, found that warming occurred in 87% and oxygen loss occurred in 70% of the nearly 800 rivers studied.

The research team projects that within the next 70 years some river systems, especially those in the American South, will experience such low oxygen levels that the rivers could “induce acute death” for some fish species and threaten the aquatic diversity of river ecosystems. 

The research team used artificial intelligence and deep learning to analyze water quality data from nearly 800 rivers across the U.S. and central Europe.  The researchers found that rivers are warming up and deoxygenating faster than oceans, which could have serious implications for both aquatic life and humans.

While climate change has led to warming and oxygen loss in oceans and lakes around the world, the researchers did not expect to find warming and deoxygenation in shallower, flowing rivers.  Since life in water depends on temperature and dissolved oxygen, the researchers hope this study serves as a wake up call.  Warming and deoxygenating rivers have significant implications for water quality and the health of aquatic ecosystems worldwide.

**********

Web Links

Rivers are rapidly warming, losing oxygen; aquatic life at risk

Photo, posted June 2, 2017, courtesy of Francisco Anzola via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Chatbots Are Thirsty | Earth Wise

By Leave a Comment

We hear a lot about artificial intelligence these days.  ChatGPT has found its way into education, technology, and many other aspects of life.  It and its brethren are a source of fascination, enthusiasm, and even fear.  Many of us have given queries to the bot to see what kind of results we can obtain.  But a recent study has found out something about AI systems that we probably didn’t know – they use up lots of fresh water.

According to researchers at the University of California, Riverside, running a few dozen queries on ChatGPT uses up about half a quart of fresh water from already overtaxed reservoirs.

Running artificial intelligence systems like ChatGPT relies on cloud computations done in racks of servers in warehouse-sized data processing centers.  Google’s data centers in the U.S. alone consumed nearly 3.5 billion gallons of fresh water in 2021 in order to keep their servers cool.

Data processing centers consume water in two ways.  They often draw much of their electricity from power plants that use large cooling towers that convert water into steam emitted into the atmosphere.  In addition, the servers themselves need to be cooled to keep running and are typically connected to cooling towers as well.

It isn’t going to be easy for AI systems to reduce their water use.  The study’s authors noted that people make use of AI at all hours of the day and night.  But a significant amount of AI activity is actually the training of the systems.  That could be scheduled for the cooler hours, when less water is lost to evaporation.

In an era of scarce fresh water and droughts, it is important to make AI less thirsty.

**********

Web Links

AI programs consume large volumes of scarce water

Photo, posted May 22, 2023, courtesy of Jernej Furman via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Giant Farming Robots | Earth Wise

By Leave a Comment

Farmers are perpetually engaged in a battle against weeds, which can strangle crops and destroy their yields.  There are basically two ways to fight weeds:  spraying herbicides that are bad for the environment and human health or using human labor to pull the weeds by hand. 

Both choices are increasingly undesirable.  Herbicide resistance is a growing problem facing farms around the world and widespread labor shortages in the agricultural sector are making it increasingly difficult to use human resources to combat weeds.

A startup company called FarmWise founded by an MIT engineering alumnus is providing a third option for farmers.  The company has developed giant autonomous weeding robots that use artificial intelligence to cut out weeds without damaging crops.

The company’s first product is called the Titan.  It looks like a large tractor without a driver’s seat.  It uses machine vision to distinguish weeds from crop plants like leafy greens, cauliflower, artichokes, and tomatoes.  It snips off the weeds with sub-inch precision.

Fifteen titan robots have been roaming the fields of 30 large farms in California and Arizona for several years.  A newer robot, called the Vulcan, is more lightweight and is pulled by a tractor.  FarmWise continues to add new crops to its database so that the robots can be used to fight weeds in more and more kinds of farms.

Weed problems are especially acute for farmers of specialty crops, which grow on smaller farms than corn and soybeans, and have unique growing practices, which limit the effectiveness of chemical and technical solutions. 

The overall goal of FarmWise is to turn artificial intelligence into a tool that is as reliable and dependable as GPS is now in the farming industry.

**********

Web Links

Titanic robots make farming more sustainable

Photo, posted August 23, 2021, courtesy of Carol VanHook via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

Counting Trees | Earth Wise

By Leave a Comment

Scientists estimate that there are about 3 trillion trees on the earth.  A huge number but probably half as many as there were before people entered the picture.  And we’re losing about 10 billion trees a year to toilet paper, timber, farmland expansion, and other human activity.  Trees play a crucial role in taking carbon dioxide out of the atmosphere and storing it away.  For this reason, trees have become an integral part of the effort to mitigate climate change.

There are major initiatives underway around the world to plant more trees.  Part of this is driven by the increasing use of carbon credits by companies trying to offset their carbon emissions.   These credits are earned by either planting new trees or paying farmers or other landowners not to cut down existing trees.  But how many trees are actually planted and how many survive over time?

Whether these efforts are really resulting in more trees and more carbon storage is not easy to determine.  Current international inventories of global tree-sequestered carbon are subject to great uncertainty.

Researchers from the University of Copenhagen and NASA have developed a method for mapping large numbers of trees and determining their carbon content.  Using artificial intelligence techniques to analyze ultra-high-resolution satellite images, they can count trees, determine their individual species, and measure their carbon content.

A study of images from Africa’s Sahel region found that it is home to nearly 10 billion trees that are currently storing 840 million tons of carbon.

Now that the groundwork for this new methodology is complete, it is ready to be deployed by public agencies, NGOs, and other interested in monitoring the numbers of trees and their carbon content.

**********

Web Links

The counting of nine billion trees could help manage climate credits and nature restoration

Photo, posted October 27, 2018, courtesy of Ian Dick via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio

The Sounds Of Coral Reefs | Earth Wise          

By Leave a Comment

Coral reefs around the world face multiple threats from climate change, pollution, and other impacts of human activity.  Reef conservation and restoration projects must be able to monitor the health of reefs and that is not such a simple matter.  Surveying reefs generally is labor-intensive and time consuming.  But in a new study, scientists at the University of Exeter in the UK have found a new way to do it.

The fish and other creatures living on coral reefs produce a vast range of sounds.  The meaning of these various sounds is for the most part unknown, but reefs nonetheless have distinctive sonic signatures.

The Exeter researchers decided to make use of machine learning technology.  They trained a computer algorithm using multiple recordings of both healthy and degraded coral reefs.  This essentially taught the computer to learn the difference between them.  A computer can pick up patterns that are undetectable to the human year.  This application of artificial intelligence can tell us faster and more accurately how a reef is doing.

The computer was then used to analyze a set of new recordings, and successfully identified reef health 92% of the time.  The team then was able to use this technique to track the progress of reef restoration efforts.

It is generally much cheaper and easier to deploy an underwater hydrophone on a reef and leave it there instead of having expert divers make repeated visits to a reef to survey its status.  Sound recorders and artificial intelligence could be used around the world to monitor the health of coral reefs and determine whether efforts to protect and restore them are working.

**********

Web Links

AI learns coral reef “song”

Photo, posted January 11, 2015, courtesy of Falco Ermert via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

Helping Corals With Beneficial Bacteria | Earth Wise

By Leave a Comment

A group of researchers at the King Abdullah University of Science and Technology in Saudi Arabia is exploring a novel technology to improve the health of corals.  Around the globe, corals are being stressed by pathogens, toxins, and warming waters leading to widespread bleaching events.

The new idea is to introduce beneficial bacteria to the corals, thereby boosting the strength and resilience of their symbiotic partners.  The concept is akin to the use of probiotics in plant science.  Corals rely on bacterial and algal symbionts to provide nutrients, energy (through photosynthesis), toxin regulation, and protection against pathogens.  

The researchers selected bacteria that are naturally symbiotic to specific coral species on reefs in the Red Sea, ensuring that no alien bacteria are accidentally introduced.  A probiotic cocktail comprising six bacteria strains was used in a laboratory setting.  Results in the lab have been promising so far, as they have observed dynamic and metabolic alterations to the corals that boosted their chances of survival under heat stress. 

Success in the lab will need to be translated to success in the open oceans, which is challenging.  Scaling up and seeding whole reefs might involve robots and artificial intelligence in order to deliver probiotics either into sediments or directly onto corals.

The use of beneficial microorganisms is not the solution to the global destruction of coral reefs.  Only worldwide CO2 mitigation can ultimately accomplish that.  But the probiotic approach might buy corals some time as they deal with shifting environmental pressures and try to adapt to a changing world.

**********

Web Links

Microbiome boost may help corals resist bleaching

Photo, posted March 18, 2018, courtesy of Steven dos Remedios via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

Rising Seas Will Erase Cities

By Leave a Comment

According to new research, climate-driven sea level rise could affect three times more people by 2050 than previously thought.  This sobering assessment means some of the world’s great coastal cities, including Bangkok, Shanghai, Mumbai, Basra, Alexandria, and Ho Chi Minh City, could be in big trouble.   

Scientists have always relied on land elevation data to determine the effects of sea level rise over large areas.  But standard elevation measurements using satellites struggle to differentiate the true ground level from the tops of trees or buildings.  The authors of the paper developed a more accurate way to calculate land elevation by using artificial intelligence to determine the error rate and to correct for it.  The new findings revealed that 150 million people – three times more than previously thought – are now living on land that is projected to be below the high-tide line by the middle of this century. 

Eight Asian nations – China, Bangladesh, India, Vietnam, Indonesia, Thailand, the Philippines, and Japan – account for about 70% of the people living on at-risk land. 

More than 20 million people in Vietnam, including much of Ho Chi Minh City, live on land that will be inundated by 2050.  In Thailand, more than 10% of its citizens, including much of Bangkok, currently live on land imperiled by projected sea level rise. 

This new research was produced by Climate Central, a New Jersey-based science organization, and was recently published in the journal Nature Communications. 

Sea level rise is clearly not just an environmental problem.  It’s a humanitarian crisis.

**********  

Web Links

New elevation data triple estimates of global vulnerability to sea-level rise and coastal flooding

Rising Seas Will Erase More Cities by 2050, New Research Shows

Photo, posted December 18, 2009, courtesy of Misko via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

Bioacoustics

By Leave a Comment

Researchers are increasingly placing microphones in forests and other ecosystems to monitor birds, insects, frogs, and other animals.  Advances in technology are enabling the wide-spread use of bioacoustics as an important research tool.

Studying animals in their natural habitat Is often a difficult task.  For one thing, many animals are difficult to find, and the presence of humans disrupts their behavior or even drives them off.  Remote cameras are useful, but cameras can only see what is in front of them and aren’t much use for detecting small animals, hidden animals, or ones high up in trees.

Biologists have long recognized the value of recording sound to identify animals and learn about their havior.  Animal sounds can be as definitive a means of identification as visual images and microphones can pick up the sounds from animals located anywhere within their detection range.

The two advances in technology that are turning bioacoustics into a widely used tool are a steep drop in the price of recording equipment and the rapidly expanding capabilities of user-friendly artificial intelligence algorithms.

Autonomous environmental audio recorders tended to cost between $500 and $1000 until quite recently.  Now, such equipment can be had for as little as $70.

The other big challenge is analyzing audio data.  Finding specific animal sounds among hundreds of hours of recordings is an untenably tedious task.  Identifying the characteristic sounds of specific species in crowded environments is a tricky business.  But neural network-based artificial intelligence technology is making such big data analysis quite practical and, remarkably, it is becoming quite user-friendly.

**********

Web Links

Listening to Nature: The Emerging Field of Bioacoustics

Photo, posted January 28, 2013, courtesy of Felix Uribe via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

Predicting Lightning Strikes

By Leave a Comment

Lightning is one of the most unpredictable phenomena in nature.  Approximately 100 lightning bolts strike earth’s surface every second, and each lightning bolt can contain up to one billion volts of electricity.  Lightning regularly kills both people and animals and sets homes and forests on fire.  It’s also been known to ground airplanes. 

Researchers at EPFL – a research institute and university in Switzerland – have developed a novel way to predict where and when lightning will strike.  The system relies on a combination of standard data from weather stations and artificial intelligence to predict lightning strikes to the nearest 10 to 30 minutes and within a radius of less than 20 miles.  The simple and inexpensive system was outlined in a research paper recently published in Climate and Atmospheric Science, a Nature partner journal.   

According to researchers, the current systems for predicting lightning strikes are slow, expensive, and complex, relying on external data acquired by satellite and radar.  The new inexpensive system from EPFL uses real time data that can be obtained from any weather station, meaning it can cover remote regions that are out of radar and satellite range and where communication networks are lacking.  The quick predictions from the system allow alerts to be issued before a storm has even formed. 

The system uses a machine-learning algorithm that’s been trained to recognize conditions that lead to lightning.  The researchers took into account atmospheric pressure, air temperature, relative humidity, and wind speed, among other things.  After training the algorithm, the system was able to predict lightning strikes accurately nearly 80% of the time.

This system is a simple way to predict a complex phenomenon. 

**********

Web Links

Using AI to predict where and when lightning will strike

Photo, posted December 14, 2018, courtesy of Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

Weather-Responsive Traffic Signals

By Leave a Comment

We all spend time sitting at red lights – sometimes it seems like a whole lot of time.  There is a fair amount of science applied in the design of traffic signals that at least has the aim of easing congestion and improving traffic safety.

Signals in modern cities are timed using optimization models that analyze multiple factors including traffic volume and speed with the goal of safely getting as many vehicles as possible through intersections.  It sure doesn’t seem that way in many places, but that is the intent in any case.

But a real problem with these models is that they assume normal conditions including weather conditions.  In places that experience real winter conditions, the assumptions of traffic models fail.  If the road surface is covered with snow and ice and visibility is poor, variables like speed and stopping distances become very different.

Researchers at the University of Waterloo in Canada collected data from real-world intersections and ran computer simulations to determine the effects of adjusting traffic signal behavior in bad weather (as well as in the presence of other conditions such as accidents or construction.)  They found that such adjustments could reduce traffic delays by as much as 20%.   

Cities with computerized signal systems are already equipped to remotely and inexpensively adjust the timing of traffic lights.  To gain the benefits of smarter signals, there would need to be video cameras and a certain amount of artificial intelligence software that would be able to automatically tweak the timing of lights in response to traffic changes caused by weather, accidents or construction. 

It sounds like a great idea.

**********

Web Links

Weather-responsive intersections could ease traffic congestion

Photo, posted September 22, 2009, courtesy of Tristan Bowersox via Flickr.

Earth Wise is a production of WAMC Northeast Public Radio.

WAMC Northeast Public Radio

WAMC/Northeast Public Radio is a regional public radio network serving parts of seven northeastern states (more...)