It’s possible that I shall make an ass of myself. But in that case one can always get out of it with a little dialectic. I have, of course, so worded my proposition as to be right either way (K.Marx, Letter to F.Engels on the Indian Mutiny)
Tuesday, September 06, 2022
Local food boon spurred by pandemic may be short-lived, new research reports
IMAGE: NEW RESEARCH SHOWS THAT WHILE LOCAL FOOD OUTLETS RECEIVED SIGNIFICANTLY MORE ATTENTION FROM CONSUMERS AS A RESULT OF THE PANDEMIC, THOSE IN THE LOCAL FOOD COMMUNITY SHOULD NOT EXPECT THE ELEVATED INTEREST TO CONTINUE.view more
CREDIT: JOSHUA SCHEINBERG / PENN STATE
The COVID‐19 pandemic affected American households in countless ways, but according to researchers, some of the most tangible shifts are taking place in the food system.
A combination of supply chain issues, tighter budgets, concern about shopping in public spaces, and increases in at-home preparation has led to a greater interest in sourcing food locally, but the question remains how long that interest will last. A team of researchers from Penn State’s Department of Agricultural Economics, Sociology and Education conducted a study to find out.
Their results, recently published in the journal Agribusiness, indicate the boon to local food producers may be short-lived, especially if consumers are feeling a sense of anxiety.
“During the pandemic, food consumption changed and so did the sourcing of that food,” said Martina Vecchi, assistant professor of agricultural economics at Penn State and lead author on the study. “A lot of people started exploring different ways of purchasing food and we wanted to understand the determining factors in their decisions.”
Using an online survey, the researchers asked 1,650 participants to reflect on the pandemic and their willingness to buy food locally. Their results suggest that thinking about the pandemic increased anxiety, reduced a sense of community belonging, and lowered the price premiums that respondents were willing to pay for local fruits, vegetables and meat.
“The main mechanism that drives the decreased willingness to pay for locally produced food is anxiety,” Vecchi said. “We didn't expect this, but managing anxiety might be one of the most important things we can do to protect general health were there to be another health crisis.”
The researchers began the survey by inducing or “priming” a subset of participants to think about the impact of the pandemic on either their personal life, finances and health or on their local community and its members. They found that both prompts or “primes” increased participants’ levels of anxiety, slightly reduced their sense of community, and significantly decreased the hypothetical price premium participants were willing to pay for local food.
“We thought of those as the two mechanisms that could influence the willingness to buy this type of product: anxiety and sense of community,” Vecchi said. “We assumed that as people got more anxious because of the pandemic, they would buy more local food because they thought it was safer. We also thought it might strengthen their sense of community and would therefore reflect a higher willingness to pay for local food.”
The results show a trend in the opposite direction. As anxiety increased, sense of community decreased. Vecchi explains that the rise in local food sales during the pandemic may simply be a byproduct of supply chain issues and fears about supermarkets, not a reflection of permanent changes in consumer behavior.
“It doesn't appear that their actual willingness to invest in local food was higher,” Vecchi said. “Sure, they were paying for local food, just because they felt that was the safest option, but it's not that their actual willingness to pay for it was higher.”
The researchers explained that while local food outlets received significantly more attention from consumers as a result of the pandemic, those in the local food community should not expect the elevated interest to continue.
“My advice to policymakers and farmers is to try and deal with consumers’ anxiety and their sense of community first,” Vecchi said. “We have to solve for that if we want to sustain a vibrant local food economy.”
In addition to Vecchi, the research team includes Edward Jaenicke and Claudia Schmidt of Penn State’s Department of Agricultural Economics, Sociology and Education.
The work was funded by a Rapid Response to COVID‐19 Grant by the College of Agricultural Sciences' Institute for Sustainable Agricultural, Food and Environmental Science and the USDA National Institute of Food and Agriculture and Hatch appropriations.
IMAGE: IN THE WAKE OF UNPRECEDENTED MARKET SHOCKS IN THE FED CATTLE INDUSTRY, RESEARCHERS AT THE UNIVERSITY OF TENNESSEE INSTITUTE OF AGRICULTURE TEAMED UP WITH MISSISSIPPI STATE UNIVERSITY AND TEXAS A&M UNIVERSITY TO ANALYZE THE FACTORS AFFECTING PRICE RANGES IN NEGOTIATED CASH SALES. PHOTO COURTESY UTIA.view more
CREDIT: UNIVERSITY OF TENNESSEE INSTITUTE OF AGRICULTURE
In the wake of unprecedented market shocks in the fed cattle industry, researchers at the University of Tennessee Institute of Agriculture teamed up with Mississippi State University and Texas A&M University to analyze the factors affecting price ranges in negotiated cash sales. The study indicates that additional information from the reported data is needed to better understand the outcomes of increased cash sales. Filling these data gaps could help inform proposed legislation and voluntary industry plans in their efforts to uncover drivers of price variability and ultimately price discovery, which is the process of revealing prices from market transactions.
Market shocks in recent years have increased concerns regarding fed cattle prices. The COVID-19 pandemic exacerbated these concerns when fed cattle prices declined, despite wholesale and retail beef prices reaching new highs. The heightened concerns led to policy proposals meant to increase the volume of negotiated cash sales. Proponents believe that increasing negotiated cash sales would improve price discovery by reversing a thinning market.
In response to reenergized concerns about price discovery, researchers launched this latest study to analyze how volume of head sold, day of the week, sex, grade, weight range and other factors impact price ranges in the negotiated cash market. Study results indicate that negotiated cash price ranges peak on Monday and are lowest on Tuesday, but increase from Wednesday to Friday. Price ranges were also found to increase with an increased volume of trade, until reaching approximately 8,800 head per sale per day, then it starts to slowly decline. Further, the study shows that negotiated cash price ranges were highest in the Iowa/Minnesota market relative to all other areas in the study.
“While the motivation of many proposed policies is that increased negotiated purchase volumes will yield improved price discovery, results from this study suggest that daily higher negotiated cash trade volume is not necessarily associated with reduced volatility or improved price discovery,” said lead researcher Chris Boyer. “However, reported price ranges lack important information needed to fully understand how market information impacts price discovery.”
The study indicates that increased information about how many and what quality of cattle were traded near the high and low prices reported would allow for more precise analyses. Also, more detailed data on the distribution of prices such as the fifteenth and eighty-fifth percentile of daily prices and median price would greatly enhance price discovery.
Project team members include Chris Boyer and Charley Martinez from the Department of Agricultural and Resource Economics, along with Joshua Maples from Mississippi State University and Justin Benavidez from Texas A&M University. Martinez and Boyer provide leadership in the newly launched UT Center of Farm Management, which focuses on farm financial management in Tennessee and the Southeast. For more information, visit farmmanagement.tennessee.edu.
Through its land-grant mission of research, teaching and extension, the University of Tennessee Institute of Agriculture touches lives and provides Real. Life. Solutions. utia.tennessee.edu.
Argonne puts climate impact in cities under the microscope with new collaborative study
IMAGE: CROCUS WILL CONDUCT NEIGHBORHOOD-SCALE CLIMATE RESEARCH.view more
CREDIT: (IMAGE BY ARGONNE NATIONAL LABORATORY.)
Community Research on Climate and Urban Science will conduct neighborhood-scale climate research aimed at advancing scientific understanding and empowering communities to identify climate and energy solutions for a sustainable future.
The U.S. Department of Energy (DOE) has awarded DOE’s Argonne National Laboratory and a team of academic and community leaders $25 million over five years to advance urban climate science by studying climate change effects at local and regional scales. The results of this new research will inform communities to build resilience to future effects of climate change.
Argonne and partners will establish an Urban Integrated Field Laboratory called Community Research on Climate and Urban Science (CROCUS) focusing on the Chicago region. CROCUS will use community input to identify questions and specific areas of urban climate change to study, ensuring that research results directly benefit local residents. CROCUS researchers will also work with organizations and students to collect on-the-ground data and develop climate models.
“The Chicagoland area provides a rich environment for study and we are excited to work with such a diverse group of community, research and educational partners.” — Cristina Negri, director of Argonne’s Environmental Sciences division and CROCUS lead
Like other U.S. cities, Chicago is already experiencing disruption from climate change in the form of extreme weather, flooding, drought and heat waves. Unfortunately, the neighborhoods that are most at risk for climate-related disasters have historically been understudied and unable to access the resources or services they need. That’s why CROCUS has strong representation from local organizations to develop its research goals.
Researchers will measure Chicago’s temperature, precipitation and soil conditions. They will explore how trees, open spaces, buildings, expressways and Lake Michigan are shaping the city’s climate, as well as how the Chicago area influences climate regionally. And because no two communities are alike, the study will create more detailed climate models than ever before to reveal the effects of climate change on individual neighborhoods. Instead of looking at the climate of the entire region or city as a whole, researchers will be able to predict how climate will evolve at a much smaller scale — even down to street level. This will help communities identify and vet solutions that will make their neighborhoods resilient against the effects of a changing climate.
“The Chicagoland area provides a rich environment for study and we are excited to work with such a diverse group of community, research and educational partners,” said Cristina Negri, director of Argonne’s Environmental Sciences division and CROCUS lead. “The climate here is noticeably changing. Through CROCUS, we can all join forces to understand the underlying processes and provide science-based information. This will help local planners enact solutions leading to an equitable and effective transition to a resilient and carbon-efficient future for all communities.”
Collaboration is central to CROCUS’s work in Chicago. Argonne is partnering with local, regional and national colleges and universities who will recruit and train the next generation of climate and environmental researchers. To address the underrepresentation of people of color in this field of study, the CROCUS collaborative includes minority-serving institutions and historically black colleges and universities. CROCUS academic partners include:
This study focuses on climate change at the neighborhood level, so the research team includes community-based organizations on Chicago’s South and West Sides. This unique collaboration will empower community members to share their needs and concerns, ensuring that researchers deliver information critical to neighborhoods as they transition to clean energy and green infrastructure. Community partners include:
While Chicago is the center of this study, the new insights and lessons learned will help researchers create a blueprint to assist other cities across the country and around the world as they work to become climate change resilient.
“If we understand how climate and urban systems interact at increasingly detailed scales, we can address the challenge in a fair, equitable and sustainable way,” Negri said. “By advancing the science, we can help neighborhoods, governments and communities envision a climate-ready future. We’re all in this together.”
CROCUS is funded by the Biological and Environmental Research program in the DOE’s Office of Science.
The Argonne Leadership Computing Facility provides supercomputing capabilities to the scientific and engineering community to advance fundamental discovery and understanding in a broad range of disciplines. Supported by the U.S. Department of Energy’s (DOE’s) Office of Science, Advanced Scientific Computing Research (ASCR) program, the ALCF is one of two DOE Leadership Computing Facilities in the nation dedicated to open science.
Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.
The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.
DOE announces $66 million to research the impact of climate change on America's urban communities
Field labs in Baltimore, Chicago, and Texas will study the impact of extreme weather on people, homes, and local infrastructure
WASHINGTON, D.C. — The U.S. Department of Energy (DOE) today announced $66 million in funding for three projects, together involving over 20 institutions, that will develop Urban Integrated Field Laboratories (Urban IFLs) in Baltimore, MD, Chicago, IL, and the Texas Gulf Coast. These Urban IFLs will expand the understanding of climate and weather events and their impact on urban systems, including diverse demographic characteristics; differing climate-induced pressures on people and infrastructures; and varied geographic settings. Understanding how climate change will impact urban systems and infrastructure is key to building resilient cities powered by clean energy, helping achieve President Biden’s goal of a net-zero carbon economy by 2050.
“Understanding the risks of climate change and extreme weather means understanding the direct and indirect effects on people, their homes, their businesses, and the communities they live in,” said U.S. Secretary of Energy Jennifer Granholm. “The Urban Integrated Field Labs will strengthen DOE leadership in climate modeling and drive scientific breakthroughs to inform the development of resilience technology that can protect America’s diverse communities.”
Each Urban IFL project team brings together scientific expertise from multiple institutions with a breadth of expertise in field observations, data assimilation, modeling, and model-data fusion to study the environmental, ecological, infrastructural, and human components of their selected urban regions. The selected projects will advance our scientific understanding of urban systems and harness that understanding to inform equitable climate and energy solutions, strengthening community scale resilience in urban landscapes, and addressing climate change impacts on underrepresented and disadvantaged communities.
The three selected projects will work in three different urban regions that are facing different environmental and climate hazards, and that each have distinct and diverse disadvantaged populations. Each selected IFL includes significant participation from local and minority serving institutions and will provide new opportunities at these institutions to inspire, train, and support leading scientists who have an appreciation for the global climate and energy challenges of the 21st century. The Urban IFLs will serve as an important element of DOE Office of Science’s commitment to the “Justice 40” initiative, which prioritizes investment in diverse and underrepresented communities affected by a changing climate.
The Urban IFL projects include:
Chicago, IL, the 3rd largest city in the nation, led by Argonne National Laboratory, will employ a network of observations and modeling from street to regional scales to explore multiple issues, including mitigation via green roofs and blue spaces, and community-driven future scenarios for adaptation and decarbonization.
Austin, TX, led by the University of Texas at Austin in Beaumont/Port Arthur Texas, focuses on specific challenges of industrialized, medium sized port cities, including significant legacies of petrochemical industry, and how climate change may affect urban flooding and air quality.
Baltimore, MD, led by Johns Hopkins University, focuses on a metropolitan area facing interlinked challenges of aging infrastructure, increased heat and flood risk, and inequitable burdens of air and water pollution that are common to many other mid-sized industrial cities in the Eastern and Midwest United States.
While each project is distinct, each has similarities to other U.S. urban regions and will develop new tools and techniques that will help other cities benefit from the science and success stories of these Urban IFLs.
The projects were selected by competitive peer review under the DOE Funding Opportunity Announcement for Urban Integrated Field Laboratories. Additional selections will be made in fiscal year 2023, subject to the availability of funds.
Total funding is $66 million for projects lasting up to five years in duration, with $18 million in Fiscal Year 2022 dollars and outyear funding contingent on congressional appropriations. The list of projects and more information can be found here.
Major leap for stable high-efficiency perovskite solar cells
Ion-modulated radical doping of spiro-OMeTAD for more efficient and stable perovskite solar cells
IMAGE: FENG WANG, JUNIOR LECTURER AT LINKÖPING UNIVERSITY.view more
CREDIT: ANNA NILSEN
Solar cells manufactured from materials known as “perovskites” are catching up with the efficiency of traditional silicon-based solar cells. At the same time, they have advantages of low cost and short energy payback time. However, such solar cells have problems with stability – something that researchers at Linköping University, together with international collaborators, have now managed to solve. The results, published in Science, are a major step forwards in the quest for next-generation solar cells.
“Our results open new possibilities to develop efficient and stable solar cells. Further, they provide new insights into how the doping of organic semiconductors works,” says Feng Gao, professor in the Department of Physics, Chemistry and Biology (IFM) at Linköping University.
Perovskites are crystalline materials with huge potential to contribute to solving the world’s energy shortage. They are cheap to manufacture, with high efficiency and low weight. However, the perovskite solar cells can degrade quickly, and it has not been possible to build high-efficiency perovskite-based solar cells with the required stability.
“There seems to be a trade-off between high efficiency and stability in perovskite-based solar cells. High-efficiency perovskite solar cells tend to show low stability, and vice versa,” says Tiankai Zhang, a postdoc at IFM and one of the principal authors of the article published in Science.
When solar energy is converted into electricity in perovskite-based solar cells, one or more charge transport layers are usually needed. These lie directly next to the perovskite layer in the solar cell. The organic charge transport layers often need auxiliary molecules in order to function as intended. The material is described as being “doped”.
One doped transport layer called Spiro-OMeTAD is a benchmark in perovskite solar cells, and delivers record power conversion efficiencies. But the present method used to dope Spiro-OMeTAD is slow, and causes the stability issue of perovskite solar cells.
“We have now managed to eliminate the trade-off that has hindered development, using a new doping strategy for Spiro-OMeTAD. This makes it possible for us to obtain both high efficiency and good stability,” says Tiankai Zhang.
Another principal author of the article, Feng Wang, is a junior lecturer at IFM. He points out that perovskite-based solar cells can be used in many ways, and have many areas of applications.
“One advantage of using perovskites is that the solar cells made are thin, which means that they are light and flexible. They can also be semi-transparent. It would be possible, for example, to apply perovskite-based solar cells onto large windows, or building façades. Silicon-based solar cells are too heavy to be used in this way,” says Feng Wang.
The study has been financed by the Swedish Research Council, an ERC Starting Grant, the Knut and Alice Wallenberg Foundation and AFM (the Swedish Government Strategic Research Area in Materials Science on Functional Materials) at Linköping University. Feng Gao is also a Wallenberg Academy Fellow.
CAPTION
Solar cells manufactured from materials known as “perovskites” are catching up with the efficiency of traditional silicon-based solar cells.
Researchers at the U.S. Department of Energy’s (DOE’s) National Renewable Energy Laboratory (NREL) made a technological breakthrough and constructed a perovskite solar cell with the dual benefits of being both highly efficient and highly stable.
The work was done in collaboration with scientists from the University of Toledo, the University of Colorado–Boulder, and the University of California–San Diego.
A unique architectural structure enabled the researchers to record a certified stabilized efficiency of 24% under 1-sun illumination, making it the highest reported of its kind. The highly efficient cell also retained 87% of its original efficiency after 2,400 hours of operation at 55 degrees Celsius.
The paper, “Surface Reaction for Efficient and Stable Inverted Perovskite Solar Cells,” appears in the journal Nature. The authors from NREL are Qi Jiang, Jinhui Tong, Ross Kerner, Sean Dunfield, Chuanxiao Xiao, Rebecca Scheidt, Darius Kuciauskas, Matthew Hautzinger, Robert Tirawat, Matthew Beard, Joseph Berry, Bryon Larson, and Kai Zhu.
Perovskite, which refers to a crystalline structure, has emerged in the last decade as an impressive means to efficiently capture sunlight and convert it to electricity. Research into perovskite solar cells has been focused to a large degree on how to increase their stability.
“Some people can demonstrate perovskites with high stability, but efficiency is lower,” said Zhu, a senior scientist in the Chemistry and Nanoscience Center at NREL. “You ought to have high efficiency and high stability simultaneously. That’s challenging.”
The researchers used an inverted architecture, rather than the “normal” architecture that has to date yielded the highest efficiencies. The difference between the two types is defined by how the layers are deposited on the glass substrate. The inverted perovskite architecture is known for its high stability and integration into tandem solar cells. The NREL-led team also added a new molecule, 3-(Aminomethyl) pyridine (3-APy), to the surface of the perovskite. The molecule reacted to the formamidinium within the perovskite to create an electric field on the surface of the perovskite layer.
“That suddenly gave us a huge boost of not only efficiency but also stability,” Zhu said.
The scientists reported the 3-APy reactive surface engineering can improve the efficiency of an inverted cell from less than 23% to greater than 25%. They also noted the reactive surface engineering stands out as an effective approach to significantly enhance the performance of inverted cells “to new state-of-the-art levels of efficiency and operational reliability.”
Funding for the research done at NREL came from the Center for Hybrid Organic-Inorganic Semiconductors for Energy (CHOISE), an Energy Frontier Research Center within DOE’s Office of Basic Energy Sciences, and from the DOE’s Solar Energy Technologies Office.
NREL is the U.S. Department of Energy's primary national laboratory for renewable energy and energy efficiency research and development. NREL is operated for the Energy Department by the Alliance for Sustainable Energy, LLC.
IMAGE: YORK UNIVERSITY PHD STUDENT MICHAEL DE SANTIview more
CREDIT: YORK UNIVERSITY
TORONTO, Sept. 6, 2022 - Waterborne illness is one of the leading causes of infectious disease outbreaks in refugee and internally displaced persons (IDP) settlements, but a team led by York University has developed a new technique to keep drinking water safe using machine learning, and it could be a game changer.
As drinking water is not piped into homes in most settlements, residents instead collect it from public tap stands using storage containers.
“When water is stored in a container in a dwelling it is at high risk of being exposed to contaminants, so it’s imperative there is enough free residual chlorine to kill any pathogens,” says Lassonde School of Engineering PhD student Michael De Santi, part of York’s Dahdaleh Institute for Global Health Research, who led the research.
Recontamination of previously safe drinking water during its collection, transport and storage has been a major factor in outbreaks of cholera, hepatitis E, and shigellosis in refugee and IDP settlements in Kenya, Malawi, Sudan, South Sudan, and Uganda.
“A variety of factors can affect chlorine decay in stored water. You can have safe water at that collection point, but once you bring it home and store it, sometimes up to 24 hours, you can lose that residual chlorine, pathogens can thrive and illness can spread,” says Lassonde Adjunct Professor Syed Imran Ali, a Research Fellow at York's Dahdaleh Institute for Global Health Research, who has first-hand experience working in a settlement in South Sudan.
Using machine learning, the research team, including Associate Professor Usman Khan also of Lassonde, has developed a new way to predict the probability that enough chlorine will remain until the last glass is consumed. They used an artificial neural network (ANN) along with ensemble forecasting systems (EFS), something that is not typically done. EFS is a probabilistic model commonly used to predict the probability of precipitation in weather forecasts.
“ANN-EFS can generate forecasts at the time of consumption that take a variety of factors into consideration that affect the level of residual chlorine, unlike the typically used models. This new probabilistic modelling is replacing the currently used universal guideline for chlorine use, which has been shown to be ineffective,” says Ali.
Factors such as local temperature, how the water is stored and handled from home to home, the type and quality of the water pipes, water quality or did a child dipped their hand in the water container, can all play a role in how safe the water is to drink.
“However, it’s really important that these probabilistic models be trained on data at a specific settlement as each one is as unique as a snowflake,” says De Santi. “Two people could collect the same water on the same day, both store it for six hours, and one could still have all the chlorine remaining in the water and the other could have almost none of it left. Another 10 people could have varying ranges of chlorine.”
Determining how to teach the ANN-EFS to come up with realistic probability forecasts with the smallest possible error required out-of-the-box thinking.
“How that error is measured is key as it determines how the model behaves in the context of probabilistic modelling,” says De Santi. “Using cost-sensitive learning, a tool that morphs the cost function towards a targeted behaviour when using machine learning, we found it could improve probabilistic forecasts and reliability. We are not aware of this being done before in this context.”
For example, this model can say that under certain conditions at the tap with a particular amount of free residual chlorine in the water, there is a 90 per cent chance that the remaining chlorine in the stored water after 15 hours will be below the safety level for drinking.
“That’s the kind of probabilistic determination this modelling can give us,” says De Santi. “Like with weather forecasts, if there is a 90 per cent chance of rain, you should bring an umbrella. Instead of an umbrella, we can ask water operators to increase the chlorine concentration so there will be a greater percentage of people with safe drinking water.”
“Our Safe Water Optimization Tool takes this machine learning work and makes it available to aid workers in the field. The only difference for the water operators is we ask them to sample water in the container at the tap and in that same container at the home after several hours,” says Ali.
“This work Michael is doing is advancing the state of practice of machine learning models. Not only can this be used to ensure safe drinking water in refugee and IDP settlements, it can also be used in other applications.”
De Santi will deliver a seminar on this paper as part of the Dahdaleh Institute Seminar Series on Sept. 7, from 1 to 2 p.m. EST. It is open to the public and registration is free.
Lassonde School of Enginneering Adjunct Professor Syed Imran Ali, a Research Fellow at York University's Dahdaleh Institute for Global Health Research
CREDIT
York University
CAPTION
Associate Professor Usman Khan of York University's Lassonde School of Engineering
CREDIT
York University
York University is a modern, multi-campus, urban university located in Toronto, Ontario. Backed by a diverse group of students, faculty, staff, alumni and partners, we bring a uniquely global perspective to help solve societal challenges, drive positive change and prepare our students for success. York's fully bilingual Glendon Campus is home to Southern Ontario's Centre of Excellence for French Language and Bilingual Postsecondary Education. York’s campuses in Costa Rica and India offer students exceptional transnational learning opportunities and innovative programs. Together, we can make things right for our communities, our planet, and our future.
Media Contact:
Sandra McLean, York University Media Relations, 416-272-6317, sandramc@yorku.ca
Waterborne illness is one of the leading causes of infectious disease outbreaks in refugee and internally displaced persons (IDP) settlements, but a team led by York University has developed a new technique to keep drinking water safe using machine learning, and it could be a game changer. The research is published in the journal PLOS Water.
As drinking water is not piped into homes in most settlements, residents instead collect it from public tap stands using storage containers.
"When water is stored in a container in a dwelling it is at high risk of being exposed to contaminants, so it's imperative there is enough free residual chlorine to kill any pathogens," says Lassonde School of Engineering Ph.D. student Michael De Santi, who is part of York's Dahdaleh Institute for Global Health Research, and who led the research.
Recontamination of previously safe drinking water during its collection, transport and storage has been a major factor in outbreaks of cholera, hepatitis E, and shigellosis in refugee and IDP settlements in Kenya, Malawi, Sudan, South Sudan, and Uganda.
"A variety of factors can affect chlorine decay in stored water. You can have safe water at that collection point, but once you bring it home and store it, sometimes up to 24 hours, you can lose that residual chlorine, pathogens can thrive and illness can spread," says Lassonde Adjunct Professor Syed Imran Ali, a Research Fellow at York's Dahdaleh Institute for Global Health Research, who has firsthand experience working in a settlement in South Sudan.
Using machine learning, the research team—including Associate Professor Usman Khan, also of Lassonde—has developed a new way to predict the probability that enough chlorine will remain until the last glass is consumed. They used an artificial neural network (ANN) along with ensemble forecasting systems (EFS), something that is not typically done. EFS is a probabilistic model commonly used to predict the probability of precipitation in weather forecasts.
"ANN-EFS can generate forecasts at the time of consumption that take a variety of factors into consideration that affect the level of residual chlorine, unlike the typically used models. This new probabilistic modeling is replacing the currently used universal guideline for chlorine use, which has been shown to be ineffective," says Ali.
Factors such as local temperature, how the water is stored and handled from home to home, the type and quality of the water pipes, water quality and whether a child dipped their hand in the water container can all play a role in how safe the water is to drink.
"However, it's really important that these probabilistic models be trained on data at a specific settlement as each one is as unique as a snowflake," says De Santi. "Two people could collect the same water on the same day, both store it for six hours, and one could still have all the chlorine remaining in the water and the other could have almost none of it left. Another 10 people could have varying ranges of chlorine."
Determining how to teach the ANN-EFS to come up with realistic probability forecasts with the smallest possible error required out-of-the-box thinking.
"How that error is measured is key as it determines how the model behaves in the context of probabilistic modeling," says De Santi. "Using cost-sensitive learning, a tool that morphs the cost function towards a targeted behavior when using machine learning, we found it could improve probabilistic forecasts and reliability. We are not aware of this being done before in this context."
For example, this model can say that under certain conditions at the tap with a particular amount of free residual chlorine in the water, there is a 90 percent chance that the remaining chlorine in the stored water after 15 hours will be below the safety level for drinking.
"That's the kind of probabilistic determination this modeling can give us," says De Santi. "Like with weather forecasts, if there is a 90 percent chance of rain, you should bring an umbrella. Instead of an umbrella, we can ask water operators to increase the chlorine concentration so there will be a greater percentage of people with safe drinking water."
"Our Safe Water Optimization Tool takes this machine learning work and makes it available to aid workers in the field. The only difference for the water operators is we ask them to sample water in the container at the tap and in that same container at the home after several hours," says Ali.
"This work Michael is doing is advancing the state of practice of machine learning models. Not only can this be used to ensure safe drinking water in refugee and IDP settlements, it can also be used in other applications."
More information:Michael De Santi et al, Modelling point-of-consumption residual chlorine in humanitarian response: Can cost-sensitive learning improve probabilistic forecasts?,PLOS Water(2022).DOI: 10.1371/journal.pwat.000004
