Researchers have developed a machine learning model that can identify Gamba grass from high resolution satellite imagery with up to 90 percent accuracy.
Scientists from Charles Darwin University, the University of Western Australia and the CSIRO have developed and trained the model to detect the invasive weed from high resolution multispectral imagery.
Gamba grass is a Weed of National Significance in northern Australia that can grow in tussocks up to 4m high and burn in large hot fires in the dry season. The scale and remoteness of the areas it affects make on-the-ground mapping approaches impractical, according to the CSIRO and Associate Professor Samantha Setterfield from the University of Western Australia.
“Mapping gamba grass using satellite imagery unlocks the potential to frequently map large areas so we can get a better picture of where gamba grass is across northern Australia, and how quickly it is spreading,” she said.
When reckless lending by major US banks erupted into the 2008 global financial crisis, many blamed the institutions’ massive size. But when physics professor Sean Cornelius takes a scientific lens to the problem, he sees a deeper culprit.
“History is full of well-intentioned but disastrous policies fouled by the lack of complex systems thinking.”
Cornelius, along with fellow professors Eric De Giuli, Catherine Beauchemin and Aidan Brown are among a growing community that researches systems characterized by nonlinear dynamics, adaptive responses, unexpected behaviors and hence, limited predictability.
Tackling such densely connected problems falls under complex systems science. As of 2020, Ryerson University’s Department of Physics is among only a handful of schools in North America, let alone Ontario, to offer formal training in it, with new courses at the master’s and PhD levels.
National Institutes of Health (NIH), NIH Office of the Director
from
The National Institutes of Health has awarded nearly $45 million to expand the research network of the Rapid Acceleration of Diagnostics Underserved Populations (RADx-UP) program, adding 20 institutions and seven states and territories. RADx-UP aims to enable and enhance COVID-19 testing of populations disproportionately affected by the disease, including African Americans, American Indians/Alaskan Natives, Latinos/Latinas, Native Hawaiians, older adults, pregnant women and those who are homeless or incarcerated. This second round of awards brings the total investment in the RADx-UP program to more than $283 million at 55 institutions across 33 states and territories and the Cherokee Nation.
The European Union has proposed new rules to allow companies access to public and personal data, an effort to compete with U.S. and Asian giants and encourage innovation in areas like climate change and health.
The rules proposed by the European Commission, the bloc’s executive body, would grant businesses and research organizations access to data normally blocked off due to privacy, commercial confidentiality, or intellectual property rights. It will also make it easier for people to donate their data for non-commercial research.
The bloc’s tough data protection rules, called the General Data Protection Regulation or GDPR, would still apply
A new tech regulator will work to limit the power of Google, Facebook and other tech platforms, the government has announced, in an effort to ensure a level playing field for smaller competitors and a fair market for consumers.
Under the plans, the Competition and Markets Authority (CMA) will gain a dedicated Digital Markets Unit, empowered to write and enforce a new code of practice on technology companies which will set out the limits of acceptable behaviour.
The code will only affect those companies deemed to have “strategic market status”, though it has not yet been decided what that means, nor what restrictions will be imposed.
The business secretary, Alok Sharma, said: “Digital platforms like Google and Facebook make a significant contribution to our economy and play a massive role in our day-to-day lives – whether it’s helping us stay in touch with our loved ones, share creative content or access the latest news.
The draft version of the new law significantly increases penalties for companies responsible for data breaches, proposing fines of up to US$7.6 million
Given the huge size of the Chinese big data market, some believe the penalties under the new law are light and that it has some shortcomings
Hacker houses are making a comeback for entrepreneurs as remote work drags on. While founders are adapting to quarantine in style, a group of college women in their 20s aren’t waiting until they are done with undergraduate work to plunge into the lifestyle themselves.
Started by college juniors Coco Sack and Kendall Titus, Womxn Ignite is a house for female and nonbinary college undergraduates studying computer science. The idea was born out of Sack and Titus’s exhaustion with remote school at Yale and Stanford respectively. After too many boring Zoom lectures, they took gap semesters and searched for a productive way to spend their time off.
“There are a lot of [programs] that target younger women to get them into coding in high school, and there [are] a lot of syndicates and founder groups for women late into their careers,” Titus said. “But there was nothing for anyone in the age range of 20 to 25 where you’re trying to find your way, raise your voice and hold your ground.”
Several Canadian universities are preparing to test wastewater from long-term care homes in Ottawa, Toronto and Edmonton to get early warnings of COVID-19 outbreaks.
Researchers in municipalities in six provinces are already testing wastewater for traces of SARS-CoV-2, the virus responsible for the disease. Many of those infected shed the virus through their feces, even if they don’t have symptoms, according to researchers.
But that kind of testing uses samples from wastewater facilities and shows the results for an entire community. Researchers currently aren’t able to pinpoint the exact locations where outbreaks are flaring up.
A study that tests for parts of the coronavirus in sewage has helped give public health workers advance notice of virus surges, and officials say this kind of testing could eventually help them direct resources to the places that need them the most.
As part of a study contracted through the University of Kansas School of Engineering, the City of Lawrence has been taking weekly sewage samples at both of its wastewater treatment plants to test for components of the virus shed in feces. The city has also been sharing that data with local and state health departments.
Lawrence-Douglas County Public Health spokesman George Diepenbrock said that the presence of the virus in wastewater has served as an early predictor of surges in positive cases, providing about a week’s notice and giving the health department valuable lead time.
State officials have expanded a coronavirus-related wastewater study, but several cities have declined to participate, with Tioga citing concerns that testing could become too intrusive.
North Dakota’s Emergency Commission and the Legislature’s Budget Section last month approved $675,000 in repurposed federal CARES Act coronavirus aid to expand the state Department of Environmental Quality study of cities’ wastewater to analyze coronavirus presence. The money includes $600,000 for North Dakota State University for testing, equipment and other work.
Wastewater samples are delivered to NDSU in Fargo, which does the lab analysis for the virus’ genetic material, measured as millions of viral particles per person per day.
University of Chicago, Chicago Maroon student newspaper, Michael McClure
from
Understanding the set of social factors that influence health outcomes is crucial to modeling the effects of the COVID-19 pandemic, according to University of Chicago health geographer Marynia Kolak.
In a talk on November 17 hosted by the Triple Helix, an undergraduate organization focused on the intersection of science and society, Kolak discussed the process of analyzing the impact of the COVID-19 pandemic using the social determinants of health (SDOH): opportunity, mobility, support, and advantage. With SDOH in mind, Kolak and her research colleagues at UChicago have built the U.S. COVID Atlas, which identifies and tracks hotspots at the county and state levels and helps communities predict the trajectory of the pandemic.
Kolak is the assistant director for health informatics and a lecturer in geographic information science (GIS) at the University’s Center for Spatial Data Science. She conducts research on the ways location and environment can affect individual health outcomes by combining sociological and scientific methods.
A rising tide of COVID-19 cases is putting pressure on supplies of tests for the novel coronavirus. Now, some scientists think they might have found a way to relieve some of that pressure. They say they can narrow down who should be tested by using sounds hidden in human vocal cords.
Eight months into the coronavirus pandemic, Colorado doctors and scientists have a growing study sample: tens of thousands of people in the state who have survived COVID-19.
Their initial findings are beginning to trickle in, helping piece together the long-term effects of a virus that has killed more than 2,300 Coloradans and infected more than 200,000.
The first long-term study of COVID-19 Colorado survivors, from UCHealth, is finding that about one-third of highly symptomatic patients who survive reported that after six or seven weeks, they were still struggling.
As health officials around the world tack COVID-19 infection rates, two universities in the U.S. have partnered with Facebook to try to predict infections with real-time survey data.
Dr. Alex Reinhart, an assistant teaching professor of statistics and data science at Carnegie Mellon University and a member of the Delphi Group, says that as health officials were struggling with testing capacity in the spring, they realized they might be able to predict infections by analyzing social media.
“They realized that if we could know when people are experiencing symptoms, they probably experience symptoms a few days before seeing a doctor. That’s probably a few days before they get test results back and so that could potentially be an early indicator,” Reinhart said.
The Delphi Group reached out to Facebook, which agreed to help them survey its users.
The University is currently ranked #11 in overall best global universities according to U.S. News, but its standing in computer science is far lower. The ranking is based on the department’s research performance.
Within the past 10 years, the number of CS majors at Yale has grown ten-fold, and the program is now the third most popular undergraduate major. But for more than 20 years, the number of faculty in the department did not increase significantly, even as the field has gained popularity. The hiring process is also crippled by subpar facilities, seven faculty who spoke to the News said, and Yale’s science priorities initially placed computer science as an “additional investment area,” not a chief focus of the coming capital campaign.
“If you don’t have a strong computer science research program, you will be left behind in almost all sciences,” computer science professor Lin Zhong said. “What I don’t see from any of the leadership is maybe the epiphany that science has gotten into a watershed moment … Computer science is really going to be one of the centers of scientific activity for humanity for the next century.”
then, having acknowledged the uncertainty, say what research is being done, what people can do in the meantime, and that advice will change as more is learned.”
arXiv, Computer Science > Machine Learning; Andrei Paleyes, Raoul-Gabriel Urma, Neil D. Lawrence
from
In recent years, machine learning has received increased interest both as an academic research field and as a solution for real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. Our survey shows that practitioners face challenges at each stage of the deployment. The goal of this paper is to layout a research agenda to explore approaches addressing these challenges.