The same models can also glean other information from animal vocalizations, such as the animal’s age, breed and sex. A collaboration with Mexico’s National Institute of Astrophysics, Optics and Electronics (INAOE) Institute in Puebla, the study finds that AI models originally trained on human speech can be used as a starting point to train new systems that target animal communication.

The results were presented at the Joint International Conference on Computational Linguistics, Language Resources and Evaluation.

“By using speech processing models initially trained on human speech, our research opens a new window into how we can leverage what we built so far in speech processing to start understanding the nuances of dog barks,” said Rada Mihalcea, the Janice M. Jenkins Collegiate Professor of Computer Science and Engineering, and director of U-M’s AI Laboratory.

“There is so much we don’t yet know about the animals that share this world with us. Advances in AI can be used to revolutionize our understanding of animal communication, and our findings suggest that we may not have to start from scratch.”

One of the prevailing obstacles to developing AI models that can analyze animal vocalizations is the lack of publicly available data. While there are numerous resources and opportunities for recording human speech, collecting such data from animals is more difficult.

“Animal vocalizations are logistically much harder to solicit and record,” said Artem Abzaliev, lead author and U-M doctoral student in computer science and engineering. “They must be passively recorded in the wild or, in the case of domestic pets, with the permission of owners.”

Because of this dearth of usable data, techniques for analyzing dog vocalizations have proven difficult to develop, and the ones that do exist are limited by a lack of training material. The researchers overcame these challenges by repurposing an existing model that was originally designed to analyze human speech.

This approach enabled the researchers to tap into robust models that form the backbone of the various voice-enabled technologies we use today, including voice-to-text and language translation. These models are trained to distinguish nuances in human speech, like tone, pitch and accent, and convert this information into a format that a computer can use to identify what words are being said, recognize the individual speaking, and more.

“These models are able to learn and encode the incredibly complex patterns of human language and speech,” Abzaliev said. “We wanted to see if we could leverage this ability to discern and interpret dog barks.”

The researchers used a dataset of dog vocalizations recorded from 74 dogs of varying breed, age and sex, in a variety of contexts. Humberto Pérez-Espinosa, a collaborator at INAOE, led the team who collected the dataset. Abzaliev then used the recordings to modify a machine-learning model — a type of computer algorithm that identifies patterns in large data sets. The team chose a speech representation model called Wav2Vec2, which was originally trained on human speech data.

With this model, the researchers were able to generate representations of the acoustic data collected from the dogs and interpret these representations. They found that Wav2Vec2 not only succeeded at four classification tasks; it also outperformed other models trained specifically on dog bark data, with accuracy figures up to 70%.

“This is the first time that techniques optimized for human speech have been built upon to help with the decoding of animal communication,” Mihalcea said. “Our results show that the sounds and patterns derived from human speech can serve as a foundation for analyzing and understanding the acoustic patterns of other sounds, such as animal vocalizations.”

In addition to establishing human speech models as a useful tool in analyzing animal communication — which could benefit biologists, animal behaviorists and more — this research has important implications for animal welfare. Understanding the nuances of dog vocalizations could greatly improve how humans interpret and respond to the emotional and physical needs of dogs, thereby enhancing their care and preventing potentially dangerous situations, the researchers said.

New research by the University of South Australia has found a connection between pleasant weather conditions and higher investment in lottery-like stocks.

Lottery-like stocks are cheap compared to other stocks and, like lottery tickets, they can be seen as an opportunity to make a substantial gain. However, the chance of a higher return is minimal, and it’s therefore considered a high-risk investment. A study by UniSA finance researchers discovered that when the weather is sunny and skies are blue, investors are more likely to engage in these types of investments.

Dr Reza Bradrania, Senior Lecturer of Finance and member of UniSA’s Centre for Markets, Values and Inclusion, says studies in psychology have shown that weather has a significant effect on human moods and behaviour. It can explain about 40% of daily variation in moods and sunshine in particular can have a large impact on how we feel.

“Since being in a good mood spurs people to take more risks, we were curious to see if weather, as an important factor that impacts human moods, relates to demand for lottery-like stocks which are highly risky and have lottery features like casino or lotto products,” Dr Bradrania says.

“The idea is that investors who are in a good mood because of sunny weather tend to have more optimistic expectations or beliefs about the future payoff of lottery stocks. This investigation was important as it has implications on how weather can influence investors’ judgements and choices and in particular impact their financial decisions.”

“To our knowledge this is the first study of its kind to investigate how weather plays a role in our investment decisions and in particular the demand for and the performance of lottery-like stocks which have implications for financial markets.”

Dr Bradrania and PhD student Ya Gao gathered 36 years’ worth of weather data including hourly sky cloud cover, wind speed rate, rain depth and air temperature from major weather stations across US cities. Price data of common stocks from over this period (1983 to 2019) was also examined.

“We found that on days with pleasant weather conditions, investors were more likely to be risk-taking and optimistic and invest more in lottery-like stocks, which further results in high demand and higher price for these stocks. However, their price is adjusted later, which resulted in significant loss,” Dr Bradrania says.

“Overoptimism is associated with overconfidence in many cases and investors who are overconfident tend to trade lottery-like stocks more. The research suggests weather relates to gambling preference and influences our judgment and choices. It also provides some guidance on investment decisions depending on weather conditions.”

A study published in Nature’s Scientific Reports has found that frequent mowing of Solanum elaeagnifolium may help create a “superweed.”

Solanum elaeagnifolium — also known as silverleaf nightshade — can be found from south Texas to South Africa and Greece, infesting fields and soaking up valuable nutrients intended for cash crops. The weed with purple flowers — sometimes white and light purple — has prickly spines and poisonous berries.

Relatives of the plant, including Solanum ptychanthum or black nightshade, and Solanum carolinense, or Carolina horsenettle, also produce toxic berries and are native to Arkansas. It’s a family that also includes some friendly crops such as tomatoes, potatoes, peppers and eggplants.

Rupesh Kariyat, an associate professor of entomology and plant pathology with the Arkansas Agricultural Experiment Station, has been studying silverleaf nightshade for more than a decade. Kariyat began the study while at the University of Texas Rio Grande Valley, when he and his graduate student Alejandro Vasquez took on what turned into a five-year, two-part study to observe the effects of frequently mowed silverleaf nightshade. Kariyat joined the experiment station, the research arm of the University of Arkansas System Division of Agriculture, in 2022.

Although studies have often highlighted weed fitness and defense traits resulting from disturbances like mowing, most were limited to foliar, or leaf, defenses, Kariyat said. That changed when Vasquez and fellow master’s biology students at the University of Texas Rio Grande Valley monitored fields of mowed, unmowed and frequently mowed silverleaf nightshade in and around Edinburg, Texas.

“Alejandro’s question was, ‘how do these flowers differ between mowed and unmowed plants?'” Kariyat said. “‘And does that have consequences for the insects that actually feed on them?'”

Self-defense strategies

Findings in both studies showed that the more silverleaf nightshade was mowed, the more it developed ways to avoid destruction, Kariyat said. The taproot went down further, nearly 5 feet deep, in the first generation of mowed plants. More spikes popped out on the stem as a defense against caterpillars feeding on the flowers. The flowers became more toxic to caterpillars, leading to less pressure from natural predators.

Like time bombs, the plant produced some groups of seeds that germinated faster and others that were delayed. This “staggered” germination was the plant’s way to ensure survival over the long haul.

“You are trying to mow these plants so that the plants are getting eliminated,” Kariyat said. “But what you are actually doing here, you are making them much worse, much stronger.”

Tilling areas with silverleaf nightshade also spreads the plant because the rhizomic roots, like many weeds, can propagate asexually over multiple years and growing seasons.

The observations of mowed, unmowed and frequently mowed areas with silverleaf nightshade provide evidence that could prompt further studies by weed scientists on best management practices, Kariyat said.

Since the studies focus solely on silverleaf nightshade, Kariyat said other weeds — even the plant’s family relatives — may or may not react the same way to frequent mowing. However, the study does provide more insight into the defensive capabilities of plants pitted against human disturbance.

“This should be something that we consider when we make management plans,” Kariyat said of the plant’s defenses. “Management practices need to be better understood using the ecology and biology of the species and the other species which interact with them.”

Kariyat and Vasquez published their results in April with an article titled “Continuous mowing differentially affects floral defenses in the noxious and invasive weed Solanum elaeagnifolium in its native range.” Vasquez, now an entomology and plant pathology Ph.D. student at the University of Arkansas, was the lead author. Co-authors included Kariyat, Alexa Alaniz, and Robert Dearth, founding director of the School of Integrative Biological and Chemical Sciences at the University of Texas Rio Grande Valley.

“As scientists, we want our research to be accessible and applicable to anyone, and mowing is a concept the world at large can understand,” Vasquez said.

The initial study was published in 2021 with an article titled “Local adaptation to continuous mowing makes the noxious weed Solanum elaeagnifolium a superweed candidate by improving fitness and defense traits.” The lead author for that study was Jesus Chavana, with co-authors Sukhman Singh, Bradley Christopherson, Alexis Racelis, Vasquez and Kariyat, all with the University of Texas Rio Grande Valley at the time.

Research has shown that noise from airplanes and helicopters flying overhead are far more bothersome to people than noise from other modes of transportation, and a growing body of research suggests that aircraft noise is also contributing to negative health outcomes.

One of the latest studies, led by Boston University School of Public Health (BUSPH) and Oregon State University (OSU) indicates that airplane noise may increase one’s risk of developing cardiometabolic diseases, a cluster of conditions such as heart attack, stroke, diabetes, and hypertension.

Published in the journal Environment International, the study found that people who were exposed to airplane noise levels at 45 dB or more were more likely to have higher self-reported body mass index (BMI), with the highest BMI measures linked to aircraft noise levels at 55 dB or above. Airplane noise exposure at 45 dB or above was also associated with having higher BMI in middle to late adulthood from early adulthood. For comparison, the sound of a whisper is 30 dB, a library setting is 40 dB, and a typical conversation at home is 50 dB.

BMI is an indicator of general obesity, which can lead to cardiometabolic diseases, as well as a range of other health issues. The study is the first to explore a connection between aircraft noise exposure and obesity nationwide in the United States; past studies on this subject have focused on European populations, and results have varied.

“Prior research has shown that aircraft noise can elevate stress responses and disturb sleep, but there has been mixed evidence of any links with body mass index,” says study lead and corresponding author Dr. Matthew Bozigar, assistant professor of epidemiology at OSU. “We were surprised to see a fairly robust link between aircraft noise and higher body mass index among women across the US.”

These new findings underscore the role of the environment on one’s risk of chronic disease.

‘Obesity has become very stigmatized, but what is important to remember is that it is linked with poor cardiometabolic health outcomes, and that it has strong environmental drivers,” Dr. Bozigar says. “This is disheartening, but also promising, in the sense that we could potentially enact policies to mitigate these drivers of obesity.”

For the study, Dr. Bozigar and colleagues examined airplane noise exposure and self-reported BMI and other individual characteristics among nearly 75,000 participants living around 90 of the major US airports. The participants were selected from the Nurses’ Health Studies (NHS), ongoing, prospective studies of US female nurses who have completed biennial questionnaires since the 1970s and 1980s.

The team examined aircraft noise levels every five years from 1995 to 2010, using a day-night estimate (DNL) that captures the average noise level over a 24-hour period and applies a 10 dB adjustment for aircraft noise occurring at night, when background noise is low. The current policy-related threshold for significant noise impacts is above DNL 65 dB. The team assessed BMI measures at multiple thresholds below that (less than 45 dB; 45-54 dB; 55 dB and above; and continuous exposure at 45 dB or above) for the nurses’ geocoded residential addresses.

Although the team acknowledges that BMI is a suboptimal metric, the independent and strong association between more aircraft noise exposure and higher BMI that they observed is notable. There were also regional differences, with stronger associations among participants on the West Coast and those who live in arid conditions.

“We can only hypothesize about why we saw these regional variations, but one reason may relate to the era of regional development, building characteristics, and climate which may affect factors such as housing age, design, and level of insulation,” says study senior author Dr. Junenette Peters, associate professor of environmental health at BUSPH. “Regional differences in temperature and humidity may influence behaviors such as window opening, so perhaps study participants living in the West were more exposed to aircraft noise due to open windows or housing type, which allowed more noise to penetrate.”

Similarly, the stronger associations observed in arid climates, many of which are also in the Western US, may relate to the way noise travels under various atmospheric conditions, Dr. Peters says.

Future research should explore this link between aircraft noise exposure and obesity further, as well as broader inequities in environmental noise exposure, particularly among other populations. Previous data suggest that Black, Hispanic, and low-income populations are disproportionately exposed to aircraft noise. The participants in the NHS study groups were primarily White and of mid-level socioeconomic status.

“We need to study the potential health impacts of environmental injustices in transportation noise exposures alongside other environmental drivers of poor health outcomes” Dr. Bozigar says. “There is a lot more to figure out, but this study adds evidence to a growing body of literature that noise negatively impacts health.”