Research Brief

My colleagues and I have developed an artificial intelligence system that helps buildings shift their energy use to times when the electric grid is cleaner. I’m an engineer who studies and develops smart buildings. My lab created Merlin, which learns how people use energy in their homes and adjust energy controls like thermostats to meet their needs while at the same time minimizing the impact on the grid. The system can learn on one set of buildings and occupants and be used in buildings with different controls and energy use patterns. We dubbed it Merlin after King Arthur’s legendary magician to reflect the magical nature of the system: It automatically collects data on how people use energy in their homes and identifies opportunities to charge and discharge home battery storage. And it does so in a way that you always have power for whatever you need. So your air conditioning is always available, but at the same time it reduces the strain on the grid – for...

Activities associated with cocaine trafficking threaten two-thirds of the most important landscapes in Central America for 196 forest bird species, including 67 migratory species. This is the key takeaway from a study that colleagues and I published in June 2024 in the journal Nature Sustainability. Our findings suggest that there is real potential for drug-related deforestation to negatively affect populations of migratory birds. Many of these species are unusually concentrated in winter in Central America, which has a comparatively smaller area than their summer breeding regions in North America. For 1 in 5 migratory species that travel to Central American forests annually, including familiar birds like the Baltimore oriole, more than 50% of their global population winters in areas that are becoming more attractive to traffickers. For half of migratory species, at least 25% of their populations winter in these areas. Baltimore orioles...

The most significant predictors of bug biodiversity in Los Angeles are proximity to the mountains and temperature stability throughout the year, according to a study we co-authored with Brian V. Brown of the Los Angeles Natural History Museum and colleagues at the University of Southern California and California State University. The project used data from the museum’s BioSCAN project, where volunteers across Los Angeles allowed insect traps to be installed on their property between 2014 and 2018. Arthropod species richness in Los Angeles. Black dots show locations where the BioSCAN project collected bugs between 2014-2018. The color scale shows the predicted number of species, with blue being the least rich and orange being the most rich. Map tiles by Stamen Design, CC BY-SA The analysis showed some surprising results. For instance, land values had little impact on the overall diversity of art...

Human-wildlife overlap is projected to increase across more than half of all lands around the globe by 2070. The main driver of these changes is human population growth. This is the central finding of our newly published study in the journal Science Advances. Our research suggests that as human population increases, humans and animals will share increasingly crowded landscapes. For example, as more people move into forests and agricultural regions, human-wildlife overlap will increase sharply. It also will increase in urban areas as people move to cities in search of jobs and opportunities. Animals are also moving, mainly in response to climate change, which is shifting their ranges. Across most areas, species richness – the number of unique species present – will decrease as animals follow their preferred climates. But because human population growth is increasing, there still will be more human-wildlife overlap across most lands. We also found areas where human-...

My colleagues and I mapped activity in the northeast Pacific of “dark” fishing vessels – boats that turn off their location devices or lose signal for technical reasons. In our new study, we found that highly mobile marine predators, such as sea lions, sharks and leatherback sea turtles, are significantly more threatened than previously thought because of large numbers of dark fishing vessels operating where these species live. While we couldn’t directly watch the activities of each of these dark vessels, new technological advances, including satellite data and machine learning, make it possible to estimate where they go when they are not broadcasting their locations. Examining five years of data from fishing vessel location devices and the habitats of 14 large marine species, including seabirds, sharks, turtles, sea lions and tunas, we found that our estimates of risk to these animals increased by nearly 25% when we accounted for the presence of dark v...