The research team, led by scientists at the Northeast Institute of Geography and Agroecology of the Chinese Academy of Sciences in Changchun, together with senior author Zhibin Zhang of the School of Ecology at Hainan University, set out to answer a question that has long lingered in rangeland ecology. Small herbivores such as pikas, voles, prairie dogs, and pocket gophers are both consumers and ecosystem engineers in grasslands worldwide. Through feeding, clipping vegetation, and digging burrows, they profoundly alter plant communities and soil properties. But while population outbreaks clearly harm livestock interests, almost nothing was known about what happens when their numbers sit at lower, non-outbreak levels. Co-first author Zhiwei Zhong, Professor of Ecology at the Northeast Institute of Geography and Agroecology, framed the stakes in stark terms: livestock grazing currently occupies around 77 percent of global agricultural land and sustains billions of people, making a critical assessment of small mammals’ impacts on livestock production urgently needed for both production and biodiversity conservation.

The study focused on a specific ecological mechanism. The team hypothesised that at moderate densities — defined in the study as approximately 200 active burrows per hectare — pikas would benefit yaks by suppressing tall poisonous plants known as Stellera, a genus of forbs that thrives in degraded alpine grasslands and is toxic to livestock. If pikas cut back Stellera, the reasoning went, palatable grasses and sedges would gain space, light, and nutrients, raising both the abundance and the protein content of the forage available to yaks during the growing season from June to August.

To test this idea, the researchers combined observational and experimental approaches. First, they conducted two field surveys to establish how the diets of pikas and yaks differ, and to examine the associations among pika density, Stellera abundance, and yak grazing activity across the landscape. Then they moved to a manipulative field experiment, using fenced enclosures measuring 150 by 150 metres on the Qinghai–Tibetan Plateau, to isolate the interactive effects of pikas and Stellera on yak body growth and to uncover the mechanisms driving those effects. This two-pronged design allowed the team to move beyond correlation and demonstrate causation in a realistic grazing context.

The surveys revealed a striking dietary asymmetry. Pikas and yaks, despite sharing the same meadows, barely overlap in what they actually eat. Pikas very frequently clipped Stellera plants but did not eat them, feeding mostly on other forbs instead. Yaks, as expected, consumed far greater proportions of grasses and sedges. In other words, the supposed competition between the two herbivores was largely an illusion: the pikas were not eating the yak’s lunch, they were weeding the yak’s garden. By selectively clipping the tall poisonous forbs, pikas reduced Stellera cover by two-thirds, which in turn increased the availability and protein content of the grasses and sedges that yaks depend on.

The consequences for the yaks themselves were measurable and substantial. Co-first author Bingbo Ni, an environmental researcher at the Northeast Institute of Geography and Agroecology, explained that by improving the composition of the vegetation, the moderate presence of pikas facilitated weight gains in yaks. In livestock production, where body condition directly determines meat, milk, and economic returns, a natural mechanism that boosts weight gain without any human intervention carries obvious significance for herding communities across the plateau and beyond.

Perhaps even more compelling were the findings on foraging efficiency. The researchers tracked two behavioural metrics: bite rate, the number of bites taken on plants per hour, and the bites–step ratio, the number of bites per step taken while moving through the sward. During the manipulative experiment, when pikas were absent, the yaks’ sedge bite rate and sedge bites per step fell by 32 percent and 46 percent respectively, compared with conditions when pikas were present. Grass bite rate and grass bites per step similarly declined by 29 percent and 43 percent. The team attributed these drops directly to the resurgence of poisonous Stellera in the pikas’ absence, which forced yaks to spend more time and movement searching for acceptable forage among the toxic plants.

Zhong noted that the study is the first to show that maintaining a moderate density of pikas can substantially enhance livestock growth by suppressing Stellera, reconciling long-running debates about the effects of pikas on yak production through changes in vegetation properties. He added that the observations shed light on how small and large mammalian herbivores co-exist in complex ways. The findings carry a broader ecological message: interactions between animals of very different body sizes in shared ecosystems are rarely one-dimensional, and management policies built on the assumption of simple competition may destroy beneficial relationships that were never measured in the first place.

The authors are careful to delineate the limits of their conclusions, and those limits chart a research agenda. Their work examined pika–yak interactions only during the summer, when food resources are most abundant; whether the facilitation weakens or even flips into competition under more stressful conditions, such as autumn or winter when forage becomes limited, remains untested. The study site also sat at approximately 3,200 metres elevation, relatively low by Qinghai–Tibetan Plateau standards, so it is unknown whether similar facilitation occurs at higher elevations where other unpalatable species replace Stellera as the problematic plant. Finally, whether the same relationship holds between pikas and other livestock in the region, such as domestic sheep and goats, has yet to be determined.

Even with those caveats, the implications for rangeland management are far-reaching. Senior author Zhibin Zhang emphasised that because the conclusions rest on both experimental and observational evidence across realistic contexts, they are applicable beyond the Qinghai–Tibetan Plateau to rangeland management elsewhere, and the team hopes the insights will inform conversations and future studies concerning biodiversity and ecosystem functioning worldwide. For a species long targeted as a pest, the pika’s rehabilitation carries a cautionary lesson for land managers everywhere: culling programs aimed at small mammals may quietly remove an ecological service — natural weed suppression that fattens livestock — and the true costs of such interventions are only now coming into focus. In the alpine meadows of the world’s highest rangelands, the smallest grazers may be among the livestock industry’s most valuable, and least appreciated, partners.

Subject of Research: Facilitative interactions between plateau pikas and grazing yaks in alpine grassland ecosystems

Article Title: Plateau pikas, long considered pests, can help livestock eat well

Article References: Plateau pikas, long considered pests, can help livestock eat well. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: plateau pika, yak, Qinghai–Tibetan Plateau, rangeland management, Stellera, livestock grazing, ecosystem engineers, foraging efficiency, grassland ecology, small mammals, vegetation composition, eLife

The central obstacle the team faced was the sheer complexity of the honey bee’s sense of smell. Bees rely on more than 200 odor receptors to navigate their world, detecting and responding to a vast array of volatile compounds in their environment. That sensitivity is what makes bees such effective foragers, but it also makes their olfactory behavior extraordinarily difficult to predict. Finding a scent that reliably repels a bee, rather than attracting it or doing nothing at all, has long been considered a major challenge. Anandasankar Ray, a professor of molecular, cell and systems biology at UC Riverside and an expert on insect olfactory behavior, led the interdisciplinary effort to overcome it.

“Bees rely heavily on their sense of smell to forage, but that sensitivity makes it tough to find odors that push them away instead of drawing them in,” Ray said. “Our goal was to flip that script and find a way to use scent as a deterrent — safely and effectively.” To pursue that goal, Ray’s team collaborated with honey bee researchers in the laboratory of Boris Baer, a professor of entomology at UC Riverside, combining expertise in computational modeling with hands-on knowledge of bee behavior.

The approach the researchers developed was a machine-learning model trained on two kinds of information: the chemical structures of odorant molecules and previously recorded behavioral responses of bees to those odorants. By learning the relationship between molecular features and behavioral outcomes, the model could begin to predict how a bee would respond to a compound it had never encountered. Crucially, the team did not stop with the initial training data. They refined the model with new behavioral data generated in their own laboratory, gathered from both honey bees and Drosophila, the fruit fly that serves as a workhorse of insect olfaction research. That iterative improvement step allowed the system to make increasingly accurate predictions of insect olfactory responses.

One of the most striking aspects of the work is that it succeeded without the enormous datasets usually assumed to be necessary for machine learning. “It is generally thought you need abundant data to do any kind of machine learning, but that’s not true for olfaction,” Ray said. “You simply need good-quality data and iterative improvement steps.” That insight has implications well beyond bee research, suggesting that carefully curated behavioral measurements can substitute for sheer data volume when the underlying structure of the problem is learnable. Once the model was optimized, the researchers put it to work on a truly industrial scale, screening a library of more than 50 million compounds. From that vast chemical space, the system identified roughly 130 candidates predicted to have strong potential as bee repellents.

Predictions, of course, mean little until they are tested against living insects. The team reports in eLife how they put the top-performing candidates through exactly that gauntlet. In laboratory assays, honey bees exposed to the candidate compounds exhibited clear avoidance behaviors, and those responses aligned closely with what the model had predicted. That agreement between computation and behavior is the heart of the study’s significance: it demonstrates that a model trained on limited but high-quality data can generalize to new molecules and correctly forecast how bees will react to them in the real world.

The validation did not stop in the laboratory. The researchers then moved to field experiments with freely foraging bees, a far more demanding test because wild conditions introduce wind, competing odors, and the full complexity of natural foraging behavior. All seven of the compounds tested in the field reliably repelled bees from honey combs, and importantly, they did so without harming the insects. A repellent that injured the very pollinators it was meant to protect would defeat its own purpose, so the demonstration that these odorants deter bees safely is a critical part of the result.

“This is a powerful demonstration of how machine learning can help solve real-world ecological problems,” Ray said. “By keeping bees away from harmful pesticides, we can potentially reduce their risk of exposure without compromising the protection of crops.” The logic of the approach is straightforward: instead of banning or restricting every pesticide that poses a risk to bees — a regulatory path that has already removed some of the most harmful products from use — farmers could blend repellent compounds into their pesticide applications. The crop would retain its protection against pests, while bees, sensing the deterrent odor, would simply choose to forage elsewhere. Unintended exposure to pesticides is widely considered a contributing factor to bee population decline and colony collapse, and minimizing bee contact with treated crops addresses that exposure directly.

The researchers also point to applications that extend well beyond agricultural spraying. “In certain public environments — hospitals, office buildings, and residential areas, for example — reducing the formation of beehives can help avoid human-bee conflicts,” Ray said. In those settings, a safe repellent could discourage bees from establishing colonies where they are unwelcome, without resorting to lethal control. There are agricultural uses as well: some farming practices, particularly with seedless fruit varieties, aim to avoid pollination altogether, and a reliable repellent could help keep bees away from crops where pollination is undesirable rather than essential. According to Ray, the research is a step toward developing bee-friendly pesticide formulations — products that safeguard pollinators while still meeting the needs of modern agriculture.

“Protecting pollinators doesn’t have to come at the expense of food security,” Ray said. “With the right tools, we can strike a balance — and this model helps us get there. We believe our work will help guide further exploration of machine learning-guided solutions in environmental protection and sustainable farming practices.” Ray and Baer were joined in the research by Joel Kowalewski, Barbara Baer-Imhoof, Tom Guda, Matthew Luy, and Payton DePalma. The work was funded by a grant from the California Research Alliance by BASF. The research paper, titled “Machine learning of honey bee olfactory behavior identifies repellent odorants in free flying bees in the field,” was published in eLife on 23 September 2026, with the DOI 10.7554/eLife.104831.3. The authors note that Ray is founder and president of Sensorygen and Remote Epigenetics and holds equity in both companies, Kowalewski holds equity in Sensorygen, and several of the authors are inventors in a patent application covering the compounds discussed in the article. If the approach scales from honey combs to whole orchards, the humble trick of making treated flowers smell unappealing could become one of the more elegant tools in the effort to keep the world’s most important pollinators alive.

Subject of Research: Machine learning-guided discovery of odorant compounds that repel honey bees from pesticide-treated crops

Article Title: Machine learning helps identify chemicals that repel honey bees from pesticides

Article References: Machine learning helps identify chemicals that repel honey bees from pesticides. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: honey bees, machine learning, pollinator protection, pesticides, olfaction, repellents, eLife, UC Riverside, colony collapse, sustainable agriculture, chemical ecology, Drosophila