By Jamie Martin
According to the University of Hawaiʻi at Mānoa College of Tropical Agriculture and Human Resilience, research led by Dr. Pascal Aigbedion-Atalor is using machine learning to identify areas at risk from the coconut rhinoceros beetle and support early pest management efforts.
Advances in artificial intelligence are creating new opportunities for agriculture, including improved pest management and crop protection. Researchers are now applying machine learning technology to help predict the movement of invasive insects before they establish damaging populations.
A new research initiative aims to improve the ability of agricultural officials and growers to identify high-risk areas for pest infestations and respond before significant crop losses occur.
“Stopping invasive pests before they spread is one of the best ways to protect American agriculture,” said Dr. Kathy Munkvold, FFAR scientific program director for Cultivating Thriving Production Systems Priority Area. “This research gives farmers a head start against a devastating introduced pest, helping to protect crops, livelihoods and the future of Hawaii’s agriculture.”
“Stopping invasive pests before they spread is one of the best ways to protect American agriculture,” said Dr. Kathy Munkvold, FFAR scientific program director for Cultivating Thriving Production Systems Priority Area. “This research gives farmers a head start against a devastating introduced pest, helping to protect crops, livelihoods and the future of Hawaii’s agriculture.”
The project focuses on the coconut rhinoceros beetle, an invasive insect that has become a growing threat to agriculture and natural resources in Hawaii. The research is supported through a partnership between the Foundation for Food & Agriculture Research (FFAR) and the University of Hawaiʻi’s College of Tropical Agriculture and Human Resilience.
Supported by a $300,000 investment, the project is using machine learning systems to analyze environmental data and identify locations where the beetle is most likely to spread.
Machine learning uses computer programs that learn from large amounts of data and identify patterns that may be difficult for humans to recognize. In agriculture, these systems are increasingly being used to improve decision-making, reduce risk, and increase efficiency.
Researchers are studying environmental conditions linked to beetle survival and reproduction. By examining these factors, they can build predictive models and create maps that highlight areas that are most vulnerable to future infestations.
These maps are expected to play an important role in pest monitoring programs. Agricultural officials can use them to strategically place pheromone traps that attract the beetles and provide early warning of new infestations.
Early detection remains one of the most effective ways to manage invasive pests. Identifying populations before they become established gives farmers and pest managers more options for controlling outbreaks and minimizing economic damage.
The coconut rhinoceros beetle poses a serious threat because it damages palm trees and other plants by boring into them during feeding. The resulting injuries can reduce plant growth, decrease fruit production, and weaken overall plant health.
The insect also threatens industries connected to agriculture, landscaping, and tourism. Since its arrival in Hawaii more than a decade ago, the pest has expanded its range and continues to concern researchers and growers.
Beyond Hawaii, the project highlights the growing role of advanced technology in modern agriculture. Invasive species remain a major challenge across the United States, where pest-related losses are estimated at approximately $137 billion annually.
Researchers believe predictive technology can help improve preparedness, reduce monitoring costs, and strengthen long-term pest management efforts. Similar approaches may eventually be adapted for other invasive species affecting crops nationwide.
The project is particularly important for supporting food security. Hawaii relies heavily on imported food, and protecting local agricultural production is essential for maintaining a stable and resilient food system.
Estimates indicate the coconut rhinoceros beetle could cause between $500 million and $1 billion in economic damage over the next decade if its spread continues unchecked. By identifying risks early, researchers hope to reduce potential losses and help preserve farm productivity.
The initiative aligns with broader efforts to protect American agriculture from invasive species and emerging threats. As machine learning applications continue to evolve, they are becoming valuable tools for supporting faster, more informed agricultural decisions.
For growers facing increasing pest pressures, predictive technology may offer a practical way to stay ahead of emerging threats and protect crops before damage occurs.
Photo Credit: Foundation for Food & Agriculture Research
Categories: National