Amsterdam aims to “rigorously green” the city—implementing new green infrastructures, fostering climate-adaptive solutions, and seeking to bolster biodiversity. However, the city has little data showing how these interventions, air pollution, and climate change may affect biodiversity. So, how can we measure biodiversity in a city? And what constitutes urban biodiversity? One crucial measurement here is the health and abundance of insect species.
Insect biodiversity and abundance are in global decline, potentially leading to a crisis with profound ecological and economic consequences. Many of us have heard about the decline in the bee population, but it goes beyond that. Approximately 20% of all vertebrate species are at risk of extinction in the wild, while a recent NASA study found that 65% of insect populations could go extinct over the next century. The problem's urgency is enormous, yet we need to learn more about the role of cities in this crisis.
In new research published in Nature Scientific Reports, Towards real-time monitoring of insect species populations, MIT and AMS Institute researchers propose a novel AI-driven model and method to quantify insect population dynamics in real time, thereby exposing how climate change, urbanisation, and other environmental stressors may affect insect populations.
“Global biodiversity decline and urbanization are inextricably linked – cities should know how their actions affect biodiversity, especially with the increasing threat of climate change. Novel technologies can provide great solutions to monitor what works and what does not, but they must be open-source and available to all. With this paper, we call on the scientific community to come together to help cities develop and adopt these technologies – without paywalls”
Titus Venverloo
Lead, Senseable City Amsterdam
Measuring insects in real-time: how does that work?
Researchers working at the MIT Senseable City Amsterdam, a collaboration between MIT Senseable City Laboratory and AMS Institute, propose a computer vision model that works towards "multi-objective insect species identification" in real-time and on a large scale. It leverages an image data source with 16 million impressions and allows a quick and open-access method to develop visual AI models to monitor insect species across climatic regions. This model will first be deployed in Amsterdam, but eventually, the technology could be used to create data-driven insights for other cities seeking to safeguard or promote biodiversity.
The AI model used in the study focuses on insect species in the Western European region. This model, part of the B++ project, trained on 1.54 million web-scraped images, can classify 2,584 insect species and could be deployed on images collected from high-definition cameras in urban, suburban, agricultural, and natural areas. For scalability to other geographic regions, the researchers can present a code repository that uses an existing 16 million image dataset to train custom AI models for local insect species of interest.
“Insects are a proxy for biodiversity. So, when cities monitor insect abundance and diversity, they are also monitoring how healthy the environment is we – humans - share with other species”
Fabio Duarte, a principal researcher at MIT’s Senseable City Lab and a co-author of the new paper.
A model that overcomes existing barriers?
This is by no means the first project to automate data acquisition on insect species using AI. However, it goes a step further than other models out there. In a systematic literature review from 2023, the most significant number of species included in a visual AI model was 40, trained on a dataset containing 4,500 images. While the largest dataset in the review contained 88,670 images, it had only 16 insect species. Very few studies ventured beyond classifying a limited number of insect species and often have a clear objective that narrows their focus: pest control, for example.
Moreover, several technologies could help acquire better data—computer vision, acoustic sensors, radar, and molecular methods, for example—but these are often commercial products and expensive to develop. The researchers emphasize that open-source methods and tools are necessary to address this gap and allow the insect monitoring effort to reach regions with lower economic resources.
Do you want to make your city more biodiverse? Reach out to us!
