Blog icon

By Fiona Brown 5 July 2023 4 min read

Key points

  • Thousands of new cars are sitting in Australian ports due to a backlog in cars needing to be cleaned and checked for biosecurity risk materials.
  • These biosecurity processes are hugely important as they keep out unwanted pests and diseases that could decimate our agricultural industries.
  • We’re working on a new initiative to drive innovation across Australia’s biosecurity system, including an app that can tell Brown Marmorated Stink Bug apart from harmless native stink bugs.

Bought a new car recently and want to enjoy that new car smell? Unfortunately, you’ve probably been told that delivery is going to take longer than usual. We know that stinks. But not as much as a Brown Marmorated Stink Bug (BMSB) outbreak would!

How stink bugs (and other biosecurity risks) are causing delays

Over the past few months, thousands of new cars have been sitting on ships waiting to be offloaded at ports around Australia. The delay has been caused by a backlog in vehicles waiting to be thoroughly cleaned and checked for biosecurity risk materials. These materials include any pests, weeds or diseases that could harm our economy, environment or community if they got into Australia. In the case of cars, likely suspects are soil, plant debris, seeds and live insects, such as the potentially devastating BMSB.

According to our friends at the Department of Agriculture, Fisheries and Forestry (DAFF), since 2021, Australia’s ports have seen an 88 per cent increase in new vehicles arriving with biosecurity risk material contamination.

Over the same period, there has been a 17 per cent increase in the total number of new vehicle imports into Australia.

These factors have combined to create one great big cleaning job for the commercial companies employed by car manufacturers to ensure your new car doesn’t come with any ‘hidden extras’!

Insects and weeds and seeds – oh my!

Why the massive increase in risky materials, you ask? Great question!

Seasonality is responsible for some increases. For example, BMSB are more likely to hide out in vehicles at certain times of the year.

However, the likely culprit is COVID. During the pandemic, many vehicles were stored overseas in paddocks waiting to be shipped. This exposed them to higher levels of plant debris and insects prior to export, resulting in a bigger cleaning job once they finally arrived in Australia.

What’s all the fuss?

How much damage could one tiny bug do, you ask? Another great question! (Have you considered a job as a researcher? We’re looking for people like you!)

The answer is a lot! BMSB can breed huge populations that become both a household nuisance, as well as a major problem for crop growers.

If BMSB established in Australia, it would be extremely difficult and expensive to manage. Unlike our native stink bugs, it has no specialised natural enemies here to keep its population in check. The Samurai wasp, Trissolcus mitsukurii, is a potential biocontrol agent that has been found here previously, however it hasn’t been spotted recently. BMSB isn’t easily controlled with pesticides either and feeds on more than 300 types of plant, so could spread rapidly.

We’re on the stinky case

We’re working with DAFF and partners from across the system to transform Australia’s biosecurity system and ensure it continues to protect our industries, environment, and communities from the growing threats of pests, weeds and diseases.

The developing initiative is called Catalysing Australia’s Biosecurity and that’s what we’re planning to do – work with our partners to catalyse innovation and ensure our biosecurity system remains world-leading.

It’s early days yet, but an example of the type of project we’ll be undertaking is an app designed to help the biosecurity officers tasked with the tricky job of correctly identifying a BMSB.

[Image appears of a black screen with text: Development of the BMSB AI app, Funded through the Biosecurity Innovation Programme, Department of Agriculture, Water and the Environment]

[Image changes to show a close view of five stink bugs in a small box, and text appears at the centre: Developing a BMSB App]

Dr Michael Elias: So, stink bugs are quite a diverse group in Australia.

[Image changes to show Dr Michael Elias pulling a drawer of bugs out of a cabinet and then the camera zooms in on the drawer of bugs]

There are about 600 different native species in Australia, and potentially thousands of species we haven’t discovered yet.

[Image changes to show Michael placing the tray onto a table, and then the camera zooms in on the bugs in the tray]

Generally speaking, they’re quite specialist so they’ll only eat one or two species of plants, and because they’ve evolved here they will only eat native species.

[Image changes to show Michael’s hand as he points to various bugs in the tray, and then the camera zooms in on some of the bugs]

There are a few which are more generalist and they tend to be the bigger pests.

[Image changes to show Michael talking to the camera, and text appears: Dr Michael Elias, Australian National Insect Collection]

But the biggest pests are the ones which come from overseas because they’re adapted to eat crops. Most of our crops come from somewhere else so they’re adapted to eat those crops and they have no natural predators.

[Image changes to show a very close view of the brown marmorated stink bug]

Brown marmorated stink bug is originally from east Asia, especially China, especially the wetter regions of China.

[Image changes to show Michael talking to the camera, and then the image changes to show an aerial view looking down on vineyards]

Because it’s such a generalist species it targets a very wide variety of crops, especially stone fruit, apples, pears, tree nuts – especially hazelnuts, it’s a big, big pest on hazelnuts – and wine grapes and there’s several other smaller crops as well.

[Image changes to show a person working in a vineyard, and then the image changes to show an aerial view looking down on a cargo ship, and the camera zooms out a little]

The way they deal with most pests when they find them at the border is they go out and they collect them.

[Camera pans over the cargo ship, and then the image changes to show a shipping container held on a crane]

Because they’re not trained entomologists they send them back to an entomology lab. In the meantime that cargo has to be held in quarantine at the expense of the importer.

[Image changes to show Michael talking to the camera]

If the biosecurity officers had a tool which they could use to identify on the spot, you wouldn’t need to spend that much time, which is a lot of money for the various importers.

[Image changes to show Dr Alexander Schmidt-Lebuhn sitting at a table looking at a stink bug in a box and talking to the camera, and text appears: Dr Alexander Schmidt-Lebuhn, CSIRO Scientist, Centre for Australian National Biodiversity Research]

Dr Alexander Schmidt-Lebuhn: This is the brown marmorated stink bug which is a major biosecurity threat for Australia. It’s a very generalist sap sucking insect that might cause immense damage to horticulture and agriculture if it establishes in Australia.

[Images move through to show a close view of trays of stink bugs, charts showing pictures of stink bugs, and then the camera zooms in on the trays of stink bugs again]

There are about 600 known Australian native species of stink bugs but there may be thousands of undescribed species too.

[Image changes to show Alexander talking to the camera]

The critical thing about invasive species is that they don’t have any natural enemies here so they may be able to do a lot more damage than the native ones that are actually controlled.

[Images move through to show camera equipment, and then the camera zooms in on the camera photographing a stink bug]

The present project is funded by the Department of Agriculture, Water and the Environment, through a biosecurity invasion programme.

[Images move through to show a photo of the stink bug on a computer screen, a researcher working on the computer looking at the stink bug photo, and then the camera equipment again]

We are creating an image recognition model that will allow inspectors and biosecurity officers to distinguish the brown marmorated stink bug and other potential pest species from closely related and similar native species.

[Images move through to show the camera equipment photographing the stink bug, a researcher working on the computer, and then a stink bug shown on a Smartphone screen]

That will allow them to make decisions about cleaning cargo, for example, about eradication actions, and will ultimately safeguard Australian, the Australian economy and agriculture.

[Camera zooms in on the Smartphone screen app showing the stink bug]

We have produced this AI model but to really make it useable to people we are putting it into a Smartphone app that the Department of Agriculture can then use at the border at ports to identify specimens in the future.

[Image changes to show Alexander talking to the camera]

I myself am an optimist, and actually the first model that we produced, and that we put into this prototype app here was a wheat seed identification model because I’d come out of the wheat seed identification project for the Department. And when we showed this to our partners at the Department of Agriculture, Water and Environment it turned out that yes the principle of this identification app was great but the actual really concrete problem at the moment were the stink bugs so that is where we then turned our attention next.

[Image continues to show Alexander talking to the camera and a female can be seen in the background working on the computer with the stink bug photo on the screen]

But ultimately an app like this can have all manner of identification models in it. We could have one in the future for moths, we could have one for wheat seeds again, we could have one for rust fungi, potentially anything that lends itself to being visually recognised by the expert can also then be visually recognised by the artificial intelligence.

[Image changes to show a black screen and credits and  appear at the bottom, and the Coat of Arms and text appears above: Australian Government, Department of Agriculture, Water and the Environment]

We are working with biosecurity officers at the Department of Agriculture, Fisheries and Forestry (formerly Department of Agriculture, Water and Environment) to develop an app to help correctly identify BMSB.

Share & embed this video



Embed code

<iframe src="//" width="640" height="360" frameborder="0" allow="autoplay; fullscreen" allowfullscreen></iframe>


There’s an app for that

A Brown Marmorated Stink Bug specimen.

The BMSB looks similar to many other stink bug species, making it difficult to recognise. And there are a lot of other stink bug species!

Australia has about 600 named native stink bug species as well as several thousand more undescribed species – none of which pose a biosecurity risk. On top of this, biosecurity inspectors may only have part of an insect to work with making correct identification even harder.

Correctly identifying whether a specimen is or isn’t a BMSB is really important. An incorrect identification could lead to a BMSB entering Australia with devastating impacts. Conversely, a false positive could result in an expensive and time-consuming biosecurity response to a harmless native stick bug.

To help ensure correct identification, our botanist Dr Alexander Schmidt-Lebuhn used artificial intelligence (AI) to build a prototype of an easy-to-use stink bug identification app.

"We took detailed digital images of the thousands of specimens of expertly identified species of Australian and exotic stink bugs we have in our Australian National Insect Collection," Alexander said.

"We then trained AI models to recognise BMSB and tell it apart from similar looking species, especially native ones that are commonly found by biosecurity officers."

The resultant prototype app is now being further developed by DAFF, with biosecurity officers currently trialling it at ports and airports around Australia.

"We’re now working on a new AI model that can identify priority weed seeds, which can be equally difficult to correctly identify," Alexander said.

Through projects like this, we’re working to deliver practical science and technology innovations that will ensure Australia’s biosecurity system is ready to meet future challenges.

Contact us

Find out how we can help you and your business. Get in touch using the form below and our experts will get in contact soon!

CSIRO will handle your personal information in accordance with the Privacy Act 1988 (Cth) and our Privacy Policy.

First name must be filled in

Surname must be filled in

I am representing *

Please choose an option

Please provide a subject for the enquriy

0 / 100

We'll need to know what you want to contact us about so we can give you an answer

0 / 1900

You shouldn't be able to see this field. Please try again and leave the field blank.