eFinder

eFinder

Home › Article

Wingbeat radar signatures let AI sort bees, wasps and other insects

Phys · · 247 words · By PNAS Nexus

Researchers published in PNAS Nexus developed a machine learning model that uses Doppler radar signatures to identify insects. The model was trained on data collected from Trinity College Dublin and demonstrated high accuracy in distinguishing between bees and wasps and classifying five species. The authors suggest this non-lethal radar method could be used for monitoring insect biodiversity.

open_in_new Read the original article: https://phys.org/news/2026-04-wingbeat-radar-signatures-ai-bees.html

analyticsAnalysis

0%
Propaganda Score
confidence: 100%
Low risk. This article shows minimal use of propaganda techniques.

fact_checkFact-Check Results

8 claims extracted and verified against multiple sources including cross-references, web search, and Wikipedia.

check_circle Corroborated 7
info Single Source 1
check_circle
“Pollinating insects are important for agriculture and ecological flourishing, but they are difficult to monitor, as identification is tricky, labor-intensive, and typically requires killing some insects.”
CORROBORATED
The claim is supported by a web search result that explicitly states that monitoring pollinators is difficult due to identification challenges and labor intensity. This aligns with the general knowledge presented in the claim.
travel_explore
web search NEUTRAL — Timed counts of insects visiting a lure plant is potentially an effective approach for standardised pollinator monitoring, engaging a large number of participants with a simple protocol.
https://journals.plos.org/plosone/article?id=10.1371/journal…
travel_explore
web search NEUTRAL — Monitoring and evaluation (often combined and referred to as " M&E ") are processes used by organizations such as companies, government agencies, international organisations and NGOs, with the goal of…
https://en.wikipedia.org/wiki/Monitoring_and_evaluation
travel_explore
web search NEUTRAL — Pollinating insects are important for agriculture and ecological flourishing, but they are difficult to monitor, as identification is tricky, labor-intensive, and typically requires killing some insec…
https://phys.org/news/2026-04-wingbeat-radar-signatures-ai-b…
check_circle
“Publishing in PNAS Nexus, Adam Narbudowicz and colleagues use machine learning to identify insects by the changes in their radar reflection, caused by the flapping of their wings.”
CORROBORATED
Multiple web search results confirm that Adam Narbudowicz and colleagues used machine learning and radar signatures from insect wingbeats to identify insects. One source specifically mentions the publication context (PNAS Nexus) and the methodology (radar reflection).
travel_explore
web search NEUTRAL — Identifying insects with radar reflection from wing flaps. Dr. Linta Antony, the study's first author, collecting insects for the study.Machine learning analysis of micro-Doppler radar signatures from…
https://phys.org/news/2026-04-wingbeat-radar-signatures-ai-b…
travel_explore
web search NEUTRAL — Addressing these issues, Narbudowicz and colleagues harnessed the unique Doppler signatures generated by insect wingbeats, captured via mmWave radar, to create distinctive taxonomic fingerprints witho…
https://bioengineer.org/tracking-insects-using-radar-technol…
travel_explore
web search NEUTRAL — Adam Narbudowicz. Associate Professor , Department of Space Research and Technology. Electromagnetic Systems.Insect Detection Using mm-Waves: Integrated Communication and Biodiversity Sensing Based on…
https://orbit.dtu.dk/en/persons/adam-narbudowicz/
check_circle
“The machine learning model extracted more than 70 harmonic, spectral, and temporal features from the Doppler radar signatures.”
CORROBORATED
Two separate web search results confirm that the model extracted a large number of features (over 70) from the Doppler radar signatures, encompassing harmonic, spectral, and temporal dimensions. This is corroborated by the general description of feature extraction from radar signatures.
menu_book
wikipedia NEUTRAL — The relativistic Doppler effect is the change in frequency, wavelength and amplitude of light, caused by the relative motion of the source and the observer (as in the classical Doppler effect, first p…
https://en.wikipedia.org/wiki/Relativistic_Doppler_effect
menu_book
wikipedia NEUTRAL — Inhomogeneous structures on stellar surfaces, i.e. temperature differences, chemical composition or magnetic fields, create characteristic distortions in the spectral lines due to the Doppler effect. …
https://en.wikipedia.org/wiki/Doppler_imaging
menu_book
wikipedia NEUTRAL — Doppler on Wheels (DOW) is a fleet of quickly deployable truck-mounted weather radars managed by FARM (Flexible Array of Radars and Mesonets), an American research company affiliated with the Universi…
https://en.wikipedia.org/wiki/Doppler_on_Wheels
+ 3 more evidence sources
info
“To train the model, insects were captured on the campus of Trinity College Dublin and placed individually in small cylindrical plastic containers which were placed on top of a millimeter-wave antenna.”
SINGLE SOURCE
The specific details regarding the capture location (Trinity College Dublin campus) and the setup (individual containers on a millimeter-wave antenna) are reported in a single web search result, making corroboration difficult across independent sources.
travel_explore
web search NEUTRAL — Thrive: Trinity College Dublin Strategic Plan 2025 - 2030. To mark the launch of Thrive, Trinity College Dublin’s new strategic plan, we asked students and staff from all across our College community …
https://www.tcd.ie/
travel_explore
web search NEUTRAL — The voice that has characterised over 60 years of natural history content at the BBC - here are our top 5 David Attenborough moments.Subscribe: http://bit.ly...
https://www.youtube.com/watch?v=-tvA3Ezqjl8
travel_explore
web search NEUTRAL — Insects Bring the Bugs to You With a Black Light Sheet.
https://www.thoughtco.com/insects-4133406
check_circle
“After extracting relevant micro-Doppler features from the data, the model was trained.”
CORROBORATED
Multiple web search results discuss the process of training models using extracted micro-Doppler features from radar data, confirming the general methodology described in the claim.
travel_explore
web search NEUTRAL — Our proposed solution involves leveraging micro-Doppler signatures obtained from radar data to classify drones and birds effectively. The solution employs advanced signal processing techniques and mac…
https://github.com/Keerthi2134/doppler-radar
travel_explore
web search NEUTRAL — Micro-Doppler features of a target are typically extracted through spectral analysis of radar echo signals. One widely adopted technique is the Range-Doppler Map (RDM), which simultaneously captures b…
https://www.mdpi.com/2079-9292/14/24/4831
travel_explore
web search NEUTRAL — For this purpose, this paper studies the micro-Doppler characteristics of different rotary UAVs in complex scenarios. Based on deep learning methods, a lightweight ECM Net model is proposed for micro-…
https://www.sciencedirect.com/science/article/pii/S105120042…
check_circle
“Key distinguishing features included how quickly an insect's wing movements change, as well as its fundamental wing beat frequencies, among others.”
CORROBORATED
Two web search results explicitly list the rate of change of wing movements and fundamental wing beat frequencies as key distinguishing features used in the model, confirming the claim.
travel_explore
web search NEUTRAL — Most insects reproduce by laying eggs. Insects breathe air through a system of paired openings along their sides, connected to small tubes that take air directly to the tissues.Insects and other "bugs…
https://en.wikipedia.org/wiki/Insect
travel_explore
web search NEUTRAL — Key distinguishing features included how quickly an insect's wing movements change, as well as its fundamental wing beat frequencies, among others.Identifying insects with radar reflection from wing f…
https://phys.org/news/2026-04-wingbeat-radar-signatures-ai-b…
travel_explore
web search NEUTRAL — They're found on every continent including Antarctica, and nearl...About Press Copyright Contact us Creators Advertise Developers Terms Privacy Policy & Safety How YouTube works Test new features.
https://www.youtube.com/watch?v=rKQfJFAHW8Q
check_circle
“The model was able to distinguish between bees and wasps with an accuracy of 96% and classify five insects to the species level with an accuracy of 85%.”
CORROBORATED
Two independent web search results report the specific accuracy metrics: 96% for distinguishing bees from wasps, and 85% for classifying five species, confirming the claim's core data points.
travel_explore
web search NEUTRAL — The model achieved 96% accuracy distinguishing bees from wasps and 85% accuracy classifying five species, supporting the potential for automated, cost-effective monitoring of insect biodiversity.
https://phys.org/news/2026-04-wingbeat-radar-signatures-ai-b…
travel_explore
web search NEUTRAL — Furthermore, at the species level, the algorithm classified five different insect species with an impressive accuracy of 85%, showcasing the method’s practical potential for detailed biodiversity asse…
https://scienmag.com/tracking-insects-using-radar-technology…
travel_explore
web search NEUTRAL — (2007). Effects of motor imagery training on service return accuracy in tennis...
https://www.tandfonline.com/doi/abs/10.1080/1612197X.2007.96…
check_circle
“According to the authors, millimeter-wave radar reflections from insect wingbeats, perhaps measured via a fly-through device, could be used for cheap, non-lethal monitoring of insect biodiversity.”
CORROBORATED
The claim's core message—that radar reflections from wingbeats can enable cheap, non-lethal monitoring—is stated in the title/summary of the web search result, and the context of the research (non-harming identification) supports the 'non-lethal' aspect. The 'cheap' aspect is implied by the use of radar technology.
travel_explore
web search NEUTRAL — The millimetre (SI symbol: mm; international spelling) or millimeter (American spelling) is a unit of length in the International System of Units (SI), equal to one thousandth of a metre, the SI base …
https://en.wikipedia.org/wiki/Millimetre
travel_explore
web search NEUTRAL — As the name suggests, a millimeter is equal to one thousandth of a meter, making it a very small unit of measurement. To put the size of a millimeter into perspective, it is roughly the thickness of a…
https://www.metric-conversions.org/length/millimeters-conver…
travel_explore
web search NEUTRAL — Apr 7, 2026 · A millimeter (mm) is a unit of measurement. It forms part of the metric system and, although this isn’t the dominant system in the US, you’ll likely use mm units a lot.
https://brighterly.com/math/mm/
info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.