Using Artificial Intelligence to understand the diversity of leaf-cutting ants
- Beschreibung
Ants are some of the most abundant and diverse insects on Earth. There are over 14,000 ant species of which 260 grow their food like in human agriculture. These ants, known as the fungus-growing ants do not grow the same crops as humans, but rather a type of fungus. The most specialized group of fungus-growing ants are the leaf-cutting ants, which use freshly cut leaves to grow their fungi. Because of this herbivore behavior, leaf-cutting ants are a damaging crop pest in the Neotropics. However, identifying species of leaf-cutting ants is still challenging because they display an enormous diversity of morphological and biological features. Overall, this prevents us from understanding their biology and effectively controlling their crop damage.
Traditionally, scientists have identified leaf-cutting ant species by visually describing their physical traits. But what if we could use measurable, data-driven methods instead? Our project explores how morphometrics, which are quantitative measurements of body structures, can help distinguish between different ant species more accurately.
Since launching in the winter semester of 2024, and with the fantastic support of Humboldt reloaded participants, we’ve created a dataset of over 300 images of leaf-cutting ants. These images have already been analyzed for both linear and geometric morphometric traits.
Now, we are ready for the next step and we need your help! In the upcoming winter semester of 2025, we aim to automate our image analysis process and test whether artificial intelligence can detect the key morphological differences between species.
If you're curious about ants, interested in biodiversity, or excited by the idea of combining biology with AI and image analysis, this is a great opportunity to get hands-on experience in an innovative research project.
Key questions we’ll explore:
- Are there measurable shape differences between species of leaf-cutting ants?
- Can AI help us identify these ants more accurately?
- Projektzeitraum
- Wintersemester 2025/2026
- Bewerbungszeitraum
- 13. bis 27.10.2025
- Durchführung
- semesterbegleitend
- Details zu Projektzeitraum und Durchführung
The project will be conducted at the University of Hohenheim during the winter semester of 2025. The main activities will involve processing images of leaf-cutting ants and training artificial intelligence algorithms. No prior experience in AI or morphometrics is required, just curiosity, motivation, and a willingness to learn. Join us and be part of a unique research project at the intersection of biology and technology!
- Studienfach
-
Agrarbiologie
Agrarwissenschaften
Agricultural Sciences in the Tropics & Subtropics
Biologie
Crop Sciences - Betreuende
- Laura Daniela Mera-Rodriguez
- Institut
- Institut für Biologie (190) (Insect biodiversity)
- Sprache
- deutsch/englisch
- Teilnehmendenanzahl
- min. 1, max. 1
- Arbeitsaufwand
-
ca. 180 Stunden pro Teilnehmende:r
| 6
ECTS-Punkte
Arbeitsaufwand (Stunden und ggf. ECTS) sind ungefähre Angaben. Die tatsächlich vergebenen ECTS-Punkte ergeben sich aus der tatsächlich geleisteten Arbeit.
- Für dieses Projekt ist ein Motivationsschreiben des Studierenden erforderlich
- Projektart
- theoretisch/nicht experimentell
- Lernziele
-
Die Teilnehmende lernen in diesem Projekt:
Learning objectives:
-Gain research experience conducting taxonomic studies about insects
-Develop an independent research project about insect biodiversity
-Learn to use current methods for insect identification
-Understand the relevance of biological collections for biodiversity research
- Anmerkungen für Studierende
- Schlagworte
- Tiere, Biodiversität, artificial intelligen