12.04.2024
Scientists from the Leibniz Centre for Agricultural Landscape Research (ZALF), together with two Chinese partner institutions, have published a paper in the journal Plants People Planet. The results show how artificial intelligence can be used to identify so-called traditional agricultural systems and preserve them to protect biodiversity. As a case study, the researchers use a widespread crop with a particularly long tradition in China: Chinese tea.
In the course of the ongoing modernization of agriculture worldwide, standardized seeds are increasingly being used in many places. Genetic diversity is being lost at an alarming rate. In agriculture, this has a negative impact on disease and pest resistance, adaptability to climate change and the stability and function of ecosystems, among other things. Traditional agricultural systems offer the possibility of preserving both genetic diversity and indigenous knowledge of cultivation, thereby preserving important cultural and social values that play an important role for a culture.
With the help of indicator evaluation models and machine learning, the researchers have now been able to narrow down areas in China that are particularly suitable for the preservation of traditional agricultural systems. Areas were identified that are characterized by a particularly high genetic diversity and other socio-economic factors, such as the presence of local knowledge and cultural systems. Conserving these systems not only protects biodiversity, but also the indigenous knowledge and cultures associated with them.
"The results of the research are a call to action to recognize traditional agricultural systems as an indispensable part of our cultural heritage and ecological future," explains Yunxiao Bai, lead author of the study. The methodology provides a model that can be applied globally to identify and protect other critically endangered agricultural systems. The map enables politicians to use resources specifically for the conservation of these systems.
To the publication:
https://doi.org/10.1002/ppp3.10479
The text was created with the help of artificial intelligence and carefully reviewed and revised under the aspects of AI regulations at ZALF. The text is used at the user's own risk.
