Mattana, E. | Search bioRxiv

bioRxiv2025

Impacts of climate change on fonio millet: in-vitro seed germination and suitability modelling of an important indigenous West African crop

Seed germination is highly temperature sensitive. Climate change factors such as increasing temperatures are likely to have a harmful effect on agriculture, particularly after crop sowing. Better utilisation of indigenous, arid-resilient crops like fonio (Digitaria exilis) are a commonly proposed solution to improving food security. This study develops knowledge of fonio germination requirements and how these correspond to future climate conditions across West Africa. We use a combined approach; integrating seed germination experiments under a range of temperatures, and niche suitability modelling to investigate how cultivation of fonio will be impacted by climate change. We find that from 37 seed accessions collected across Guinea, Togo, Mali, and Burkina Faso, the ceiling temperature for germination is around 42{degrees}C, with an optimum temperature of 30-35{degrees}C - also noted from phenotypic observations. Drought trials show successful germination to beyond -1MPa. There is no obvious difference in response by accessions originating from either hotter or cooler climates. By comparing these temperature thresholds with future climate predictions, alongside a suitability modelling approach, we predict an average decline of 10% in the suitable area for fonio cultivation, especially affecting Senegal, Mali, and Burkina Faso. Newly suitable area is predicted to increase in Guinea, Ghana, Cote dIvoire, and Nigeria by around 5%. These findings provide valuable insight for developing future dryland agriculture policies and prioritisation of resilient crops.

plant biology↗

bioRxiv2025

Enhancing tree seed germination prediction with image-driven machine learning models.

1. Tree planting is crucial for reversing deforestation and meeting net zero targets, requiring a reliable supply of high-quality seeds. Efficient use of limited native seeds can be promoted by sorting methods, but traditional techniques commonly used for agricultural species are often unsuitable for tree seeds due to their high trait variability. 2. Here, we explored the potential of combining image analysis with machine learning models to improve tree seed sorting outcomes. We selected five UK native tree species of interest for tree production and afforestation projects and applied machine learning XGBoost and Convolutional Neural Networks algorithms to predict seed germination using colour and X-ray images as well as features extracted from these images. 3. The machine learning models achieved good accuracy and F1-scores, but their specificity was limited, particularly when relying solely on colour images or related features. This poses a problem, as wild seeds are often scarce, and falsely classifying seeds that germinate as non-germinable would result in a waste of valuable resources. X-ray images and features were highly effective in identifying empty seeds but did not perform well when differentiating filled seeds into germinable and non-viable. Consequently, the models performed best for species with a high proportion of empty seeds. 4. For three of the five species, model performance varied significantly by mother tree, with some trees showing markedly poorer results. This aspect had not been previously investigated and raises concerns that biased seed sorting will disadvantage certain mother trees, leading to the loss of valuable genetic diversity and woodland resilience. Synthesis and applications: The performance of image-based machine learning models in predicting seed germination ultimately depended on whether most non-germinated seeds were empty, non-viable, or dormant. X-ray models showed strong performance in detecting empty seeds, but colour image models exhibited poor results due to the high variability in seed external features, the subtle differences between germinated and non-germinated seeds, and the variability among individual mother trees. Developing open, accessible training databases and more adaptable models is crucial for addressing these limitations and enable technologies to further support large-scale tree production.

plant biology↗