Application of artificial neural networks to classify Avena fatua and Avena sterilis based on seed traits: insights from European Avena populations primarily from the Balkan Region.

BACKGROUND: Avena fatua and A. sterilis are challenging to distinguish due to their strong similarities. However, Artificial Neural Networks (ANN) can effectively extract patterns and identify these species. We measured seed traits of Avena species from 122 locations across the Balkans and from some populations from southern, western, and central Europe (total over 22 000 seeds). The inputs for the ANN model included seed mass, size, color, hairiness, and placement of the awn attachment on the lemma. RESULTS: The ANN model achieved high classification accuracy for A. fatua and A. sterilis (R2 > 0.99, RASE < 0.0003) with no misclassification. Incorporating geographic coordinates as inputs also resulted in successful classification (R2 > 0.99, RASE < 0.000001) with no misclassification. This highlights the significant influence of geographic coordinates on the occurrence of Avena species. The models revealed hidden relationships between morphological traits that are not easily detectable through traditional statistical methods. For example, seed color can be partially predicted by other seed traits combined with geographic coordinates. When comparing the two species, A. fatua predominantly had the lemma attachment point in the upper half, while A. sterilis had it in the lower half. A. sterilis exhibited slightly longer seeds and hairs than A. fatua, while seed hairiness and mass were similar in both species. A. fatua populations primarily had brown, light brown, and black colors, while A. sterilis populations had black, brown, and yellow colors. CONCLUSIONS: Distinguishing A. fatua from A. sterilis based solely on individual characteristics is challenging due to their shared traits and considerable variability of traits within each species. However, it is possible to classify these species by combining multiple seed traits. This approach also has significant potential for exploring relationships among different traits that are typically difficult to assess using conventional methods.

Non-destructive estimation of weed response to bleaching herbicides by Raman spectroscopy.

The aim of our study was to evaluate the use of Raman spectroscopy for pre-diagnostic estimation of weed response to bleaching herbicides. Model plants were Chenopodium album and Abutilon theophrasti treated with mesotrione (120 g a.i. ha-1). Raman single-point measurements were taken 1, 2, 3, and 7 days after herbicide application from different points on the leaves. Principal component analysis (PCA) was carried out on data normalized by the highest intensity band at 1522 cm-1 and using spectral region from 950 to 1650 cm-1 comprising mainly contributions of carotenoids. The carotenoids by intensive band at ∼1522 cm-1 and bands with lower intensity at ∼1155 and 1007 cm-1 in treated plants were confirmed. According to PC1 (the first principal component) and PC2 (the second principal component), the highest intensity bands responsible for treatment differentiation in C. album could be assigned to chlorophyll, lignin, and carotenes. According to PC1 in A. theophrasti leaves the treatment differences could be observed 7 days after mesotrione treatment and PC2 gave a clear separation between all control and treated leaf samples. Raman spectroscopy may be a good complement to invasive analytical methods, in assessing the plant abiotic stress induced by bleaching herbicides.