Fig. 4 | Scientific Reports

Fig. 4

From: Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation

Fig. 4

t-SNE projections of input features and SHAP values. (a) Input feature-based t-SNE shows overlap between high-Q10 (orange) and low-Q10 (blue) soils. (b) SHAP value-based t-SNE reveals improved separation between high and low Q10 soils. The Euclidean distance between the centroids of high and low \(\hbox {Q}_{10}\) soils in the input feature space was 5.22, whereas in the SHAP-based t-SNE embeddings, it increased to 20.59, highlighting improved class separability.

Back to article page