Using a newly developed model approach and combining it with remote sensing, population, and climate data, first insights are provided into how local diets, urbanisation, and climate change relates to local urban food self-sufficiency. In plain terms, by utilizing the global peri-urban (PU) food production potential approximately 1bn urban residents (30% of global urban population) can be locally nourished, whereby further urbanisation is by far the largest pressure factor on PU agriculture, followed by a change of diets, and climate change. A simple global food transport model which optimizes transport and neglects differences in local emission intensities indicates that CO₂ emissions related to food transport can be reduced by a factor of 10.

We aimed to assess the effects of hyperparameter tuning and automatic image augmentation for deep learning-based classification of orthodontic photographs along the Angle classes. Our dataset consisted of 605 images of Angle class I, 1038 images of class II, and 408 images of class III. We trained ResNet architectures for classification of different combinations of learning rate and batch size. For the best combination, we compared the performance of models trained with and without automatic augmentation using 10-fold cross-validation. We used GradCAM to increase explainability, which can provide heat maps containing the salient areas relevant for the classification. The best combination of hyperparameters yielded a model with an accuracy of 0.63–0.64, F1-score 0.61–0.62, sensitivity 0.59–0.65, and specificity 0.80–0.81. For all metrics, it was apparent that there was an ideal corridor of batch size and learning rate combinations; smaller learning rates were associated with higher classification performance. Overall, the performance was highest for learning rates of around 1–3 × 10⁻⁶ and a batch size of eight, respectively. Additional automatic augmentation improved all metrics by 5–10% for all metrics. Misclassifications were most common between Angle classes I and II. GradCAM showed that the models employed features relevant for human classification, too. The choice of hyperparameters drastically affected the performance of deep learning models in orthodontics, and automatic image augmentation resulted in further improvements. Our models managed to classify the dental sagittal occlusion along Angle classes based on digital intraoral photos.