The transportation industry contributes significantly to climate change through carbon dioxide (\(\hbox {CO}_{2}\)) emissions, intensifying global warming and leading to more frequent and severe weather phenomena such as flooding, drought, heat waves, glacier melting, and rising sea levels. This study proposes a comprehensive approach for predicting \(\hbox {CO}_{2}\) emissions from vehicles using deep learning techniques enhanced by eXplainable Artificial Intelligence (XAI) methods. Utilizing a dataset from the Canadian government’s official open data portal, we explored the impact of various vehicle attributes on \(\hbox {CO}_{2}\) emissions. Our analysis reveals that not only do high-performance engines emit more pollutants, but fuel consumption under both city and highway conditions also contributes significantly to higher emissions. We identified skewed distributions in the number of vehicles produced by different manufacturers and trends in fuel consumption across fuel types. This study used deep learning techniques to construct a CO₂ emission prediction model, specifically a light multilayer perceptron (MLP) architecture called CarbonMLP. The proposed model was optimized by hyperparameter tuning and achieved excellent performance metrics, such as a high R-squared value of 0.9938 and a low Mean Squared Error (MSE) of 0.0002. This study employs XAI approaches, particularly SHapley Additive exPlanations (SHAP), to improve the model interpretation ability and provide information about the importance of features. The findings of this study show that the proposed methodology accurately predicts CO₂ emissions from vehicles. Additionally, the analysis suggests areas for further research, such as increasing the dataset, integrating additional pollutants, improving interpretability, and investigating real-world applications. Overall, this study contributes to the design of effective strategies for reducing vehicle CO₂ emissions and promoting environmental sustainability.

This study presents FireNet-CNN, an advanced deep-learning model particularly designed for forest fire detection, which significantly surpasses existing methods in terms of reliability, efficiency, and interpretability. FireNet-CNN is compared to popular pre-trained models, including VGG16, VGG19, and Inception V3, across key performance metrics and consistently shows superior results, achieving 99.05% accuracy, 99.41% precision, and 98.28% recall. The model was evaluated using two augmented datasets: Dataset A and Dataset B, which consist of fire and non-fire images sourced from multiple video and image datasets. FireNet-CNN’s architecture, which includes 2.75 million parameters and a compact model size of 10.58 MB, has been meticulously optimized for fire detection tasks. As a consequence, the inference time of 0.95 seconds/image enables fast real-time deployment especially suitable for resource-constrained platforms like drones, remote sensors or other types of embedded systems in wooded regions. FireNet-CNN uses synthetic data augmentation based on Stable Diffusion to overcome the limitations of dataset size and class imbalance. This augmentation is critical as it helps the model accurately identify fire instances with a lower false positive rate, which is key for any real-time fire detection system where reliability and dependability are vital. To improve transparency and trust in safety-critical applications, FireNet-CNN incorporates the explainable AI (XAI) techniques, such as Grad-CAM and Saliency Maps. Despite encountering challenges such as reliance on synthetic data and issues of class imbalance, FireNet-CNN has demonstrated promising potential as a viable and effective solution for early wildfire detection. It offers significant insights for future research and practical applications in fire management and disaster response.

Breast cancer is one of the world's significant health challenges. There is a need to have better techniques in the early diagnosis of this disease to increase patients' survival rates. This paper introduces a robust approach for breast cancer detection by integrating deep-learning and classical machine-learning techniques into a custom lightweight neural network model. This approach is based on integrating conventional machine-learning and deep-learning paradigms using a range of data pre-processing steps, including data cleaning, label converting, scaling, and feature selecting to improve the given dataset's readiness for training. The proposed model demonstrated impressive accuracy in breast cancer detection compared to individual classifiers by achieving an overall accuracy of 97.54 %. Additionally, integrating eXplainable Artificial Intelligence (XAI) techniques gives the application interpretability and transparency for clinicians to make sense of the feature's importance and individual prognosis. It is a more accurate and easy-to-understand tool for clinicians, making it a better use of faulty or confusing reference values. This study presents the need to learn more about making deep learning and eXplainable Artificial Intelligence (XAI) complementary approaches to breast cancer diagnosis and treatment research.

Blood cell identification is a critical task in medical diagnosis, particularly for detecting and monitoring various hematological conditions. Automation of blood cell detection offers a solution to these challenges. This study presents a comprehensive study on the application of deep learning for automated blood cell identification, specifically, the Inception V3 model, showcasing its potential to revolutionize diagnostic accuracy in medical imaging. By employing advanced pre-processing techniques, and optimal model design, the InceptionV3 model achieved impressive results with 98.8% test accuracy on a dataset of high-quality microscopic blood cell images. To enhance decision-making transparency, the study employs Explainable AI (XAI) approaches such as Grad-CAM and Grad-CAM++ to produce heatmaps that highlight significant regions influencing the model’s identification. The study incorporated a comparative investigation with other deep-learning models, including VGG16, VGG19, and RESNET50. The efficacy of blood cell identification is demonstrated by evaluation measures like precision, recall, F1 score, Jaccard similarity, MCC score, and overall accuracy. The combination of strong performance and transparency through XAI techniques makes it a valuable tool for precise and dependable diagnoses. The potential of integrating advanced deep learning and XAI methods to improve the reliability and clinical adoption of automated blood cell identification systems is highlighted in this study.