We present SolarFlux Predictor, a novel deep-learning model designed to revolutionize photovoltaic (PV) power forecasting in South Korea. This model uses a self-attention-based temporal convolutional network (TCN) to process and predict PV outputs with high precision. We perform meticulous data preprocessing to ensure accurate data normalization and outlier rectification, which are vital for reliable PV power data analysis. The TCN layers are crucial for capturing temporal patterns in PV energy data; we complement them with the teacher forcing technique during the training phase to significantly enhance the sequence prediction accuracy. By optimizing hyperparameters with Optuna, we further improve the model’s performance. Our model incorporates multi-head self-attention mechanisms to focus on the most impactful temporal features, thereby improving forecasting accuracy. In validations against datasets from nine regions in South Korea, SolarFlux outperformed conventional methods. The results indicate that SolarFlux is a robust tool for optimizing PV systems’ management and operational efficiency and can contribute to South Korea’s pursuit of sustainable energy solutions.

Lane-changing is one of the most fundamental driving behaviors, yet it is also one of the most hazardous maneuvers, as interactions with adjacent lanes critically impact vehicle safety. Accurate prediction of lane-change trajectories is essential for enhancing road safety and the effectiveness of autonomous driving systems. This study proposes a model that leverages traffic context from drone footage to predict lane-change trajectories, incorporating interactions between surrounding vehicles. The proposed model analyzes drone footage collected from natural urban driving environments using computer vision techniques to extract traffic context and employs a Transformer-LSTM architecture to predict lane-change trajectories. Beyond trajectory prediction, this study enhances model interpretability by analyzing the key factors influencing lane-change predictions. Critical moments in the prediction process can be visually identified using attention heatmaps, and the model’s focus on essential input information, such as the approach of nearby vehicles or significant interactions, can be observed. This approach offers meaningful insights into the model’s predictive focus. The feasibility of the proposed model was validated through the implementation of a prototype and its application to real traffic data, confirming its effectiveness in accurately predicting lane-change trajectories across diverse traffic scenarios.

Precise modeling of microscopic vehicle trajectories is critical for traffic behavior analysis and autonomous driving systems. We propose Ctx2TrajGen, a context-aware trajectory generation framework that synthesizes realistic urban driving behaviors using GAIL. Leveraging PPO and WGAN-GP, our model addresses nonlinear interdependencies and training instability inherent in microscopic settings. By explicitly conditioning on surrounding vehicles and road geometry, Ctx2TrajGen generates interaction-aware trajectories aligned with real-world context. Experiments on the drone-captured DRIFT dataset demonstrate superior performance over existing methods in terms of realism, behavioral diversity, and contextual fidelity, offering a robust solution to data scarcity and domain shift without simulation.

Autonomous driving in dense urban environments requires accurate trajectory forecasting supported by interpretable contextual evidence. This study presents a multimodal framework that performs driving scene context (DSC)-aware trajectory prediction while providing risk-aware explanations to reveal the contextual cues behind predicted motion. The framework integrates temporal object states—trajectories, velocities, yaw angles, and motion status—with semantic information from forward-facing camera imagery, and is composed of four modules: object behavioral feature extraction, scene context extraction, DSC-augmented trajectory prediction, and risk-aware reasoning using a multimodal large language model (MLLM). Experiments on the Rank2Tell dataset demonstrate the feasibility and applicability of the proposed approach, achieving an ADE of 10.972, an FDE of 13.701, and an RMSE of 8.782. Additional qualitative evaluation shows that DeepSeek-R1-Distill-Qwen-7B generates the most coherent and contextually aligned explanations among the tested models. These findings indicate that combining DSC-aware prediction with interpretable reasoning provides a practical and transparent solution for autonomous driving in complex urban environments.