The scattering and absorption of light results in the degradation of image in sandstorm scenes, it is vulnerable to issues such as color casting, low contrast and lost details, resulting in poor visual quality. In such circumstances, traditional image restoration methods cannot fully restore images owing to the persistence of color casting problems and the poor estimation of scene transmission maps and atmospheric light. To effectively correct color casting and enhance visibility for such sand dust images, we proposed a sand dust image enhancement algorithm using the red and blue channels, which consists of two modules: the red channel-based correction function (RCC) and blue channel-based dust particle removal (BDPR), the RCC module is used to correct color casting errors, and the BDPR module removes sand dust particles. After the dust image is processed by these two modules, a clear and visible image can be produced. The experimental results were analyzed qualitatively and quantitatively, and the results show that this method can significantly improve the image quality under sandstorm weather and outperform the state-of-the-art restoration algorithms.

PM_2.5 poses a serious threat to human life and health, so the accurate prediction of PM_2.5 concentration is essential for controlling air pollution. However, previous studies lacked the generalization ability to predict high-dimensional PM_2.5 concentration time series. Therefore, a new model for predicting PM_2.5 concentration was proposed to address this in this paper. Firstly, the linear rectification function with leakage (LeakyRelu) was used to replace the activation function in the Temporal Convolutional Network (TCN) to better capture the dependence of feature data over long distances. Next, the residual structure, dilated rate, and feature-matching convolution position of the TCN were adjusted to improve the performance of the improved TCN (LR-TCN) and reduce the amount of computation. Finally, a new prediction model (GRU-LR-TCN) was established, which adaptively integrated the prediction of the fused Gated Recurrent Unit (GRU) and LR-TCN based on the inverse ratio of root mean square error (RMSE) weighting. The experimental results show that, for monitoring station #1001, LR-TCN increased the RMSE, mean absolute error (MAE), and determination coefficient (R²) by 12.9%, 11.3%, and 3.8%, respectively, compared with baselines. Compared with LR-TCN, GRU-LR-TCN improved the index symmetric mean absolute percentage error (SMAPE) by 7.1%. In addition, by comparing the estimation results with other models on other air quality datasets, all the indicators have advantages, and it is further demonstrated that the GRU-LR-TCN model exhibits superior generalization across various datasets, proving to be more efficient and applicable in predicting urban PM_2.5 concentration. This can contribute to enhancing air quality and safeguarding public health.

Adverse weather conditions can significantly hinder the performance of deep learning-based object detection models. Traditional approaches often rely on image restoration techniques to enhance the quality of degraded images prior to detection. However, these methods frequently struggle to balance image enhancement and detection tasks effectively, often overlooking latent information that could be beneficial for detection. To address these challenges, we propose a novel framework: Knowledge Distillation based on Diffusion Models (KDDM). This framework incorporates a Dehaze Network (DN), which employs large kernel convolution to remove weather-specific artifacts, thereby revealing more latent information. The DN, together with a text detector, forms an end-to-end scene text detection network, acting as the student network. Additionally, the nuanced internal representations of text-to-image diffusion models adeptly capture and integrate higher-order visual semantic concepts. Given the rich textual and visual content inherent in scene text, there is a fundamental connection to text-to-image diffusion models. As such, we utilize diffusion models as a teacher network to distill high-level visual semantic knowledge into the student network. Notably, we introduce an innovative distillation technique using a “Threshold_Mask”, which ensures that the student network focuses on text regions while minimizing interference from irrelevant background elements. Comprehensive experimental evaluations demonstrate that our KDDM framework significantly outperforms baseline models under foggy weather conditions, marking a substantial advancement in the field.