Although many machine learning methods have been widely used to predict PM2.5 concentrations, these single or hybrid methods still have some shortcomings. This study integrated the advantages of convolutional neural network (CNN) feature extraction and the regression ability of random forest (RF) to propose a novel CNN-RF ensemble framework for PM2.5 concentration modeling. The observational data from 13 monitoring stations in Kaohsiung in 2021 were selected for model training and testing. First, CNN was implemented to extract key meteorological and pollution data. Subsequently, the RF algorithm was employed to train the model with five input factors, namely the extracted features from the CNN and spatiotemporal factors, including the day of the year, the hour of the day, latitude, and longitude. Independent observations from two stations were used to evaluate the models. The findings demonstrated that the proposed CNN–RF model had better modeling capability compared with the independent CNN and RF models: the average improvements in root mean square error (RMSE) and mean absolute error (MAE) ranged from 8.10% to 11.11%, respectively. In addition, the proposed CNN–RF hybrid model has fewer excess residuals at thresholds of 10 μg/m³, 20 μg/m³, and 30 μg/m³. The results revealed that the proposed CNN–RF ensemble framework is a stable, reliable, and accurate method that can generate superior results compared with the single CNN and RF methods. The proposed method could be a valuable reference for readers and may inspire researchers to develop even more effective methods for air pollution modeling. This research has important implications for air pollution research, data analysis, model estimation, and machine learning.

Images captured in rainy weather conditions often suffer from contamination, resulting in blurred or obscured objects, which can significantly impact detection performance due to the loss of identifiable texture and color information. Moreover, the quality of the detection model plays a pivotal role in determining detection outcomes. This study adopts a dual perspective, considering both pre-trained models and training data. It employs 15 image augmentation techniques, combined with neural style transfer (NST), CycleGAN, and an analytical method, to synthesize images under rainy conditions. The Real-Time Detection Transformer (RTDETR) and YOLOv8 pre-trained models are utilized to establish object detection frameworks tailored for rainy weather conditions. Testing is carried out using the DAWN (Detection in Adverse Weather Nature) dataset. The findings suggest compatibility between the pre-trained detection models and various data synthesis methods. Notably, YOLOv8 exhibits better compatibility with CycleGAN data synthesis, while RTDETR demonstrates a stronger alignment with the NST and analytical approaches. Upon the integration of synthesized rainy images into model training, RTDETR demonstrates significantly enhanced detection accuracy compared to YOLOv8, indicating a more pronounced improvement in performance. The proposed approach of combining RTDETR with NST in this study shows a significant improvement in Recall (R) and mAP50-95 by 16.35% and 15.50%, respectively, demonstrating the robust rainy weather resilience of this method. Additionally, RTDETR outperforms YOLOv8 in terms of inference speed and hardware requirements, making it easier to use and deploy in real-time applications.

Although advancement has been observed in global navigation satellite systems and these systems are widely used, they cannot provide effective navigation and positioning services in covered areas and areas that lack strong signals, such as indoor environments. Therefore, in recent years, indoor positioning technology has become the focus of research and development. The magnetic field of the Earth is quite stable in an open environment. Due to differences in building and internal structures, this type of three-dimensional vector magnetic field is widely available indoors for indoor positioning. A smartphone magnetometer was used in this study to collect magnetic field data for constructing indoor magnetic field maps. Moreover, an acceleration sensor and a gyroscope were used to identify the position of a mobile phone and detect the number of steps travelled by users with the phone. This study designed a procedure for measuring the step length of users. All obtained information was input into a pedestrian dead reckoning (PDR) algorithm for calculating the position of the device. The indoor positioning accuracy of the PDR algorithm was optimised using magnetic gradients of magnetic field maps with a modified particle filter algorithm. Experimental results reveal that the indoor positioning accuracy was between 0.6 and 0.8 m for a testing area that was 85 m long and 33 m wide. This study effectively improved the indoor positioning accuracy and efficiency by using the particle filter method in combination with the PDR algorithm with the magnetic fingerprint map.

Rivers in Taiwan are characterised by steep slopes and high sediment concentrations. Moreover, with global climate change, the dynamics of channel meandering have become complicated and frequent. The primary task of river governance and disaster prevention is to analyse river changes. Spectral water indices are mostly used for surface water estimation, which separates the water from the background based on a threshold value, but it can be challenging in the case of environmental noise. Edge detection uses a canny edge detector and mathematical morphology for extracting geometrical features from the image and effective edge detection. This study combined spectral water indices and mathematical morphology to capture water bodies based on downloaded remote sensing images. From the findings, this study summarised the applicability of various spectral water body indices to the surface water extraction of different river channel patterns in Taiwan. The normalised difference water index and the modified normalised difference water index are suitable for braided rivers, whereas the automated water extraction index is ideal for meandering rivers.

This research examines the risk of natural disasters for offshore wind turbines together with their potential wind energy capacity to help the site selection of offshore wind power farms. Through evaluations of expert questionnaires, we use the fuzzy analytic hierarchy process to weight how natural disasters damage the sub-assemblies of an offshore wind turbine, then obtain the natural disaster risk assessment model, and finally utilize ArcGIS Pro 3.2 to map the potential wind farm sites for the waters off Taiwan’s west coast. We identify that typhoons are the most threatening type of disaster to generators, rotor blades, and rotor hubs; earthquakes are the most threatening to towers; and lightning is the most threatening to transformers. For the whole wind turbine, wind is ironically the most threatening natural disaster, followed by lightning, sea waves, and then earthquakes. Lastly, we examine the results by overlapping the offshore wind farms developed and planned in Taiwan, which coincide with locations in relatively low risk and high wind speed areas.