Search

Predicting carbon prices is crucial for the growth of China's carbon trading industry. This paper proposes a residual correction model that considers multiple influencing factors. First, the best historical data and main external factors input by the model are determined by using the partial autocorrelation function and Spearman correlation analysis, and the carbon price forecasting index system is constructed. Second, the whale optimization algorithm (WOA) is utilized to determine the optimal parameters of the extreme gradient boosting (XGBoost), and the WOA‐XGBoost model is built to perform preliminary carbon price forecasts and obtain the residual series. Finally, the carbon price residual series undergoes decomposition into multiple components utilizing the complete ensemble empirical mode decomposition for subsequent forecasting and the aggregation of outcomes. Experiments are conducted to predict two carbon trading markets in Hubei and Guangzhou, and a feature importance analysis is performed. The results indicate that the proposed hybrid model consistently outperforms the comparative models in terms of prediction accuracy. Furthermore, it is revealed that historical carbon prices and European Union carbon prices are the key factors influencing the prediction of carbon market prices. [ABSTRACT FROM AUTHOR]

To quantitatively characterize the complexity of shale pore structures and their controlling factors in the Longmaxi Formation of Western Hubei, our study focused on the organic‐rich shale outcrops of the Longmaxi Formation in the Yidu‐Hefeng compound anticline. We conducted tests for shale organic content, maturity, and whole‐rock mineral composition, along with employing high‐pressure mercury injection and low‐temperature gas adsorption experiments. Utilizing the V‐S, FHH, and sponge models, we calculated the fractal dimensions of micro‐, meso‐, and macropores. In the Yidu‐Hefeng region, the Longmaxi Formation is characterized by calcium‐rich shales that are abundant in organic matter. Our analysis of samples revealed a total organic carbon (TOC) ranging between 1.04% and 4.24%, with an average of 2.5%. The Ro values fluctuate between 2.98% and 3.57%, with a mean value of 2.845%, indicating an over‐mature stage from early to late thermogenesis. Constituents such as quartz span from 39.8% to 51.3%, with a median of 44.3%, while feldspar oscillates between 3.8% and 12.4%, averaging at 8.48%. Clay minerals constitute 24.3% to 41.7% of the samples, with a mean of 34.16%. Shale porosity exhibits a segmented fractal nature. For instance, D1 varies from 2.1278 to 2.4056, with a mean of 2.2767; D2 fluctuates between 2.4995 and 2.7492, averaging at 2.6309; and D3 ranges from 2.6835 to 2.9427, centering around 2.8111. These variations indicate the intricacies of the macropore structure. Positive correlations between TOC and maturity with D1 and D2 are evident, whereas a negative association is observed with D3. The collaborative interplay between siliceous minerals and organics mirrors the relationship between the siliceous mineral content and its fractal dimensions, akin to TOC. Clay mineral transformations, due to accumulation and dehydration, predominantly contribute to macro‐porosity, weakly aligning negatively with D1 and D2 but positively with D3. Variations in carbonate and siliceous minerals and their role in primarily yielding dissolution macropores manifest a subtle negative link with D1 and D2 while enhancing D3. Pore volume correlates positively with D1 and D2, exhibits no conspicuous association with D3, and trends negatively. The compaction and transformation processes of clay minerals seem to favor the generation of macropores, mildly aligning positively with D3. [ABSTRACT FROM AUTHOR]

Purpose: Obvious inconsistencies in auto‐segmentations exist among various AI software. In this study, we have developed a novel convolutional neural network (CNN) fine‐tuning workflow to achieve precise and robust localized segmentation. Methods: The datasets include Hubei Cancer Hospital dataset, Cetuximab Head and Neck Public Dataset, and Québec Public Dataset. Seven organs‐at‐risks (OARs), including brain stem, left parotid gland, esophagus, left optic nerve, optic chiasm, mandible, and pharyngeal constrictor, were selected. The auto‐segmentation results from four commercial AI software were first compared with the manual delineations. Then a new multi‐scale lightweight residual CNN model with an attention module (named as HN‐Net) was trained and tested on 40 samples and 10 samples from Hubei Cancer Hospital, respectively. To enhance the network's accuracy and generalization ability, the fine‐tuning workflow utilized an uncertainty estimation method for automatic selection of candidate samples of worthiness from Cetuximab Head and Neck Public Dataset for further training. The segmentation performances were evaluated on the Hubei Cancer Hospital dataset and/or the entire Québec Public Dataset. Results: A maximum difference of 0.13 and 0.7 mm in average Dice value and Hausdorff distance value for the seven OARs were observed by four AI software. The proposed HN‐Net achieved an average Dice value of 0.14 higher than that of the AI software, and it also outperformed other popular CNN models (HN‐Net: 0.79, U‐Net: 0.78, U‐Net++: 0.78, U‐Net‐Multi‐scale: 0.77, AI software: 0.65). Additionally, the HN‐Net fine‐tuning workflow by using the local datasets and external public datasets further improved the automatic segmentation with the average Dice value by 0.02. Conclusion: The delineations of commercial AI software need to be carefully reviewed, and localized further training is necessary for clinical practice. The proposed fine‐tuning workflow could be feasibly adopted to implement an accurate and robust auto‐segmentation model by using local datasets and external public datasets. [ABSTRACT FROM AUTHOR]