Carbon emissions play a significant role in shaping social policy-making, industrial planning, and other critical areas. Recurrent neural networks (RNNs) serve as the major choice for carbon emission prediction. However, year-frequency carbon emission data always results in overfitting during RNN training. To address this issue, we propose a novel model that combines oscillatory particle swarm optimization (OPSO) with long short-term memory (LSTM). OPSO is employed to fine-tune the hyperparameters of LSTM, utilizing an oscillatory strategy to effectively mitigate overfitting and consequently improve the accuracy of the LSTM model. In validation tests, real data from Hainan Province, encompassing diverse dimensions such as gross domestic product, forest area, and ten other relevant factors, are used. Standard LSTM and PSO-LSTM are selected in the control group. The mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are used to evaluate the performance of these methods. In the test dataset, the MAE of OPSO-LSTM is 117.708, 65.72% better than LSTM and 29.48% better than PSO-LSTM. The RMSE of OPSO-LSTM is 149.939, 68.52% better than LSTM and 41.90% better than PSO-LSTM. The MAPE of OPSO-LSTM is 0.017, 65.31% better than LSTM, 29.17% better than PSO-LSTM. The experimental results prove that OPSO-LSTM can provide reliable predictions for carbon emissions.

Laguncularia racemosa is widely planted in coastal mudflats as a pioneer species of mangrove afforestation in China; however, whether it exhibits invasiveness as an exotic species has been a topic of debate. In this study, we investigated the distribution, community structure, and population characteristics of L. racemosa on Hainan Island, China, to discuss its potential invasiveness. The results showed that Hainan Island has become an important distribution area for L. racemosa in China, covering a total area of 64.90 ha. In this investigation, a total of 11 true mangrove species, belonging to six families and 11 genera, were discovered in the L. racemosa community throughout Hainan Island. Furthermore, L. racemosa exhibited a strong adaptive range to seawater salinity and demonstrated a high capacity for natural dispersion. L. racemosa exhibited high importance values in the tree, shrub, and seedling layers of this artificial community, indicating its dominance and potential exclusion of other mangrove species. Over time, the importance values of L. racemosa in the tree and shrub layers initially decreased and then increased, while the opposite trend was observed in the seedling layer. Overall, the diversity indexes, including the Simpson index, Shannon–Wiener index, and Pielou community evenness index, were low in the planted L. racemosa forest on Hainan Island, suggesting a relatively simple species composition within the L. racemosa community. Additionally, based on the height levels of the L. racemosa population, we found that it mainly belonged to the first level, characterized by a large number of seedlings on Hainan Island. The number of L. racemosa seedlings gradually decreased in subsequent levels, and higher height levels of L. racemosa appeared with longer planting times, indicating a growing trend of potential invasiveness of L. racemosa on Hainan Island over an extended period. We suggest that the government should be able to list L. racemosa as an invasive species that can be harvested in the future. Based on this, this study provides fundamental data and theoretical references for the sustainable prevention, control, and management of the exotic species L. racemosa on Hainan Island, and also in other mangrove wetlands in China.