Fire is an important ecosystem process and has played a complex role in terrestrial ecosystems and the atmosphere environment. Sometimes, wildfires are highly destructive natural disasters. To reduce their destructive impact, wildfires must be detected as soon as possible. However, accurate and timely monitoring of wildfires is a challenging task due to the traditional threshold methods easily be suffered to the false alarms caused by small forest clearings, and the omission error of large fires obscured by thick smoke. Deep learning has the characteristics of strong learning ability, strong adaptability and good portability. At present, few studies have addressed the wildfires detection problem in remote sensing images using deep learning method in a nearly real time way. Therefore, in this research we proposed an active fire detection system using a novel convolutional neural network (FireCNN). FireCNN uses multi-scale convolution and residual acceptance design, which can effectively extract the accurate characteristics of fire spots. The proposed method was tested on dataset which contained 1,823 fire spots and 3,646 non-fire spots. The experimental results demonstrate that the FireCNN is fully capable of wildfire detection, with the accuracy of 35.2% higher than the traditional threshold method. We also examined the influence of different structural designs on the performance of neural network models. The comparison results indicates the proposed method produced the best results.

Detailed and timely monitoring of the location and intensity of the fire is critical to reducing the destructive impacts of a fire. Satellite imagery platforms, in particular geostationary satellites with high temporal resolution, allow for real-time fire monitoring. However, because of the coarse resolution of geostationary satellite images, even when deep learning models are applied, precision still remains limited. Thus, the prediction models easily fall into a local optimal solution because of the insufficient semantic information from low spatial resolution. Therefore, in this study, we proposed a novel deep learning model, SBT-FireNet, to monitor fire spots from Himawari-8 satellite images. Specifically, the extraction modules of spatial, band, and time-series features were designed and integrated into the model. The spatial feature extraction module served to collate information about fires and their surrounding environment, while the band and time-series features were designed to obtain fire-sensitive band and time information, respectively. The newly structured SBT-FireNet model was tested in four fire-prone areas with high forest cover. The precision of SBT-FireNet in four test areas is 35.2% higher than other methods. The model yielded significant improvements through the combination of the modules of spatial, band, and time-series features and their fire-tailored design. The advantages of the high temporal resolution of geostationary satellite images were fully integrated into the model to ensure that the model monitors the possibility of fire in an automated way in a near-real-time manner.

Coastal lagoons connecting the land and sea provide essential ecosystem services. However, emerging environmental issues such as environmental pollution and ecological degradation from rapid socio-economic development in coastal zones of south China are becoming increasingly prevalent. This study examined the spatiotemporal variation, sources, assessments, and driving forces of heavy metals based on core and surface sediments collected from Pinqing Lagoon, a coastal lagoon in South China. Sediment cores (PQ1, PQ2, and PQ3) showed distinct vertical variations in the content of Cu, Cd, Zn, Pb, As, and Sb with an average coefficient of variation (C.V.) of 0.25. However, a relatively lower vertical variation (C.V. mean = 0.13) was shown by the other elements (Mn, V, Ni, Cr, and Co). Although Cu was the chief pollutant heavy metal and it had mean values of 1.6 and 1.7 for the enrichment factor (EF) and contamination factor (CF), respectively, Cd posed the highest ecological risk (${\mathrm{E}}_r^i$mean = 36.34). A century-scale anthropogenic disturbance and growing industrial activities in the lagoon area have caused heavy-metal pollution in Pinqing Lagoon. Wastewater discharge into the lagoon over the past 30 years has further aggravated the pollution. The land-use pattern changes in the catchment and removal of polluting industries resulted in a shift in the center of gravity of heavy-metal pollution in the surface sediment of the lagoon. When integrated with the available data, significant pollution gradients were observed suggesting that the pollution level of Pinqing Lagoon was slightly higher than the marginal sea (Honghai Bay) but significantly lower than the adjacent inland water bodies (Gongping and Chisha Reservoirs). This difference attributes unique hydrodynamic conditions to the Pinqing Lagoon, which consistently mitigates environmental pollution by lying at the interface between inland water and the coastal sea in South China. These conditions resulted in the relatively low contamination degree (CD mean = 7.5) and the low ecological risk index (RI mean = 70) over the past 150 years in Pinqing Lagoon.

As global climate change escalates, wildfires have emerged as a critical form of natural disaster, presenting substantial risks to ecosystems, public safety, and economic development. While satellite remote sensing has been extensively utilized for wildfire monitoring, current methodologies face limitations in addressing complex backgrounds and environmental variations. These techniques usually depend on set thresholds or the extraction of local features, which can lead to incorrect positives and overlooked detections. Consequently, existing methods inadequately capture the comprehensive characteristics of fire points. To mitigate these challenges, this study proposes a deep-learning-based fire point detection method that integrates Swin Transformer and BiLSTM for the extraction of the multi-dimensional features associated with fire points. This research represents the inaugural application of the Swin Transformer in the context of fire point detection, leveraging its self-attention mechanism to discern global dependencies and fire point information within complex environments. By amalgamating features at various levels, the proposed method significantly improves the accuracy and robustness of fire point detection. Experimental findings demonstrate that this method surpasses traditional models such as DenseNet, SimpleCNN, and Multi-Layer Perceptron (MLP) across multiple performance metrics, including accuracy, recall, and F1 score.