Forest fires pose significant hazards to ecological environments and economic society. The detection of forest fire smoke can provide crucial information for the suppression of early fires. Previous detection models based on deep learning have been limited in detecting small smoke and smoke with smoke-like interference. In this paper, we propose a lightweight model for forest fire smoke detection that is suitable for UAVs. Firstly, a smoke dataset is created from a combination of forest smoke photos obtained through web crawling and enhanced photos generated by using the method of synthesizing smoke. Secondly, the GSELAN and GSSPPFCSPC modules are built based on Ghost Shuffle Convolution (GSConv), which efficiently reduces the number of parameters in the model and accelerates its convergence speed. Next, to address the problem of indistinguishable feature boundaries between clouds and smoke, we integrate coordinate attention (CA) into the YOLO feature extraction network to strengthen the extraction of smoke features and attenuate the background information. Additionally, we use Content-Aware Reassembly of FEatures (CARAFE) upsampling to expand the receptive field in the feature fusion network and fully exploit the semantic information. Finally, we adopt SCYLLA-Intersection over Union (SIoU) loss as a replacement for the original loss function in the prediction phase. This substitution leads to improved convergence efficiency and faster convergence. The experimental results demonstrate that the LMDFS model proposed for smoke detection achieves an accuracy of 80.2% with a 5.9% improvement compared to the baseline and a high number of Frames Per Second (FPS)—63.4. The model also reduces the parameter count by 14% and Giga FLoating-point Operations Per second (GFLOPs) by 6%. These results suggest that the proposed model can achieve a high accuracy while requiring fewer computational resources, making it a promising approach for practical deployment in applications for detecting smoke.

Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct a wetland classification study for coastal wetlands in Yancheng, Jiangsu, China. After preprocessing the Sentinel data, nine classification objects (construction land, Spartina alterniflora (S. alterniflora), Suaeda salsa (S. salsa), Phragmites australis (P. australis), farmland, river system, aquaculture and tidal falt) were identified based on the previous literature and remote sensing images. Moreover, mAcc, mIoU, aAcc, Precision, Recall and F-1 score were chosen as evaluation indicators. This study explores the potential and effectiveness of multiple methods, including data image processing, machine learning and deep learning. The results indicate that SegFormer is the best model for wetland classification, efficiently and accurately extracting small-scale features. With mIoU (0.81), mAcc (0.87), aAcc (0.94), mPrecision (0.901), mRecall (0.876) and mFscore (0.887) higher than other models. In the face of unbalanced wetland categories, combining CrossEntropyLoss and FocalLoss in the loss function can improve several indicators of difficult cases to be segmented, enhancing the classification accuracy and generalization ability of the model. Finally, the category scale pie chart of Yancheng Binhai wetlands was plotted. In conclusion, this study achieves an effective segmentation of Yancheng coastal wetlands based on the semantic segmentation method of deep learning, providing technical support and reference value for subsequent research on wetland values.

The frequent occurrence of forest fires causes irreparable damage to the environment and the economy. Therefore, the accurate detection of forest fires is particularly important. Due to the various shapes and textures of flames and the large variation in the target scales, traditional forest fire detection methods have high false alarm rates and poor adaptability, which results in severe limitations. To address the problem of the low detection accuracy caused by the multi-scale characteristics and changeable morphology of forest fires, this paper proposes YOLOv5s-CCAB, an improved multi-scale forest fire detection model based on YOLOv5s. Firstly, coordinate attention (CA) was added to YOLOv5s in order to adjust the network to focus more on the forest fire features. Secondly, Contextual Transformer (CoT) was introduced into the backbone network, and a CoT3 module was built to reduce the number of parameters while improving the detection of forest fires and the ability to capture global dependencies in forest fire images. Then, changes were made to Complete-Intersection-Over-Union (CIoU) Loss function to improve the network’s detection accuracy for forest fire targets. Finally, the Bi-directional Feature Pyramid Network (BiFPN) was constructed at the neck to provide the model with a more effective fusion capability for the extracted forest fire features. The experimental results based on the constructed multi-scale forest fire dataset show that YOLOv5s-CCAB increases AP@0.5 by 6.2% to 87.7%, and the FPS reaches 36.6. This indicates that YOLOv5s-CCAB has a high detection accuracy and speed. The method can provide a reference for the real-time, accurate detection of multi-scale forest fires.