How to learn the embedding vectors of nodes in unsupervised large-scale heterogeneous networks is a key problem in heterogeneous network embedding research. This paper proposes an unsupervised embedding learning model, named LHGI (Large-scale Heterogeneous Graph Infomax). LHGI adopts the subgraph sampling technology under the guidance of metapaths, which can compress the network and retain the semantic information in the network as much as possible. At the same time, LHGI adopts the idea of contrastive learning, and takes the mutual information between normal/negative node vectors and the global graph vector as the objective function to guide the learning process. By maximizing the mutual information, LHGI solves the problem of how to train the network without supervised information. The experimental results show that, compared with the baseline models, the LHGI model shows a better feature extraction capability both in medium-scale unsupervised heterogeneous networks and in large-scale unsupervised heterogeneous networks. The node vectors generated by the LHGI model achieve better performance in the downstream mining tasks.

Evaluation of papers’ academic influence is a hot issue in the field of scientific research management. Academic big data provides a data treasure with the coexistence of different types of academic entities, which can be used to evaluate academic influence from a more macro and comprehensive perspective. Based on academic big data, a heterogeneous academic network composed of links within and between three types of academic entities (authors, papers and venues) is constructed. In addition, a new academic influence ranking algorithm, AIRank, is proposed to evaluate papers’ academic influence. Different from the existing academic influence ranking algorithms, AIRank has made innovations in the following two aspects. (1) AIRank distinguishes the influence transmission intensity between different node pairs. Different from the strategy of evenly distributing influence among different node pairs, AIRank quantifies the intensity of influence transmission between node pairs based on investigating the citation emotional attribute, semantic similarity and academic quality differences between node pairs. Based on the intensity characteristics, AIRank realises the distribution and transmission of influence among different node pairs. (2) AIRank incorporates the influence transmission from heterogeneous neighbours in evaluating papers’ influence. According to the academic influence of author nodes and venue nodes, AIRank fine-tunes the iteration formula of paper influence to obtain the ranking of papers under the joint influence of homogeneous and heterogeneous neighbours. Experimental results show that, compared with the ranking results based on citation frequency and PageRank algorithm, AIRank algorithm can produce more differentiated and reasonable academic influence ranking results.

Unmanned aerial vehicles (UAVs) are widely used for small target detection of forest fires due to its low-risk rate, low cost and high ground coverage. However, the detection accuracy of small target forest fires is still not ideal due to its irregular shape, different scale and how easy it can be blocked by obstacles. This paper proposes a multi-scale feature extraction model (MS-FRCNN) for small target forest fire detection by improving the classic Faster RCNN target detection model. In the MS-FRCNN model, ResNet50 is used to replace VGG-16 as the backbone network of Faster RCNN to alleviate the gradient explosion or gradient dispersion phenomenon of VGG-16 when extracting the features. Then, the feature map output by ResNet50 is input into the Feature Pyramid Network (FPN). The advantage of multi-scale feature extraction for FPN will help to improve the ability of the MS-FRCNN to obtain detailed feature information. At the same time, the MS-FRCNN uses a new attention module PAM in the Regional Proposal Network (RPN), which can help reduce the influence of complex backgrounds in the images through the parallel operation of channel attention and space attention, so that the RPN can pay more attention to the semantic and location information of small target forest fires. In addition, the MS-FRCNN model uses a soft-NMS algorithm instead of an NMS algorithm to reduce the error deletion of the detected frames. The experimental results show that, compared to the baseline model, the proposed MS-FRCNN in this paper achieved a better detection performance of small target forest fires, and its detection accuracy was 5.7% higher than that of the baseline models. It shows that the strategy of multi-scale image feature extraction and the parallel attention mechanism to suppress the interference information adopted in the MS-FRCNN model can really improve the performance of small target forest fire detection.

The super-resolution reconstruction method based on deep learning can significantly improve the spatial superresolution of remote sensing images. However, the current methods make insufficient use of the remote context information and channel information in shallow feature extraction, resulting in the limited effect of super-resolution reconstruction. This paper proposed a new super-resolution reconstruction model, SIEGAN, which uses generative adversarial network with shallow information enhancement to improve the effect of super-resolution reconstruction of remote sensing images. Similar to other generative adversarial models, SIEGAN is composed of generator and discriminator. But SIEGAN enhances the generator's ability to extract shallow information by using three different scale convolution operations. Specifically, a depth-wise convolution is used to extract the local context information of each band of the image. A depth-wise dilation convolution is used to capture the remote context information in the image. Finally, a 1×1 convolution is used to extract the correlation features between different channels in remote sensing images. In addition, SIEGAN uses U-Net network as its discriminator to provide detailed feedback per pixel to the generator, to improve the model's ability to identify image details. And the spectral-spatial total variation loss function is introduced to ensure the spectral-spatial reliability of the reconstructed images. The experimental results on Gaofen-1 data proved that compared with the state-of-the-art models, SIEGAN has achieved better super-resolution reconstruction performance. Furthermore, the reconstructed images by SIEGAN demonstrate better performance in land cover classification.

Satellite remote sensing plays an important role in wildfire detection. Methods using the brightness and temperature difference of remote sensing images to determine if a wildfire has occurred are one of the main research directions of forest fire monitoring. However, common wildfire detection algorithms are mainly based on a fixed brightness temperature threshold to distinguish wildfire pixels and non-wildfire pixels, which reduces the applicability of the algorithm in different space–time regions. This paper presents an adaptive wildfire detection algorithm, DBTDW, based on a dynamic brightness temperature threshold. First, a regression dataset, MODIS_DT_Fire, was constructed based on moderate resolution imaging spectroradiometry (MODIS) to determine the wildfire brightness temperature threshold. Then, based on the meteorological information, normalized difference vegetation index (NDVI) information, and elevation information provided by the dataset, the DBTDW algorithm was used to calculate and obtain the minimum brightness temperature threshold of the burning area by using the Planck algorithm and Otsu algorithm. Finally, six regression models were trained to establish the correlation between factors and the dynamic brightness temperature threshold of wildfire. The root-mean-square error (RMSE) and mean absolute error (MAE) were used to evaluate the regression performance. The results show that under the XGBoost model, the DBTDW algorithm has the best prediction effect on the dynamic brightness temperature threshold of wildfire (leave-one-out method: RMSE/MAE = 0.0730). Compared with the method based on a fixed brightness temperature threshold, the method proposed in this paper to adaptively determine the brightness temperature threshold of wildfire has higher universality, which will help improve the effectiveness of satellite remote fire detection.