Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine.

Forest fires threaten global ecosystems, socio-economic structures, and public safety. Accurately assessing forest fire susceptibility is critical for effective environmental management. Supervised learning methods dominate this assessment, relying on a substantial dataset of forest fire occurrences for model training. However, obtaining precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors for training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in scenarios with limited samples. We conducted a comparative analysis, evaluating its performance against widely used supervised learning methods. The assessment area for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accuracies for both supervised and semi-supervised learning methods across various small sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findings indicate that TSVM exhibits superior prediction accuracy compared to supervised learning with limited samples, yielding more plausible forest fire susceptibility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves prediction accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In contrast, random forests, the top performers in supervised learning, demonstrate accuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the same small sample sizes. Additionally, we discussed three key aspects: TSVM parameter configuration, the impact of unlabeled sample size, and performance within typical sample sizes. Our findings support semi-supervised learning as a promising approach compared to supervised learning for forest fire susceptibility assessment and mapping, particularly in scenarios with small sample sizes.

Construction of Stretching-Bending Sequential Pattern to Recognize Work Cycles for Earthmoving Excavator from Long Video Sequences.

Counting the number of work cycles per unit of time of earthmoving excavators is essential in order to calculate their productivity in earthmoving projects. The existing methods based on computer vision (CV) find it difficult to recognize the work cycles of earthmoving excavators effectively in long video sequences. Even the most advanced sequential pattern-based approach finds recognition difficult because it has to discern many atomic actions with a similar visual appearance. In this paper, we combine atomic actions with a similar visual appearance to build a stretching-bending sequential pattern (SBSP) containing only "Stretching" and "Bending" atomic actions. These two atomic actions are recognized using a deep learning-based single-shot detector (SSD). The intersection over union (IOU) is used to associate atomic actions to recognize the work cycle. In addition, we consider the impact of reality factors (such as driver misoperation) on work cycle recognition, which has been neglected in existing studies. We propose to use the time required to transform "Stretching" to "Bending" in the work cycle to filter out abnormal work cycles caused by driver misoperation. A case study is used to evaluate the proposed method. The results show that SBSP can effectively recognize the work cycles of earthmoving excavators in real time in long video sequences and has the ability to calculate the productivity of earthmoving excavators accurately.

A multiscale approach to identifying spatiotemporal pattern of habitat selection for red-crowned cranes.

Effective conservation measures largely depend on knowledge of habitat selection of target species. Little is known about the scale characteristics and temporal rhythm of habitat selection of the endangered red-crowned crane, limiting the habitat conservation. Here, two red-crowned cranes were tracked with Global position system (GPS) for two years in Yancheng National Nature Reserve (YNNR). A multiscale approach was developed to identify the spatiotemporal pattern of habitat selection of red-crowned cranes. The results revealed that Red-crowned cranes preferred to select Scirpus mariqueter, ponds, Suaeda salsa, and Phragmites australis, and avoid Spartina alterniflora. In each season, habitat selection ratio for Scirpus mariqueter and ponds was the highest during the day and night, respectively. Further multiscale analysis showed that the percent coverage of Scirpus mariqueter at the 200-m to 500-m scale was the most important predictor for all habitat selection modeling, emphasizing the importance of restoring a large area of Scirpus mariqueter habitat for red-crowned crane population restoration. Additionally, other variables affect habitat selection at different scales, and their contributions vary with seasonal and circadian rhythm. Furthermore, habitat suitability was mapped to provide a direct basis for habitat management. The suitable area of daytime and nighttime habitat accounted for 5.4%-19.0% and 4.6%-10.2% of the study area, respectively, implying the urgency of restoration. The study highlighted the scale and temporal rhythms of habitat selection for various endangered species that depend on small habitats. The proposed multiscale approach applies to the restoration and management of habitats of various endangered species.

Successful infection of BALB/c mice by a swine hepatitis E virus clone constructed with reverse genetics.

BACKGROUND: Hepatitis E virus (HEV) is a leading cause of hepatitis worldwide. However, its infection biology and pathogenesis remain largely elusive. Furthermore, no proven medication is available for treating hepatitis E. Robust experimental models are urgently required to advance the research of HEV infection. Because of the lacking of a sophisticated small animal model, this study aimed to establish a mouse model of HEV infection. METHODS: We constructed a full-length swine HEV cDNA clone of genotype 4 (named as pGEM-HEV) by reverse genetics approach. And we inoculated with HEV RNA in BALB/c mice to establish small animal model for HEV infection and pathogenesis studies. RESULTS: The capped RNA transcripts of pGEM-HEV prepared in vitro were replication-competent in HepG2 cells. Importantly, BALB/c mice intravenously inoculated with RNA transcripts of pGEM-HEV developed an active infection as shown by shedding viruses in feces, detectable negative strand of HEV in the liver, spleen and kidney, and causing liver inflammation. CONCLUSION: In this study, we successfully established of BALB/c mice-based small animal model for HEV provides an opportunity to further understand HEV pathogenesis and to develop effective antiviral medications.

Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution.

Floods are among Earth's most common natural hazards, and they cause major economic losses and seriously affect peoples' lives and health. This paper addresses the development of a flood susceptibility assessment that uses intelligent techniques and GIS. An adaptive neuro-fuzzy inference system (ANFIS) was coupled with a genetic algorithm and differential evolution for flood spatial modelling. The model considers thirteen hydrologic, morphologic and lithologic parameters for the flood susceptibility assessment, and Hengfeng County in China was chosen for the application of the model due to data availability and the 195 total flood events. The flood locations were randomly divided into two subsets, namely, training (70% of the total) and testing (30%). The Step-wise Weight Assessment Ratio Analysis (SWARA) approach was used to assess the relation between the floods and influencing parameters. Subsequently, two data mining techniques were combined with the ANFIS model, including the ANFIS-Genetic Algorithm and the ANFIS-Differential Evolution, to be used for flood spatial modelling and zonation. The flood susceptibility maps were produced, and their robustness was checked using the Receiver Operating Characteristic (ROC) curve. The results showed that the area under the curve (AUC) for all models was >0.80. The highest AUC value was for the ANFIS-DE model (0.852), followed by ANFIS-GA (0.849). According to the RMSE and MSE methods, the ANFIS-DE hybrid model is more suitable for flood susceptibility mapping in the study area. The proposed method is adaptable and can easily be applied in other sites for flood management and prevention.

A New DEM Generalization Method Based on Watershed and Tree Structure.

The DEM generalization is the basis of multi-dimensional observation, the basis of expressing and analyzing the terrain. DEM is also the core of building the Multi-Scale Geographic Database. Thus, many researchers have studied both the theory and the method of DEM generalization. This paper proposed a new method of generalizing terrain, which extracts feature points based on the tree model construction which considering the nested relationship of watershed characteristics. The paper used the 5 m resolution DEM of the Jiuyuan gully watersheds in the Loess Plateau as the original data and extracted the feature points in every single watershed to reconstruct the DEM. The paper has achieved generalization from 1:10000 DEM to 1:50000 DEM by computing the best threshold. The best threshold is 0.06. In the last part of the paper, the height accuracy of the generalized DEM is analyzed by comparing it with some other classic methods, such as aggregation, resample, and VIP based on the original 1:50000 DEM. The outcome shows that the method performed well. The method can choose the best threshold according to the target generalization scale to decide the density of the feature points in the watershed. Meanwhile, this method can reserve the skeleton of the terrain, which can meet the needs of different levels of generalization. Additionally, through overlapped contour contrast, elevation statistical parameters and slope and aspect analysis, we found out that the W8D algorithm performed well and effectively in terrain representation.

Complete genome sequence of Swine hepatitis e virus prevalent in southwest china.

Hepatitis E virus (HEV) is an important public health concern in the world, especially in developing countries of Africa and Asia, including China. Hepatitis E is recognized as a zoonotic disease, which is transmitted across species, including between humans and swine. HEV is highly endemic in China, but the complete sequence of HEV in southwestern China is lacking. Swine HEV strain KM01 was isolated from a village in rural Kunming, Yunnan province, China, where swine are housed with humans. Here, we report the complete genome sequence of the swine HEV strain KM01. The sequence and phylogenetic analyses reveal that swine HEV is closely related to the strain isolated from Xinjiang (CHN-XJ-SW13). The genome of the KM01 strain will facilitate further study of HEV molecular epidemiology and genetic diversity in China.