The alpine grassland on the Qinghai-Tibet Plateau covers an area of about 1/3 of China’s total grassland area and plays a crucial role in regulating grassland ecological functions. Both environmental changes and irrational use of the grassland can result in severe grassland degradation in some areas of the Qinghai-Tibet Plateau. However, the magnitude and patterns of the physical and anthropogenic factors in driving grassland variation over northern Tibet remain debatable, and the interactive influences among those factors are still unclear. In this study, we employed a geographical detector model to quantify the primary and interactive impacts of both the physical factors (precipitation, temperature, sunshine duration, soil type, elevation, slope, and aspect) and the anthropogenic factors (population density, road density, residential density, grazing density, per capita GDP, and land use type) on vegetation variation from 2000 to 2015 in northern Tibet. Our results show that the vegetation index in northern Tibet significantly decreased from 2000 to 2015. Overall, the stability of vegetation types was sorted as follows: the alpine scrub > the alpine steppe > the alpine meadow. The physical factors, rather than the anthropogenic factors, have been the primary driving factors for vegetation dynamics in northern Tibet. Specifically, meteorological factors best explained the alpine meadow and alpine steppe variation. Precipitation was the key factor that influenced the alpine meadow variation, whereas temperature was the key factor that contributed to the alpine steppe variation. The anthropogenic factors, such as population density, grazing density and per capita GDP, influenced the alpine scrub variation most. The influence of population density is highly similar to that of grazing density, which may provide convenient access to simplify the study of the anthropogenic activities in the Tibet plateau. The interactions between the driving factors had larger effects on vegetation than any single factor. In the alpine meadow, the interaction between precipitation and temperature can explain 44.6% of the vegetation variation. In the alpine scrub, the interaction between temperature and GDP was the highest, accounting for 27.5% of vegetation variation. For the alpine steppe, the interaction between soil type and population density can explain 29.4% of the vegetation variation. The highest value of vegetation degradation occurred in the range of 448–469 mm rainfall in the alpine meadow, 0.61–1.23 people/km² in the alpine scrub and –0.83–0.15 °C in the alpine steppe, respectively. These findings could contribute to a better understanding of degradation prevention and sustainable development of the alpine grassland ecosystem in northern Tibet.

Mapping vegetation alliances is essential for understanding ecological patterns and supporting sustainable land management in arid and semi-arid areas. However, traditional remote sensing typically only distinguishes grassland boundaries or broad subclasses, failing to differentiate specific vegetation alliances. Furthermore, while traditional vegetation mapping relies heavily on field surveys, manual interpretation, and expert knowledge, this labor-intensive approach hinders efficient large-scale mapping. This study proposes an efficient method for vegetation mapping by integrating field survey data with multi-source and multi-temporal remote sensing variables using deep learning. A series of deep neural network models was designed to systematically characterize and leverage spectral signatures, climatic factors, and topographic habitat features for fine-grained classification of 32 vegetation alliances in Xinjiang, a typical arid to semi-arid region. The resulting vegetation map achieved an alliance-level classification accuracy of 0.5125 on an independent test set, with the five most dominant alliances: Stipa spp. desert steppe, Stipa spp. steppe, Poa spp. meadow, and Anabasis spp. desert, accounting for over 10.45% of the total area of Xinjiang. Compared with traditional approaches, this method significantly improves mapping efficiency and offers a scalable solution for large-area, updatable vegetation classification. The approach provides a valuable reference for ecological assessment and dynamic vegetation monitoring in arid and semi-arid regions.

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Early works performed this task via simple models developed over KG triples. Recent attempts focused on either designing more complicated triple scoring models, or incorporating extra information beyond triples. This paper, by contrast, investigates the potential of using very simple constraints to improve KG embedding. We examine non-negativity constraints on entity representations and approximate entailment constraints on relation representations. The former help to learn compact and interpretable representations for entities. The latter further encode regularities of logical entailment between relations into their distributed representations. These constraints impose prior beliefs upon the structure of the embedding space, without negative impacts on efficiency or scalability. Evaluation on WordNet, Freebase, and DBpedia shows that our approach is simple yet surprisingly effective, significantly and consistently outperforming competitive baselines. The constraints imposed indeed improve model interpretability, leading to a substantially increased structuring of the embedding space. Code and data are available at https://github.com/iieir-km/ComplEx-NNE_AER.

We present our winning solution for the WSDM Cup 2017 triple scoring task. We devise an ensemble of four base scorers, so as to leverage the power of both text and knowledge bases for that task. Then we further refine the outputs of the ensemble by trigger word detection, achieving even better predictive accuracy. The code is available at https://github.com/wsdm-cup-2017/bokchoy.