Search

In the complex dynamics of modern information systems such as e-commerce and streaming services, managing uncertainty and leveraging information theory are crucial in enhancing session-aware recommender systems (SARSs). This paper presents an innovative approach to SARSs that combines static long-term and dynamic short-term preferences within a counterfactual causal framework. Our method addresses the shortcomings of current prediction models that tend to capture spurious correlations, leading to biased recommendations. By incorporating a counterfactual viewpoint, we aim to elucidate the causal influences of static long-term preferences on next-item selections and enhance the overall robustness of predictive models. We introduce a dual-tower architecture with a novel data augmentation process and a self-supervised training strategy, tailored to tackle inherent biases and unreliable correlations. Extensive experiments demonstrate the effectiveness of our approach, outperforming existing benchmarks and paving the way for more accurate and reliable session-based recommendations. [ABSTRACT FROM AUTHOR]

We construct a spacecraft performance-fault relationship graph of the control system, which can help space robots locate and repair spacecraft faults quickly. In order to improve the performance-fault relationship graph, we improve the Deep Deterministic Policy Gradient (DDPG) algorithm, and propose a relationship prediction method that combines representation learning reasoning with deep reinforcement learning reasoning. We take the spacecraft performance-fault relationship graph as the agent learning environment and adopt reinforcement learning to realize the optimal interaction between the agent and the environment. Meanwhile, our model uses a deep neural network to construct a complex value function and strategy function, which makes the agent have excellent perceptual decision-making ability and accurate value judgment ability. We evaluate our model on a performance-fault relationship graph of the control system. The experimental results show that our model has high prediction speed and accuracy, which can completely infer the optimal relationship path between entities to complete the spacecraft performance-fault relationship graph. [ABSTRACT FROM AUTHOR]

The increasing frequency of global drought events poses a significant threat to the stability of grassland ecosystems' functionality. The Inner Mongolian grasslands stand out as one of the world's most drought-prone regions, facing elevated drought risks compared to other biomes. An in-depth comprehension of the impact of drought on grassland ecosystems is paramount for their long-term sustainability. Using the Standardized Precipitation Evapotranspiration Index (SPEI) from 1982 to 2018, this study identified various drought events within the Inner Mongolian grasslands, encompassing moderate drought, severe drought, and extreme drought. The resistance of the vegetation to the different drought conditions, assessed through net primary productivity (NPP) as a metric (reflecting its capacity to maintain its original level during drought periods), was examined. The research findings indicated that the period from 2001 to 2018 witnessed a substantial increase in both the frequency and the extent of drought events compared to the period from 1982 to 2000, particularly concerning severe and extreme droughts. The areas most severely impacted by extreme drought were the Xilingol League and the Alxa League. From 1982–2000 to 2001–2018, under moderate drought conditions, vegetation resistance exhibited a minor decrease in the central and eastern regions but experienced a slight increase in the western region. In contrast, under severe drought conditions, the western region saw a significant decrease in vegetation resistance. Remarkably, under extreme drought conditions, the western region showed a substantial increase in vegetation resistance, while the central and eastern regions experienced a slight decrease. Across all three drought conditions, as precipitation levels declined, the resistance of the meadow–steppe–desert ecosystems demonstrated a high–low–high distribution pattern. The temperate desert steppe exhibited a minimal vulnerability to drought, boasting resistance levels exceeding 0.9. Notably, extreme drought had the most pronounced impact on the temperate meadow steppe, temperate steppe, and temperate desert steppe, particularly within the temperate meadow steppe category. Given these findings, the authorities responsible for grassland management should prioritize regions characterized by frequent drought occurrences and low drought resistance, such as Ulanqab City, the Xilingol League, and the western part of Hulun Buir City. Safeguarding steppe ecosystems is of paramount importance for stabilizing vegetation productivity and land carbon sinks, especially under the anticipated exacerbation of climate conditions in the future. [ABSTRACT FROM AUTHOR]

Grassland aboveground biomass (AGB) is an important indicator for studying the change in grassland ecological quality and carbon cycle. The rapid development of high-resolution remote sensing and unmanned aerial vehicles (UAV) provides a new opportunity for accurate estimation of grassland AGB on the plot scale. In this study, the mountain grassland was taken as the research object. Using UAV Light Detection and Ranging (LiDAR) data and multispectral satellite images, the influence of topographic correction methods on AGB estimation was compared and a series of LiDAR metrics and vegetation indices were extracted. On this basis, a comprehensive indicator, the vegetation index-height-intensity model (VHI), was proposed to estimate AGB quickly. The results show that: (1) Among the four topographic correction methods, the Teillet regression has the best effect, and can effectively improve the accuracy of AGB estimation in mountain grassland. The correlation between corrected ratio vegetation index and AGB was the highest (correlation coefficient: 0.682). (2) Among the height and intensity metrics, median height and max intensity yielded the higher accuracy in estimating AGB, with Root Mean Square Error (RMSE) of 322 g/m2 and 333 g/m2, respectively. (3) The VHI integrated spectrum and LiDAR information, and its accuracy for AGB estimation for mountain grassland, was obviously better than other indicators, with an RMSE of 272 g/m2. We also found that the accuracy of VHI in univariate models was comparable to that of complex multivariate models such as stepwise regression, support vector machine, and random forest. This study provides a new approach for estimating grassland AGB with multi-source data. As a simple and effective indicator, VHI has shown strong application potential for grassland AGB estimating in mountainous areas, and can be further applied to grassland carbon cycle research and fine management. [ABSTRACT FROM AUTHOR]

This paper presents a method to invert the two-dimensional distribution of a temperature and volume concentration of soot particles from color images. By using numerical simulation, the temperature field and particle volume-concentration field of a non-uniform soot flame are simultaneously reconstructed using the wide-response spectrum of a color CCD camera without adding monochromatic filters. The influence of number of cameras, error of camera position angle, measurement noise and different reconstruction algorithms on measurement accuracy are analyzed. The numerical-simulation results demonstrate that camera-position angle errors play a crucial role in the reconstruction accuracy. In addition, increasing the number of cameras can improve the reconstruction result accuracy. Compared with the least squares algorithm, the Tikhonov-regularization algorithm has a stronger anti-noise ability and can resist 39 dB of noise. The conclusions obtained in this paper are helpful to guide following experimental studies. [ABSTRACT FROM AUTHOR]

Temperature and precipitation are considered to be the most important indicators affecting the green-up date. Sensitivity of the green-up date to temperature and precipitation is considered to be one of the key indicators to characterize the response of terrestrial ecosystems to climate change. We selected the main grassland types for analysis, including temperate steppe, temperate meadow steppe, upland meadow, and lowland meadow. This study investigates the variation in key meteorological indicators (daily maximum temperature (Tmax), daily minimum temperature (Tmin), and precipitation) between 2001 and 2018. We then examined the partial correlation and sensitivity of green-up date (GUD) to Tmax, Tmin, and precipitation. Our analysis indicated that the average GUD across the whole area was DOY 113. The mean GUD trend was −3.1 days/decade and the 25% region advanced significantly. Tmax and Tmin mainly showed a decreasing trend in winter (p > 0.05). In spring, Tmax mainly showed an increasing trend (p > 0.05) and Tmin a decreasing trend (p > 0.05). Precipitation showed no significant (p > 0.05) change trend and the trend range was ±10 mm/decade. For temperate steppe, the increase in Tmin in March promotes green-up (27.3%, the proportion of significant pixels), with a sensitivity of −0.17 days/°C. In addition, precipitation in April also promotes green-up (21.7%), with a sensitivity of −0.32 days/mm. The GUDs of temperate meadow steppe (73.9%), lowland meadow (65.9%), and upland meadow (22.1%) were mainly affected by Tmin in March, with sensitivities of −0.15 days/°C, −0.13 days/°C, and −0.14 days/°C, respectively. The results of this study reveal the response of vegetation to climate warming and contribute to improving the prediction of ecological changes as temperatures increase in the future. [ABSTRACT FROM AUTHOR]

Land surface phenology (LSP), as a precise bio-indicator that responds to climate change, has received much attention in fields concerned with climate change and ecology. Yet, the dynamics of LSP changes in the Qinling Mountains (QMs)—A transition zone between warm-temperate and north subtropical climates with complex vegetation structure—under significant climatic environmental evolution are unclear. Here, we analyzed the spatiotemporal dynamics of LSP for different vegetation types in the QMs from 2001 to 2019 and quantified the degree of influence of meteorological factors (temperature, precipitation, and shortwave radiation), and soil (temperature and moisture), and biological factors (maximum of NDVI and middle date during the growing season) on LSP changes using random forest models. The results show that there is an advanced trend (0.15 days/year) for the start of the growing season (SOS), a delayed trend (0.24 days/year) for the end of the growing season (EOS), and an overall extended trend (0.39 days/year) for the length of the growing season (LOS) in the QMs over the past two decades. Advanced SOS and delayed EOS were the dominant patterns leading to a lengthened vegetation growing season, followed by a joint delay of SOS and EOS, and the latter was particularly common in shrub and evergreen broadleaved forests. The growth season length increased significantly in western QMs. Furthermore, we confirmed that meteorological factors are the main factors affecting the interannual variations in SOS and EOS, especially the meteorological factor of preseason mean shortwave radiation (SWP). The grass and crop are most influenced by SWP. The soil condition has, overall, a minor influence the regional LSP. This study highlighted the specificity of different vegetation growth in the QMs under warming, which should be considered in the accurate prediction of vegetation growth in the future. [ABSTRACT FROM AUTHOR]