Search Results (880)

Forests play a critical role in Earth’s ecosystem, yet monitoring their long-term, large-scale spatiotemporal dynamics remains a significant challenge. This study addresses this gap by developing an integrated framework to map annual forest distribution in Hunan, China, from 1999 to 2023 at a high resolution of 30 m. Our methodology combines multi-temporal satellite imagery (Landsat 5/7/8/9) with key environmental variables, including digital elevation models, temperature, and precipitation data. To efficiently reconstruct historical maps, training samples were automatically derived from a reliable 2023 forest product using a transferable logic, drastically reducing manual annotation effort. Comprehensive evaluations demonstrate the robustness of our approach: (1) Qualitative analyses reveal superior spatial detail and temporal consistency compared to existing global forest maps. (2) Rigorous quantitative validation based on ∼9000 reference samples confirms high and stable accuracy (∼92.4%) and recall (∼91.9%) over the 24-year period. (3) Furthermore, comparisons with government forestry statistics show strong agreement, validating the practical utility of the data. This work provides a valuable, accurate long-term dataset that forms a scientific basis for critical downstream applications such as ecological conservation planning, carbon stock assessment, and climate change research, thereby highlighting the transformative potential of multi-source data fusion and automated methods in advancing geospatial monitoring. Full article

As a key component of sustainable economic development, digital transformation has become a fundamental driver for developing and upgrading the modern economic system. While existing research has identified resources and dynamic capabilities as foundational elements, a critical yet underexplored factor lies in the cognitive foundations that enable firms to strategically direct and leverage these assets. Based on 19,062 observation samples of more than 3000 listed companies in Shanghai and Shenzhen stock markets from 2010 to 2023, this paper constructs a theoretical framework of entrepreneurship, organizational attention and digital transformation from the Attention-Based View, and examines a moderated mediation model of the relationship between entrepreneurship and digital transformation. The results show that entrepreneurship significantly promotes digital transformation; organizational attention to “cooperation orientation” and “future orientation” plays a mediating role in it; and the regional innovation atmosphere positively strengthens the “cooperation orientation” path, facilitating the diffusion of innovative knowledge and technologies within the region. Meanwhile, online media reports negatively regulate the “future orientation” path, reflecting that short-term public pressure may weaken enterprises’ attention to long-term sustainable technology investment. In addition, different dimensions of entrepreneurship have varied effects on digital transformation. Heterogeneity analysis revealed significant variations across ownership type, scale, region, industry competition intensity, and technological intensity. This study expands the theoretical mechanism of entrepreneurship and digital transformation from the perspective of attention allocation, and provides theoretical and empirical foundation for fostering a strategic cognitive orientation and advancing digital transformation. Full article

To investigate whether tourism can act as a catalyst for regional economic convergence during the period 2000–2023, this study fills a critical gap in previous research by simultaneously examining the impact of tourism on economic disparities from both static stock and dynamic incremental perspectives, while accounting for spatial dependence. This study analyzes the economic convergence effects of tourism at the Chinese provincial and regional levels using σ convergence and the spatial Durbin model in a conditional β convergence framework. The results confirm the benefits that tourism brings to economic growth and convergence. Spatially, northeastern China exhibits stronger effects, followed by western and eastern China, in contrast to the relatively weaker impacts in central China. Structurally, its direct effect is more pronounced: the convergence effect is stronger for local areas than for neighboring areas. Temporally, the effect is most pronounced in the early (2000–2012) and late (2020–2023) phases, but becomes statistically insignificant in the intermediate period (2013–2019). By moving beyond the question of whether tourism drives growth to reveal for which regions it is most beneficial, this study offers a refined analytical perspective and actionable insights for achieving balanced regional development in China and other countries and regions at a comparable stage of development. The findings also highlight the potential of cultural heritage as a lever for sustainable and equitable regional growth, channeled through tourism. Full article

Forecasting stock market crashes is difficult because such events are rare, highly nonlinear, and shaped by latent structural and behavioral forces. This study introduces a calibrated and interpretable Random Forest framework for detecting pre-crash conditions through structural feature engineering, early-warning calibration, and model explainability. Using daily data on global equity indices and major large-cap stocks from the U.S., Europe, and Asia, we construct a feature set that captures volatility expansion, moving-average deterioration, Bollinger Band width, and short-horizon return dynamics. Probability-threshold optimization significantly improves sensitivity to rare events and yields an operating point at a crash-probability threshold of 0.33. Compared with econometric and machine learning benchmarks, the calibrated model attains higher precision while maintaining competitive F1 and MCC scores, and it delivers meaningful early-warning signals with an average lead-time of around 60 days. SHAP analysis indicates that predictions are anchored in theoretically consistent indicators, particularly volatility clustering and weakening trends, while robustness checks show resilience to noise, structural perturbations, and simulated flash crashes. Taken together, these results provide a transparent and reproducible blueprint for building operational early-warning systems in financial markets. Full article

Construction of precast reinforced concrete (PRC) industrial halls in seismically active areas has been increasing in recent decades. As connections are one of the most sensitive and vulnerable zones of PRC structures, there is a need to pay special attention to their investigation and modeling in seismic analysis. Knowing that each PRC system is specific and unique, this study aims to evaluate the actual seismic performances of PRC industrial halls built in the AMONT system, which represent a significant portion of the existing industrial building stock in Italy, the Balkans, and Turkey. As there is a lack of published research data on its specific joints, the results of the quasi-static full-scale experiments carried out up to failure on the models of four characteristic connections are presented. Since the implementation of nonlinear dynamic analysis in everyday engineering practice can be demanding, a simplified model of the structure considering the effects of the connections’ stiffness is proposed in this paper. The differences in the roof top displacements between the proposed model and the model with the rigid joints of the analyzed frames are in the range from 16.53% to 66.93%. The values of inter-story drift ratios are larger by 10–100% when the real stiffness of connections is considered, which is above the limit value provided by standard EN 1998-1. These results confirm the necessity of considering the nonlinear behavior and stiffness of connections in precast frame structures when determining displacements, which is particularly important for the verification of the serviceability limit state of structures in seismic regions. Full article

Australia’s National Housing Accord aims to deliver 1.2 million new dwellings between mid-2024 and mid-2029, representing 240,000 annual completions—a 37% increase above the 2024 baseline of 175,000. This study employs a comprehensive system dynamics model with 79 equations (10 stocks, 69 auxiliary variables) to analyze whether this target is structurally achievable, given construction industry capacity constraints. The model integrates builder population dynamics, workforce capacity, construction cost inflation, material supply constraints, and financial market conditions across a ten-year simulation horizon (2024.5–2035). Three policy scenarios test the effectiveness of interventions, including capacity expansion (±10–15%), cost inflation management (±15–20%), planning reforms (+5–15% efficiency), and workforce development programs (+1000–4000 annual graduates). Model validation against Australian Bureau of Statistics data from 2015 to 2024 demonstrates strong empirical foundations. Results show that structural capacity constraints—driven by three simultaneous bottlenecks in material supply, workforce availability, and financing—create a supply ceiling of around 180,000–195,000 annual completions. Even under optimistic policy assumptions, the model projects cumulative completions of 880,000–920,000 dwellings over the Accord period, falling 23–27% short of the 1.2 million target. Critical findings include the following: (1) builder insolvencies exceeding entry rates by 15–25% annually under stress conditions, (2) capacity decline trends of 0.6–0.8% per year due to productivity losses, infrastructure bottlenecks, and regulatory burden, (3) system efficiency degradation from 100% to 96% over the projection period, and (4) non-linear capacity utilization, showing saturation above 82% baseline levels. The analysis reveals that demand-side policies cannot overcome supply-side structural limits, suggesting that policymakers must either substantially reduce targets or implement transformative capacity-building interventions beyond current policy contemplation. Full article

Domestic and foreign capital and consumption goods are imperfect substitutes in production and demand functions of the growth model by Bardhan–Lewis. We extend the model by introducing exogenous technical progress and allow for foreign debt dynamics without dropping domestic capital goods. Trade and growth are mutually affecting each other. Trade may speed up or decrease growth in theory with and without technical progress in comparison with the Solow–Swan model. Steady-state growth rates include that of world income, and the income and price elasticities of export demand. The dynamic process of the economy is analyzed in terms of exports and foreign debt, and both as a share of a stock of imported capital goods. There are multiple steady states where imported capital goods are paid for by high exports and debt, low debt and low exports, or even negative debt and low exports. A stable VAR with data for Brazil shows that the high-debt steady state is relevant for this country. Steady states with high and low debt are saddle-point stable and the steady-state medium debt is stable. Neoclassical standard results appear as two special cases. We link the model to several strands of literature. Full article

This study examined long-term changes in soil carbon stock dynamics 11 and 19 years after fire under different severities at 0–5 and 0–25 cm depths with a digital soil mapping approach. Linear (MLR) and non-linear models (RF, SVR, XGBoost) combined with feature selection methods (r < 0.8, FFS, Boruta) were used to predict bulk density (BD), total C, and C stock. Distributional biases were evaluated with Kolmogorov–Smirnov statistics and corrected by Quantile Mapping (QM). RF-FFS performed best for BD and total C at 0–5, while RF-SVR outperformed for C stock and all properties at 0–25. Total C was 49% higher at 0–5, whereas C stock was 7.57 times greater at 0–25. Both models underestimated variability, especially for C stock. At 0–25, bulk density decreased after fire, particularly under conditions of medium severity, while total C increased following the same tendency. The results showed that fire’s legacy is still present in the ecosystem after one and two decades. This is particularly evident at greater depths, where long-term C stock is lower. Full article

As an essential blue carbon ecosystem, mangroves play a vital role in coastal protection, biodiversity conservation, and climate regulation. However, their complex and variable growth environments pose challenges for precise monitoring. Hainan Island represents a region within China where mangrove forests are the most concentrated and diverse in type. In recent years, ecological restoration efforts have led to the recovery of their coverage areas. This study analyzed the spatial distribution, canopy height, and aboveground carbon storage variations in Hainan mangrove forests. Deep-learning and multiple machine-learning algorithms were used to integrate multitemporal Sentinel-2 remote sensing imagery from 2019 to 2023 with unmanned aerial vehicle observations and field survey data. Multi-rule image fusion and deep-learning techniques effectively enhanced mangrove identification accuracy. The mangrove classification achieved an overall accuracy exceeding 90%. The mangrove area in Hainan increased from 3948.83 ha in 2019 to 4304.29 ha in 2023. Gradient-boosted decision tree (GBDT) models estimated average canopy height with a high coefficient of determination (R² = 0.89), and Random Forest (RF) models yielded the best estimations of total above-ground carbon stock with strong agreement to field observations. Integrating multisource remote sensing data with artificial intelligence algorithms enabled high-precision dynamic monitoring of mangrove distribution, structure, and carbon storage to provide scientific support for the assessment, management, and carbon sink accounting of Hainan mangrove ecosystems. Full article

Small and medium-sized enterprises (SMEs) play a central role in employment and regional economic development, yet they are highly vulnerable to shocks such as pandemics, energy price spikes, and supply chain disruptions. Scenario modelling, stress testing, and digital twins are used to assess resilience, yet most applications focus on large firms in single-country settings. This article develops a model to stress test the resilience of Slovenian SMEs, calibrated with parameters and mechanisms derived from South African SME resilience studies. A system dynamics model with stocks for cash, inventory, and productive capacity is specified and subjected to demand, supply, financial, and compound shock scenarios, with and without resilience measures such as liquidity buffers, customer and supplier diversification, and basic digital planning capabilities. Results indicate non-linear tipping points where small reductions in liquidity sharply increase the likelihood of distress, and show that combinations of liquidity, diversification, and collaborative supply chain practices reduce the depth and duration of output losses. The study demonstrates how evidence from an African context can inform resilience strategies in a small European economy and provides a transparent, portable modelling architecture that can be adapted to other settings. Implications are discussed for SME managers and for policies supporting sustainable, resilient enterprise ecosystems. Full article

Pan-Homophonic events denote fluctuations in stock prices that are triggered by phonetic similarities between event keywords and stock tickers. As a relatively novel and under-researched phenomenon, they mirror a subtle yet influential behavioral deviation within financial markets. Centering on the case of Chuandazhisheng, this study delves into how such events produce dynamic and time-varying impacts on stock prices. A linguistic amplitude segmentation method is devised to discriminate between high- and low-intensity events based on information entropy. To separate pan-homophonic-driven price movements from broader market trends, the Relational Stock Ranking (RSR) model is integrated with a Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) framework to establish an adjusted price benchmark. The empirical analysis reveals a sequential price response: initial moderate fluctuations in the low-amplitude phase often yield to more prominent volatility in the high-amplitude phase. While price surges typically occur within one or two days of the event, they generally revert within approximately three weeks. Moreover, repeated exposures to homo- phonic stimuli seem to attenuate the response, indicating a decaying spillover pattern. These findings contribute to a more profound understanding of the intersection between linguistic cues and market behavior and provide practical insights for investor education, information filtering, and regulatory supervision. Full article

Stock price prediction is a core challenge in quantitative finance. While machine learning has advanced the modeling of complex financial time series, existing methods often rely on single-target predictions, underutilize multidimensional market information, and are disconnected from practical trading systems. To address these gaps, this research develops a hybrid machine learning framework for flexible target forecasting and systematic trading of major American technology stocks. The framework integrates Ensemble Models (AdaBoost, Decision Tree, LightGBM, Random Forest, XGBoost) with Fusion Models (Voting, Stacking, Blending) and introduces a Transfer Learning method enhanced by Dynamic Time Warping to facilitate knowledge sharing across assets, improving robustness. Focusing on ten key stocks, we forecast three distinct momentum indicators: next-day Closing Price Difference, Moving Average Difference, and Exponential Moving Average Difference. Empirical results demonstrate that the proposed Transfer Learning approach achieves superior predictive performance and trading simulations confirm that strategies based on these predicted momentum signals generate substantial returns. This research demonstrates that the proposed hybrid machine learning framework can mitigate the high information entropy inherent in financial markets, offering a systematic and practical method for integrating machine learning with quantitative trading. Full article

Tropical rainforests play a vital role in maintaining global ecological balance, carbon cycling, and biodiversity conservation, making research on their biomass dynamics scientifically significant. This study integrates multi-source remote sensing data, including canopy height derived from GEDI and ICESat-2 satellite-borne lidar, Landsat imagery, and environmental variables, to estimate forest biomass dynamics in Hainan’s tropical rainforests at a 30 m spatial resolution, involving a correlation analysis of factors influencing spatiotemporal changes in Hainan Tropical Rainforest biomass. The research aims to investigate the spatiotemporal variations in forest biomass and identify key environmental drivers influencing biomass accumulation. Four machine learning algorithms—Backpropagation Neural Network (BP), Convolutional Neural Network (CNN), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT)—were applied to estimate biomass across five forest types from 2003 to 2023. Results indicate the Random Forest model achieved the highest accuracy (R² = 0.82). Forest biomass and carbon stocks in Hainan Tropical Rainforest National Park increased significantly, with total carbon stocks rising from 29.03 million tons of carbon to 42.47 million tons of carbon—a 46.36% increase over 20 years. These findings demonstrate that integrating multimodal remote sensing data with advanced machine learning provides an effective approach for accurately assessing biomass dynamics, supporting forest management and carbon sink evaluations in tropical rainforest ecosystems. Full article

Studies of swordfish growth provide essential biological parameters for stock assessment and fisheries management, informing both conventional population models and the evaluation of different management strategies. The present study aims to provide insight into the dynamics of the South Atlantic Ocean stock growth patterns. The sampling is the most complete to date in the literature, with a wide geographical distribution and in every month of the year. The analysis included 788 anal fins. Biometric relationships between different anal fin spine measurements and fish size were found. Some variation in the size of annulus one and vascularisation hiding some internal bands was found in larger specimens. Marginal increment ratio (MIR) and edge type analyses showed an annual band formation in the austral winter (July to September), thereby confirming the hypothesis of one annulus formation per year. Growth parameters were calculated using different growth models. The Gompertz model yielded the most reliable parameters (L_∞ = 341 cm LJFL, k = 0.13 yr⁻¹, T = 2.83 yr). The tagging and recapture data corroborated the selected model. Results were compared with other growth curves published. Full article

This study selects daily data from 27 fintech companies and 16 listed commercial banks between January 2015 and December 2024 as research samples. Based on complex network theory, we construct an integrated analytical framework encompassing risk measurement, regime identification, and early warning system construction through HD-TVP-VAR model coupled with the Elastic Net algorithm, MS-AR model, and dynamic Logit model. The findings reveal that the total risk spillover rate between fintech and banking ranges from 73.09% to 95.18%, demonstrating significant time-varying and event-driven characteristics in risk contagion. The risk contagion evolution is characterized by three distinct phases: net risk absorption by the banking sector, bidirectional equilibrium contagion, and net risk dominance by the fintech sector. Joint-stock commercial banks and city commercial banks exhibit higher sensitivity to fintech risks compared to state-owned large commercial banks. Key hubs for risk contagion include institutions like Yinxin Technology and Huaxia Bank, with concentrated risk contagion within industry clusters. The MS-AR model accurately delineates low-, medium-, and high-risk zones, showing strong alignment between high-risk periods and major events. The dynamic Logit model incorporating total risk correlation indices demonstrates high consistency between early warning signals and risk evolution trajectories, providing theoretical and practical references for cross-industry systemic financial risk prevention. Full article