Search Results (152)

This study examines how ENSO episodes affect maize price volatility transmission between the United States and South Africa. Using daily price data, from 1997 to 2024, for U.S. corn and South African white and yellow maize futures, the study employs GARCH models augmented with ENSO phase indicators and the Southern Oscillation Index (SOI) to determine volatility spillovers. The results show that South African maize prices respond to lagged US corn prices and exchange rate fluctuations, with price volatility of both white and yellow maize prices being more persistent during El Niño and La Niña events. This study integrates climate variability indicators, specifically different ENSO phases and the SOI, to investigate climate-driven volatility transmission between developed and emerging markets. Significant results were obtained when the Southern Oscillation Index was added in the volatility equations. Not only does the inclusion of ENSO indicators and SOI enhance the explanatory power of GARCH models beyond existing studies, it also provides evidence of climate-driven volatility spillovers between a developed and developing market. These findings highlight the role of climate variability in agricultural market dynamics and stress the need for proactive risk management strategies such as buffer stocks and climate responsive financial instruments to ensure food security and market resilience in Southern Africa. Full article

Deep learning has transformed numerous areas of data science by achieving outstanding performance in tasks such as image recognition, speech processing, and natural language understanding. Recently, the challenges of financial forecasting—marked by nonlinear dynamics, volatility, and regime shifts—have attracted increasing attention from the deep learning community. Among these approaches, Convolutional Neural Networks (CNNs), originally developed for spatial data, have shown strong potential for modelling financial time series. This study presents an interpretable CNN-based framework for stock price forecasting using the S&P 500 index as a case study. The proposed approach integrates historical price data with technical indicators within a unified experimental design and compares performance against traditional statistical (ARIMA) and sequential deep learning (LSTM) baselines. Empirical results demonstrate that the CNN model achieves superior predictive Accuracy while maintaining computational efficiency and interpretability through SHAP and Grad-CAM analyses. The findings suggest that lightweight CNN architectures can serve as effective, transparent tools for short-horizon financial forecasting, and future research may extend this framework to multimodal settings incorporating sentiment or news-based data. Full article

This study investigates the thermal resilience of naturally ventilated Lebanese residential buildings in the context of future climates, based on four climate zones: coastal (moderate and humid), low mountain (cool and seasonally variable), inland plateau (semi-arid with high summer heat), and high mountain (cold, with significant winter conditions). The aim of the study is to evaluate how passive envelope interventions can enhance indoor thermal resilience under five present and future work scenarios: TMY, SSP1-2.6 (2050 and 2080), and SSP5-8.5 (2050 and 2080). A baseline model was developed for typical building stock in each climate using EnergyPlus-23.2.0. The passive design parameters of window type, shading depth, and building orientation were systematically altered to analyze their effect on thermal comfort and building thermal resilience. Unlike previous studies that assessed either individual passive strategies or a single climate condition, this research combines multi-objective optimizations with overheating resilience metrics, by optimizing passive interventions using the GenOpt-3.1.0 and BESOS (Python-3.7.3 packages to minimize indoor overheating degree (IOD) and maximize climate change overheating resistivity (CCOR) index. Our findings indicate that optimized passive interventions, such as deep shading (0.6–1.0 m), low-e or bronze glazing, and southern orientations, can reduce overheating in all climate zones, reflecting a substantial improvement in thermal resilience. The novelty of this work lies in combining passive envelope optimization with future climate situations and a long-term overheating resilience index (CCOR) in the Mediterranean region. The results provide actionable suggestions for enhancing buildings’ resilience to climate change in Lebanon, thus informing sustainable design practice within the Eastern Mediterranean climate. Full article

Traditional risk models often fail to capture extreme losses in interconnected global stock markets. This study introduces a novel approach, Expectile Regression Neural Network with Modified LASSO regularization (ERNN-mLASSO), to model nonlinear systemic risk. By analyzing five major stock indices (JKSE, GSPC, GDAXI, FTSE, N225), we identify distinct market roles: developed markets, such as the GSPC, act as risk spreaders, while emerging markets, like the JKSE, act as risk takers. Our network systemic risk index, SNRI, accurately captures systemic shocks during the COVID-19 crisis. More importantly, the model projects increasing global financial fragility through 2025, providing an early warning signal for policymakers and risk managers of potential future instability. Full article

As the region with the earliest housing stock market and the most advanced development in China, the Pearl River Delta has experienced extensive housing demolition and construction, leading to buildings having short lifespans. The environmental pollution generated during this process has brought attention to the concept of green buildings. However, whether due to previous patterns of demolition and construction or the significant impacts of social and economic changes in the current and future housing stock contexts, the comprehensive adaptability of human-centered living spaces remains a crucial issue. This focus is strongly related to the residents’ psychological responses, such as sense of belonging, safety, and atmosphere, across different scales of physical environment. However, most housing evaluation systems regarding sustainable issues are green building evaluation systems. And their concept and practice are often accompanied by a neglect of the interrelationship between people and the built environment, as well as a lack of an appropriate methodological framework to integrate these elements in the temporal dimension. This paper primarily tries to provide new answers to old questions about housing durability by reconceptualizing evaluation systems beyond ecological metrics, while simultaneously challenging accepted answers that privilege material and energy indicators over sociocultural embeddedness. Moreover, an effective housing evaluation framework must transcend purely technical or ecological indicators to systematically integrate the temporal and sociocultural factors that sustain long-term residential quality, particularly in rapidly transforming urban contexts. Therefore, theories closely related to building longevity, such as open building and the “level” strategy, were introduced. Based on this combined methodological framework, selected cases of local traditional housing and green building evaluation systems were studied, aiming to identify valuable longevity factors and improved evaluation methods. Furthermore, two rounds of expert consultation and a data analysis were conducted. The first round helped determine the local indexes and preliminary evaluation methods, while the second round helped confirm the weighting value of each index through a questionnaire study and data analysis. This systematic study ultimately established a preliminary long-term housing evaluation system for the Pearl River Delta. Full article

The historic landscape and the value of the ancient city in the stock era present a diversified and mixed problem; as such, this study explores a quantifiable spatial correlation method for landscape layering characteristics and value space, in order to provide support for the urban renewal paths that integrate historical and contemporary needs. Taking as an example Chaozhou Ancient City, a renowned historical and cultural city in China, this study draws on the theory of historical urban landscape layering and comprehensively uses historical graphic interpretation, GIS spatial quantitative analysis, the single-land-use dynamic degree model, the Analytic Network Process, and the Delphi method to quantitatively analyze and evaluate the landscape layering characteristics and value space of the ancient city. Meanwhile, it explores the relationship between the historical landscape layering characteristics and value space of ancient cities using the spatial autocorrelation model and the coupling coordination modulus model. The key findings are as follows: (1) The high-layer space (66.1%) and high-value space (31.1%) of the historic landscape of Chaozhou Ancient City show significant mismatch and imbalance. Spatially, layer spaces increase from the city center toward the periphery, whereas value spaces decrease from the center outward, demonstrating marked spatial heterogeneity. (2) The layer–value space shows a spatial distribution of agglomeration, with Moran’s I index values of 0.2712 and 0.6437, respectively. The agglomeration degree of the value space is much higher than that of the layer space, and both show significant non-equilibrium and associative coupling. (3) Coupling coordination: basically balanced (D = 0.56) indicates a transition toward a more integrated state, although 48% of the region remains in a state of severe dysfunction, mainly consisting of two types of spaces: “high-layer–high-value” and “low-layer–low-value.” These two dysfunctional types should be prioritized in future conservation and renewal strategies. This study provides a more comprehensive quantitative analysis path for identifying and evaluating the landscape layer–value space of the ancient city, providing visualization tools and decision-making support for the future protection and renewal of Chaozhou Ancient City and the declaration of the World Heritage. Full article

Economic stability in emerging market economies is increasingly shaped by the interplay between global financial integration, domestic monetary dynamics, and asset price fluctuations. Yet, early detection of financial market disruptions remains a persistent challenge. This study constructs a Financial Stress Index (FSI) for Pakistan, utilizing monthly data from 2005 to 2024, to capture systemic stress in a globalized context. Using Principal Component Analysis (PCA), the FSI consolidates diverse indicators, including banking sector fragility, exchange market pressure, stock market volatility, money market spread, external debt exposure, and trade finance conditions, into a single, interpretable measure of financial instability. The index is externally validated through comparisons with the U.S. STLFSI4, the Global Economic Policy Uncertainty (EPU) Index, the Geopolitical Risk (GPR) Index, and the OECD Composite Leading Indicator (CLI). The results confirm that Pakistan’s FSI responds meaningfully to both global and domestic shocks. It successfully captures major stress episodes, including the 2008 global financial crisis, the COVID-19 pandemic, and politically driven local disruptions. A key understanding is the index’s ability to distinguish between sudden global contagion and gradually emerging domestic vulnerabilities. Empirical results show that banking sector risk, followed by trade finance constraints and exchange rate volatility, are the leading contributors to systemic stress. Granger causality analysis reveals that financial stress has a significant impact on macroeconomic performance, particularly in terms of GDP growth and trade flows. These findings emphasize the importance of monitoring sector-specific vulnerabilities in an open economy like Pakistan. The FSI offers strong potential as an early warning system to support policy design and strengthen economic resilience. Future modifications may include incorporating real-time market-based metrics indicators to better align the index with global stress patterns. Full article

Snow crabs (Chionoecetes opilio), a commercially valuable species in Korean waters, have been managed under the Total Allowable Catch (TAC) system since 2002. However, stock assessment has been limited due to difficulties in estimating key ecological traits such as growth, maturity, and mortality. In this study, the Bayesian Schaefer Model (BSM), implemented within CMSY++ framework, was applied to assess the stock status of snow crabs in Korean waters. BSM requires catch and abundance index data, such as catch per unit effort (CPUE) or biomass, as well as prior information on species resilience and relative biomass (B/k). To improve the reliability of B/k priors, we developed a method to calculate them quantitatively using fishery data, sales amounts, and biological information, unlike the qualitative assumptions on stock and fishing conditions proposed in previous research. Two standardized CPUE indices with differing temporal trends in recent years were used as abundance indices. To address the structural uncertainty associated with these divergent trends, we applied a grid-based approach by treating each CPUE index as an independent model scenario and integrating the posterior distributions. A total of 12,000 posterior estimates (6000 per index) were generated through the BSM and used to construct a Kobe plot. Results indicate that the current biomass is slightly above the level supporting maximum sustainable yield, and fishing mortality slightly below the optimal level, suggesting that the stock is healthy and sustainably exploited. Future research should aim to establish a systematic framework for developing quantitative B/k priors to enhance stock assessment accuracy. Full article

This study applies Gradient Boosting Machines (GBMs) and principal component regression (PCR) to forecast the closing price of the Johannesburg Stock Exchange (JSE) All-Share Index (ALSI), using daily data from 2009 to 2024, sourced from the Wall Street Journal. The models are evaluated under three training–testing split ratios to assess short-term forecasting performance. Forecast accuracy is assessed using standard error metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). Across all test splits, the GBM consistently achieves lower forecast errors than PCR, demonstrating superior predictive accuracy. To validate the significance of this performance difference, the Diebold–Mariano (DM) test is applied, confirming that the forecast errors from the GBM are statistically significantly lower than those of PCR at conventional significance levels. These findings highlight the GBM’s strength in capturing nonlinear relationships and complex interactions in financial time series, particularly when using features such as the USD/ZAR exchange rate, oil, platinum, and gold prices, the S&P 500 index, and calendar-based variables like month and day. Future research should consider integrating additional macroeconomic indicators and exploring alternative or hybrid forecasting models to improve robustness and generalisability across different market conditions. Full article

Investigating land cover patterns, changes in carbon stocks, and forecasting future conditions are essential for formulating regional sustainable development strategies and enhancing ecological and environmental quality. This study centers on Guiyang, a mountainous urban area in southwestern China, to analyze the dynamic changes in land cover and their effects on carbon stocks from 2000 to 2035. A carbon stocks assessment framework was developed using a cellular automaton-based artificial neural network model (CA-ANN), the InVEST model, and the geographical detector model to predict future land cover changes and identify the primary drivers of variations in carbon stocks. The results indicate that (1) from 2000 to 2020, impervious surfaces expanded significantly, increasing by 199.73 km². Compared to 2020, impervious surfaces are projected to increase by 1.06 km², 13.54 km², and 34.97 km² in 2025, 2030, and 2035, respectively, leading to further reductions in grassland and forest areas. (2) Over time, carbon stocks in Guiyang exhibited a general decreasing trend; spatially, carbon stocks were higher in the western and northern regions and lower in the central and southern regions. (3) The level of greenness, measured by the normalized vegetation index (NDVI), significantly influenced the spatial variation of carbon stocks in Guiyang. Changes in carbon stocks resulted from the combined effects of multiple factors, with the annual average temperature and NDVI being the most influential. These findings provide a scientific basis for advancing low-carbon development and constructing an ecological civilization in Guiyang. Full article

Small reservoirs have important functions, such as water resource guarantee, flood control and drought resistance, biological habitat and maintaining regional economic development. In order to better clarify the impact of agricultural activities on the nutritional status of water bodies in small reservoirs, zooplankton were quantitatively collected from four small reservoirs in the Jiuxianshan agricultural area of Qufu, Shandong Province, in March and October 2023, respectively. The physical and chemical parameters in sampling points were determined simultaneously. Meanwhile, water samples were collected for nutrient salt analysis, and the eutrophication of water bodies in four reservoirs was evaluated using the comprehensive nutrient status index method. The research found that the species richness of zooplankton after farming (100 species) was significantly higher than that before farming (81 species) (p < 0.05). On the contrary, the dominant species of zooplankton after farming (7 species) were significantly fewer than those before farming (11 species). The estimation results of the standing stock of zooplankton indicated that the abundance and biomass of zooplankton after farming (92.72 ind./L, 0.13 mg/L) were significantly higher than those before farming (32.51 ind./L, 0.40 mg/L) (p < 0.05). Community similarity analysis based on zooplankton abundance (ANOSIM) indicated that there were significant differences in zooplankton communities before and after farming (R = 0.329, p = 0.001). The results of multi-dimensional non-metric sorting (NMDS) showed that the communities of zooplankton could be clearly divided into two: pre-farming communities and after farming communities. The Monte Carlo test results are as follows (p < 0.05). Transparency (Trans), pH, permanganate index (COD_Mn), electrical conductivity (Cond) and chlorophyll a (Chl-a) had significant effects on the community structure of zooplankton before farming. Total nitrogen (TN), total phosphorus (TP) and electrical conductivity (Cond) had significant effects on the community structure of zooplankton after farming. The co-linearity network analysis based on zooplankton abundance showed that the zooplankton community before farming was more stable than that after farming. The water evaluation results based on the comprehensive nutritional status index method indicated that the water conditions of the reservoirs before farming were mostly in a mild eutrophic state, while the water conditions of the reservoirs after farming were all in a moderate eutrophic state. The results show that the nutritional status of small reservoirs in agricultural areas is significantly affected by agricultural activities. The zooplankton communities in small reservoirs underwent significant changes driven by alterations in the reservoir water environment and nutritional status. Based on the main results of this study, we suggested that the use of fertilizers and pesticides should be appropriately reduced in future agricultural activities. In order to better protect the water quality and aquatic ecology of the water reservoirs in the agricultural area. Full article

The international community is striving to build carbon-neutral societies in response to urban environmental challenges. Green Buildings (GBs) and Urban Green Spaces (UGSs) are recognized as key elements in future city development, as they contribute to both the reduction and absorption of carbon emissions. This study analyzed research fields related to GBs and UGSs by collecting and examining keywords from academic articles indexed in the Scopus database: 2880 articles from 1971 to 2025. After refining the dataset to 1685 articles, centrality, betweenness, and cluster analyses were conducted, and the results were visualized through a keyword network map. The findings are summarized as follows: (1) Research on GBs predominantly focuses on experimental and technological aspects, especially in the areas of heat and energy. (2) UGS-related studies are largely policy-driven and comprehensive, centering on green infrastructure and ecosystem services. (3) The international research landscape highlights key topics such as the greening of existing building stock, green roofs, and rooftop agriculture integrating advanced technologies, focusing on how these GB and UGS strategies address barriers to urban carbon cycling. This study offers valuable insights for researchers in architecture, landscape architecture, and urban planning who are working toward the realization of carbon-neutral cities. Full article

With the advancement of deep learning, its application in financial market forecasting has become a research hotspot. This paper proposes an innovative Multi-Scale TsMixer model for predicting stock index futures in the A-share market, covering SSE50, CSI300, and CSI500. By integrating Multi-Scale time-series features across the short, medium, and long term, the model effectively captures market fluctuations and trends. Moreover, since stock index futures reflect the collective movement of their constituent stocks, we introduce a novel approach: predicting individual constituent stocks and merging their forecasts using three fusion strategies (average fusion, weighted fusion, and weighted decay fusion). Experimental results demonstrate that the weighted decay fusion method significantly improves the prediction accuracy and stability, validating the effectiveness of Multi-Scale TsMixer. Full article

Predicting stock prices is a popular area of study within the realms of data mining and machine learning. Precise forecasting can assist investors in mitigating the risks associated with their investments. Given the unpredictable nature of the stock market, influenced by policy changes, stock data often display high levels of fluctuation and randomness, aligning closely with the prevailing market sentiment. Moreover, diverse datasets related to stocks are rich in historical data that can be leveraged to forecast future trends. However, traditional forecasting models struggle to harness this information effectively, which restricts their predictive capabilities and accuracy. To improve the existing issues, this research introduces a novel stock prediction model based on a deep-learning neural network, named after EL-MTSA, which leverages the multifaceted characteristics of stock data along with ensemble learning optimization. In addition, a new evaluation index via market-wide sentiment analysis is designed to enhance the forecasting performance of the stock prediction model by adeptly identifying the latent relationship between the target stock index and dynamic market sentiment factors. Subsequently, many demonstration experiments were conducted on three practical stock datasets, the CSI 300, SSE 50, and CSI A50 indices, respectively. Experiential results show that the proposed EL-MTSA model has achieved a superior predictive performance, surpassing various comparison models. In addition, the EL-MTSA can analyze the impact of market sentiment and media reports on the stock market, which is more consistent with the real trading situation in the stock market, and indicates good predictive robustness and credibility. Full article

The rapid advancement of digital technology has transformed how investors gather financial information, with platforms like Google Trends providing valuable insights into investor behavior through the Google Search Volume Index (GSVI). While the relationship between the GSVI and market behavior has been explored in developed markets, its application in emerging markets like Pakistan remains underexplored. This study investigates how investor attention, measured by the GSVI, influences market volatility, liquidity, and stock price movements in the Pakistan Stock Exchange (PSX), using weekly data from the KSE-100 Index between 2019 and 2024. The findings reveal that the GSVI significantly impacts market volatility and liquidity, particularly in retail-driven markets with high information asymmetry. Additionally, this research shows that the GSVI is a reliable predictor for stock price fluctuations, with heightened investor attention correlating with increased market activity. Despite the limitations of the GSVI in fully capturing investor sentiment, this study contributes to behavioral finance literature by demonstrating the role of digital information flows in shaping market behavior in emerging markets. It offers actionable insights for investors, financial institutions, and policymakers in Pakistan while suggesting areas for future research in applying the GSVI to global contexts and exploring alternative proxies for investor sentiment in emerging economies. Full article