Accurate prediction of US Treasury bond yields is crucial for investment strategies and economic policymaking. This paper explores the application of advanced machine learning techniques, specifically Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models, in forecasting these yields. By integrating key economic indicators and policy changes, our approach seeks to enhance the precision of yield predictions. Our study demonstrates the superiority of LSTM models over traditional RNNs in capturing the temporal dependencies and complexities inherent in financial data. The inclusion of macroeconomic and policy variables significantly improves the models’ predictive accuracy. This research underscores a pioneering movement for the legacy banking industry to adopt artificial intelligence (AI) in financial market prediction. In addition to considering the conventional economic indicator that drives the fluctuation of the bond market, this paper also optimizes the LSTM to handle situations when rate hike expectations have already been priced-in by market sentiment.

Uncontrolled economic development often leads to land degradation, a decline in ecosystem services, and negative impacts on community welfare. This study employs water yield (WY) modeling as a method for environmental management, aiming to provide a comprehensive understanding of the relationship between Land Use Land Cover (LULC), Land Use Intensity (LUI), and WY to support sustainable natural resource management in the Cisadane Watershed, Indonesia. The objectives include: (1) analyzing changes in WY for 2010, 2015, and 2021; (2) predicting WY for 2030 and 2050 under two scenarios—Business as Usual (BAU) and Protected Forest Area (PFA); (3) assessing the impacts of LULC and climate change on WY; and (4) exploring the relationship between LUI and WY. The Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model calculates actual and predicted WY conditions, while the Coupling Coordination Degree (CCD) analyzes the LULC-WY relationship. Results indicate that the annual WY in 2021 was 215.8 × 108 m³, reflecting a 30.42% increase from 2010. Predictions show an increasing trend in WY under both scenarios for 2030 and 2050 with different magnitudes. Rainfall contributes 88.99% more dominantly to WY than LULC. Additionally, around 50% of districts exhibited unbalanced coordination between LUI and WY in 2010 and 2020. This study reveals the importance of ESs in sustainable watershed management amidst increasing demand for natural resources due to population growth.

This study investigated the variability of climate parameters and food crop yields in Nigeria. Data were sourced from secondary sources and analyzed using correlation and multivariate regression. Findings revealed that pineapple was more sensitive to climate variability (76.17%), while maize and groundnut yields were more stable with low sensitivity (0.98 and 1.17%). Yields for crops like pineapple (0.31 kg/ha) were more sensitive to temperature, while maize, beans, groundnut, and vegetable yields were less sensitive to temperature with yields ranging from 0.15 kg/ha, 0.21 kg/ha, 0.18 kg/ha, and 0.12 kg/ha respectively. On the other hand, maize, beans, groundnut, and vegetable yields were more sensitive to rainfall ranging from 0.19kg/ha, 0.15kg/ha, 0.22 kg/ha, and 0.18 kg/ha respectively compared to pineapple yields which decreased with increase rainfall (−0.25 kg/ha). The results further showed that for every degree increase in temperature, maize, pineapple, and beans yields decreased by 0.48, 0.01, and 2.00 units at a 5 % level of significance, while vegetable yield decreased by 0.25 units and an effect was observed. Also, for every unit increase in rainfall, maize, pineapple, groundnut, and vegetable yields decreased by 3815.40, 404.40, 11,398.12, and 2342.32 units respectively at a 5% level, with an observed effect for maize yield. For robustness, these results were confirmed by the generalized additive and the Bayesian linear regression models. This study has been able to quantify the impact of temperature on food crop yields in the African context and employed a novel analytical approach combining the correlation matrix and multivariate linear regression to examine climate-crop yield relationships. The study contributes to the existing body of knowledge on climate-induced risks to food security in Nigeria and provides valuable insights for policymakers, farmers, government, and stakeholders to develop effective strategies to mitigate the impacts of climate change on food crop yields through the integration of climate-smart agricultural practices like agroforestry, conservation agriculture, and drought-tolerant varieties into national agricultural policies and programs and invest in climate information dissemination channels to help consider climate variability in agricultural planning and decision-making, thereby enhancing food security in the country.

This paper investigates the elements affecting dividend yield in developing Southeast Asian countries—more specifically, Thailand, Malaysia, and Singapore. Examined here are the roles of financial information including debt to equity ratio, free cashflows, property, plant, and equipment (PPE) and total sales with controlling factors of size, institutional ownership, and firm age using both short-run and long-run analytical frameworks including the Error Correction Model and Engle and Granger’s approach. The results reveal different trends in the three nations. Higher debt and free cashflows lower dividend yield in Thailand; institutional shareholders benefit from maintaining greater dividend payouts. Aging companies in Malaysia are more likely to pay more dividends while rising revenues are linked to smaller short-term payouts. Leveraged and asset-heavy companies are more likely to keep paying dividends in Singapore. These discoveries have important ramifications for investors and business management trying to maximize dividend policies and improve shareholder value in developing economies.

One crucial metric for estimating a reservoirs and dam’s lifespan is sedimentation. It is dependent upon sediment output, which in turn is dependent upon soil erosion. The study area, the Aguat Wuha Dam, was located in Simada woreda, of northwestern parts of Ethiopia. And the study's goal was to use Arc GIS and RUSLE adjusted to Ethiopian conditions to assess potential soil erosion and sediment output from the watershed and identify hotspot locations for appropriate planning for erosion and sedimentation problem management techniques to make the outputs of the dam project more productive and effective for the proposed and suggested purpose of the dam. To predict the geographical patterns of soil erosion in the watershed, the Geographic Information System (GIS) was combined with the revised universal soil loss equation (RUSLE). A soil erosion map was produced using ArcGIS by utilizing all of the model's parameters, including Erosivity, erodibility, steepness, land use, land cover, and supportive practice factors. The watershed's yearly soil loss varies from 0 to 413.86 tons/ha. In order to determine the erosion hotspot area, the average annual soil loss value was discovered to be 9.24 tons/ha/year and was categorized into six erosion severity classes: low, moderate, high, very high, severe, and very severe. These findings indicated that 162.57 ha and 699.17 ha of the watershed were considered to be extremely and severely vulnerable to soil erosion, respectively. It was discovered that the anticipated sediment yield supplied to the outlet varied from 0 to 104.94 tons/ha/year. By standing from the implications of the assessments of the geological, geotechnical, topographical, and socioenvironmental considerations Watershed management is the most effective way to reduce the amount of sediment produced and the amount that enters the reservoir among the several reservoir sedimentation control options that are available.