Science – Page 125 – Minority Mindset

Predicting Heart Risk in Diabetes: A New Era of Accuracy

10.11.2025 by qfx

Machine learning and deep learning techniques are significantly improving the prediction of cardiovascular disease in diabetic patients.

Predicting Carbon Prices: A New Approach to Forecasting Emissions Markets

10.11.2025 by qfx

Multiple forecasting models were evaluated, revealing varying degrees of accuracy in predicting carbon price fluctuations.

A novel forecasting framework combining signal processing and deep learning dramatically improves the accuracy of EU carbon price predictions.

Beyond the Algorithm: Making Credit Decisions Transparent

10.11.2025 by qfx

The neural network, despite its complexity, demonstrates a predictable, instance-by-instance rationale, suggesting that even sophisticated models ultimately rely on discernible, albeit potentially opaque, logic when making predictions.

New research details a practical framework for evaluating how easily we can understand the reasoning behind AI-powered credit risk assessments.

Predicting Grid Resilience in a Renewable Future

10.11.2025 by qfx

Modal features extracted from time-series data via Dynamic Mode Decomposition are mapped onto evolving dynamic adjacency matrices, enabling a recurrent network to forecast probabilities of system instability—a process inevitably strained by the complexities of real-world application despite its theoretical elegance.

A new approach to forecasting power system stability leverages the power of neural networks and dynamic systems analysis.

Mapping Landslides with AI: A New Approach to Hazard Prediction

10.11.2025 by qfx

Landslide mapping has evolved from expert-driven analysis to geospatial foundation models—leveraging self-supervised learning and fine-tuning—offering scalable, adaptable, and data-efficient solutions poised to disrupt the reinforcing cycle of climate-driven landslides and escalating community vulnerability through proactive risk management and transferable knowledge.

Geospatial foundation models demonstrate superior performance in landslide mapping, even with limited data and across diverse terrains.