Advanced Torrential Loss Function for Precipitation Forecasting

Machine learning models often reflect biases found in their training data, resulting in unfair treatment of minority groups. While various bias mitigation techniques exist, they typically involve utility costs and require organizational support. This article introduces the concept of Algorithmic Collective Action, where end-users from minority groups can collaboratively relabel their data to promote fairness without changing the firm's training process. Three model-agnostic methods for effective relabeling are proposed and validated on real-world datasets, demonstrating that a minority subgroup can significantly reduce unfairness with minimal impact on prediction error.

Software aging is a phenomenon that affects long-running systems, resulting in gradual performance degradation and an increased risk of failures. To address this issue, a new adaptive approach utilizing machine learning for software aging detection in dynamic workload environments has been proposed. This study compares static models with adaptive models, specifically the Drift Detection Method (DDM) and Adaptive Windowing (ADWIN). Experiments demonstrate that while static models experience significant performance drops with unseen workloads, the adaptive model with ADWIN maintains high accuracy, achieving an F1-Score above 0.93.

The article introduces SaTformer, a novel video transformer model designed for precipitation forecasting. Traditional numerical weather prediction models face significant limitations, particularly in computational demands and performance at short lead times. SaTformer aims to overcome these challenges by leveraging AI techniques to enhance real-time flood guidance and improve the accuracy of weather forecasts.

The paper titled 'Power Ensemble Aggregation for Improved Extreme Event AI Prediction' addresses the challenge of predicting climate extreme events, particularly heat waves, using machine learning. It frames the prediction as a classification problem, aiming to determine if surface air temperature will exceed a specific local quantile. The study finds that using a power mean to aggregate ensemble predictions significantly enhances prediction accuracy compared to traditional methods, especially for higher quantile thresholds.

A new design for an optical Echo State Network (ESN) has been proposed, enhancing reservoir computing capabilities. This innovative architecture allows for flexible optical matrix multiplication and nonlinear activation, utilizing the nonlinear properties of stimulated Brillouin scattering (SBS). The approach promises reduced computational overhead and energy consumption compared to traditional methods, with simulations demonstrating strong memory capacity and processing capabilities, making it suitable for various machine learning applications.

SpiderGen is a new workflow that utilizes large language models (LLMs) to enhance Life Cycle Assessments (LCAs) for consumer products. The tool aims to estimate the environmental impact of goods by integrating traditional LCA methodologies with the reasoning capabilities of LLMs. Initial evaluations indicate that SpiderGen generates accurate LCA process information, with a performance score of 62%. This innovation is significant as it addresses the pressing issue of greenhouse gas emissions linked to product life cycles.

The paper titled 'destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity' discusses advancements in machine learning and neural networks, particularly in natural language processing. It highlights the vulnerabilities of machine learning models and proposes a novel adversarial attack strategy that generates ambiguous inputs to confuse these models. The research aims to enhance the robustness of machine learning systems by developing adversarial instances with maximum perplexity.

Machine Learning (ML) models are increasingly used for credit risk evaluation, with their effectiveness dependent on data quality. This research investigates the impact of data quality issues such as missing values, noisy attributes, outliers, and label errors on the predictive accuracy of ML models. Using an open-source dataset, the study assesses the robustness of ten commonly used models, including Random Forest, SVM, and Logistic Regression, revealing significant differences in model performance based on data degradation.