Two new research papers explore advanced time-series forecasting methods for distinct domains. One paper introduces an event-based approach for predicting vineyard disease risk, utilizing environmental data and comparing machine learning models like XGBoost and LSTMs. The other paper proposes a Bayesian framework with a boosting mechanism to forecast oncology demand trends, outperforming traditional methods like ARIMA and LSTMs on real-world data. AI
Summary written by gemini-2.5-flash-lite from 3 sources. How we write summaries →
IMPACT These papers highlight advancements in applying machine learning to specialized time-series prediction tasks, potentially improving accuracy in agriculture and healthcare.
RANK_REASON Two distinct academic papers published on arXiv detailing novel machine learning approaches for time-series forecasting.