Comparison of extreme gradient boosting, deep learning, and self-organizing map methods in predicting groundwater depth

Environmental Earth Sciences, Journal Year: 2025, Volume and Issue: 84(7)

Published: March 21, 2025

Language: Английский

---

Comparative analysis of daily global solar radiation prediction using deep learning models inputted with stochastic variables

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 28, 2025

Photovoltaic power plant outputs depend on the daily global solar radiation (DGSR). The main issue with DGSR data is its lack of precision. potential unavailability for several sites can be attributed to high cost measuring instruments and intermittent nature time series due equipment malfunctions. Therefore, prediction research crucial nowadays produce photovoltaic power. Different artificial neural network (ANN) models will give different predictions varying levels accuracy, so it essential compare ANN model inputs various sets meteorological stochastic variables. In this study, radial basis function (RBFNN), long short-term memory (LSTMNN), modular (MNN), transformer (TM) are developed investigate performances these algorithms using combinations These employ five variables: wind speed, relative humidity, minimum, maximum, average temperatures. mean absolute error input variables as average, minimum temperatures 1.98. outperform traditional in predictive accuracy.

Language: Английский

---

A Fuzzy-Neural Model for Personalized Learning Recommendations Grounded in Experiential Learning Theory

Information, Journal Year: 2025, Volume and Issue: 16(5), P. 339 - 339

Published: April 23, 2025

Personalized learning is a defining characteristic of current education, with flexible and adaptable experiences that respond to individual learners’ requirements approaches learning. Traditional implementations educational theories—such as Kolb’s Experiential Learning Theory—often follow rule-based approaches, offering predefined structures but lacking adaptability dynamically changing learner behavior. In contrast, AI-based such artificial neural networks (ANNs) have high lack interpretability. this work, new model, fuzzy-ANN developed combines fuzzy logic ANNs make recommendations for activities in the process, overcoming model weaknesses. first stage, used map dimensions style onto continuous membership values, providing easier-to-interpret representation preferred These weights are then processed an ANN, enabling refinement improvement through analysis patterns To adapt develop over time, Weighted Sum Model (WSM) used, combining activity trends real-time feedback updating proposed recommendations. Experimental evaluation environment shows effectively generates personalized learners, harmony trends.

Language: Английский

---

Improving the Accuracy of Groundwater Level Forecasting by Coupling Ensemble Machine Learning Model and Coronavirus Herd Immunity Optimizer

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: May 3, 2025

Language: Английский

---