Published: Jan. 1, 2024
Language: Английский
Science Advances, Journal Year: 2025, Volume and Issue: 11(14)
Published: April 2, 2025
Atlantic and Benguela Niño events substantially affect the tropical region, with far-reaching consequences on local marine ecosystems, African climates, El Southern Oscillation. While accurate forecasts of these are invaluable, state-of-the-art dynamic forecasting systems have shown limited predictive capabilities. Thus, extent to which variability is predictable remains an open question. This study explores potential deep learning in this context. Using a simple convolutional neural network architecture, we show that Atlantic/Benguela Niños can be predicted up 3 4 months ahead. Our model excels peak-season remarkable accuracy extending lead time 5 months. Detailed analysis reveals our model’s ability exploit known physical precursors, such as long-wave ocean dynamics, for predictions events. challenges perception unpredictable highlights learning’s advance understanding critical climate
Language: Английский
Citations
2
Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 117650 - 117650
Published: April 1, 2025
Language: Английский
Citations
0
Published: Aug. 27, 2024
Road safety and the effectiveness of transportation system as a whole are significantly impacted by driver comfort. surface quality can play significant part in driver’s comfort experienced on roads any country. This study employs Random Forest technique to examine association between road roughness drivers' during long-distance driving. Using Forest, dependable machine learning that handle big datasets detect nonlinear correlations, this work aims shed light complex dynamics conditions 1,048,576 rows data from MIRANDA, an application developed at University Gustave Eiffel, were used collected probe vehicle. The includes International Roughness Index (IRI). IRI thresholds offer simple method for assessing irregularity. While highlighting how uneven uncomfortable is, research's findings (Road Roughness: SD – 0.73; Driver's Comfort: - Mean, 10.01, 0.64) also contribute standardization condition evaluation maintenance communication. finding is anticipated aid development strategies improving welfare long-haul drivers fixing infrastructure comply with standard index, ultimately leading creation more efficient sustainable systems.
Language: Английский
Citations
1
Transportation Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 100283 - 100283
Published: Oct. 1, 2024
Language: Английский
Citations
1
Sensors, Journal Year: 2024, Volume and Issue: 24(18), P. 6115 - 6115
Published: Sept. 21, 2024
Global trade depends on long-haul transportation, yet comfort for drivers lengthy trips is sometimes neglected. Rough roads have a major negative influence driver and increase the risk of weariness, distracted driving, accidents. Using Random Forest regression, machine learning technique well-suited to examining big datasets nonlinear relationships, this study examines relationship between road roughness comfort. MIRANDA mobile application, data were gathered from 1,048,576 rows, including vehicle acceleration values International Roughness Index (IRI). The Support Vector Regression (SVR) XGBoost models used comparative analysis. was preferred because its ability be deployed in real time use less memory, even if performed better terms training prediction accuracy. findings showed significant discomfort roughness, with rougher resulting increased vertical lower levels (Road Roughness: SD—0.73; Driver’s Comfort: Mean—10.01, SD—0.64). This highlights how crucial it provide smooth surfaces maintenance order safety, lessen promote welfare. These results offer information transportation authorities policymakers help them make data-driven decisions that enhance efficiency conditions.
Language: Английский
Citations
0
Published: Jan. 1, 2024
Language: Английский
Citations
0