Time-Series Data-Driven PM2.5 Forecasting: From Theoretical Framework to Empirical Analysis

Atmosphere, Journal Year: 2025, Volume and Issue: 16(3), P. 292 - 292

Published: Feb. 28, 2025

PM2.5 in air pollution poses a significant threat to public health and the ecological environment. There is an urgent need develop accurate prediction models support decision-making reduce risks. This review comprehensively explores progress of concentration prediction, covering bibliometric trends, time series data characteristics, deep learning applications, future development directions. article obtained on 2327 journal articles published from 2014 2024 WOS database. Bibliometric analysis shows that research output growing rapidly, with China United States playing leading role, recent increasingly focusing data-driven methods such as learning. Key sources include ground monitoring, meteorological observations, remote sensing, socioeconomic activity data. Deep (including CNN, RNN, LSTM, Transformer) perform well capturing complex temporal dependencies. With its self-attention mechanism parallel processing capabilities, Transformer particularly outstanding addressing challenges long sequence modeling. Despite these advances, integration, model interpretability, computational cost remain. Emerging technologies meta-learning, graph neural networks, multi-scale modeling offer promising solutions while integrating into real-world applications smart city systems can enhance practical impact. provides informative guide for researchers novices, providing understanding cutting-edge methods, systematic paths. It aims promote robust efficient contribute global management protection efforts.

Language: Английский

Geographically Aware Air Quality Prediction Through CNN-LSTM-KAN Hybrid Modeling with Climatic and Topographic Differentiation

Atmosphere, Journal Year: 2025, Volume and Issue: 16(5), P. 513 - 513

Published: April 28, 2025

Air pollution poses a pressing global challenge, particularly in rapidly industrializing nations like China where deteriorating air quality critically endangers public health and sustainable development. To address the heterogeneous patterns of across diverse geographical climatic regions, this study proposes novel CNN-LSTM-KAN hybrid deep learning framework for high-precision Quality Index (AQI) time-series prediction. Through systematic analysis multi-city AQI datasets encompassing five representative Chinese metropolises—strategically selected to cover climate zones (subtropical temperate), gradients (coastal inland), topographical variations (plains mountains)—we established three principal methodological advancements. First, Shapiro–Wilk normality testing (p < 0.05) revealed non-Gaussian distribution characteristics observational data, providing statistical justification implementing Gaussian filtering-based noise suppression. Second, our multi-regional validation extended beyond conventional single-city approaches, demonstrating model generalizability distinct environmental contexts. Third, we innovatively integrated Kolmogorov–Arnold Networks (KANs) with attention mechanisms replace traditional fully connected layers, achieving enhanced feature weighting capacity. Comparative experiments demonstrated superior performance 23.6–59.6% reduction Root-Mean-Square Error (RMSE) relative baseline LSTM models, along consistent outperformance over CNN-LSTM hybrids. Cross-regional correlation analyses identified PM2.5/PM10 as dominant predictive factors. The developed exhibited robust generalization capabilities divisions (R2 = 0.92–0.99), establishing reliable decision-support platform regionally adaptive early-warning systems. This provides valuable insights addressing spatial heterogeneity modeling applications.

Language: Английский

From Wastewater to Sustainability: Tackling Heavy Metal Contamination in Agriculture with Conventional and AI Techniques

Chemistry Africa, Journal Year: 2025, Volume and Issue: unknown

Published: May 23, 2025

Language: Английский