Comprehensive 24-Hour Ground-Level Ozone Monitoring: Leveraging Machine Learning for Full-Coverage Estimation in East Asia

Journal of Hazardous Materials, Journal Year: 2025, Volume and Issue: 488, P. 137369 - 137369

Published: Feb. 1, 2025

Language: Английский

---

Data driven modeling of TiO2 PVP nanofiber diameter using LSTM and regression for enhanced functional performance

Deleted Journal, Journal Year: 2025, Volume and Issue: 7(4)

Published: April 11, 2025

Abstract The prospective utilization of electrospun nanofibers across diverse fields has elicited substantial scientific attention. Nevertheless, managing their diameter remains problematic due to the intricate interactions among electrospinning variables. This research explores application Long Short-Term Memory (LSTM) networks and multiple regression models forecast diameters Titanium Dioxide (TiO₂) Polyvinyl pyrrolidone (PVP) nanofibers, facilitating improved process regulation enhancement. TiO₂ + PVP were fabricated under conditions, including changes in applied voltage, solution concentration, distance between tip collector. acquired data underwent analysis using LSTM assess predictive capabilities. outcomes revealed that both approaches effectively estimated nanofiber diameters; however, model surpassed with a lower error rate 0.077% compared 0.305%. indicates while captures nonlinear relationships, conventional yield more precise predictions this scenario. These findings underscore potential machine learning advancing technology by minimizing trial-and-error experiments boosting production efficiency. incorporation artificial intelligence-driven modeling into sets stage for accurate control over fiber morphology, resulting enhanced material properties expanded applications biomedical, environmental, energy sectors.

Language: Английский

---

A Novel Flexible Geographically Weighted Neural Network for High-Precision PM2.5 Mapping across the Contiguous United States

ISPRS International Journal of Geo-Information, Journal Year: 2024, Volume and Issue: 13(7), P. 217 - 217

Published: June 22, 2024

Air quality degradation has triggered a large-scale public health crisis globally. Existing machine learning techniques have been used to attempt the remote sensing estimates of PM2.5. However, many models ignore spatial non-stationarity predictive variables. To address this issue, study introduces Flexible Geographically Weighted Neural Network (FGWNN) estimate PM2.5 based on multi-source data. FGWNN incorporates Geographical Neuron (FGN) and Activation Function (GWAF) within framework Artificial (ANN) capture intricate non-stationary relationships among A robust air estimation model was constructed using data Aerosol Optical Depth (AOD), Normalized Difference Vegetation Index (NDVI), Temperature (TMP), Specific Humidity (SPFH), Wind Speed (WIND), Terrain Elevation (HGT) as inputs, Ground-Based observation. The results indicated that successfully generates with 2.5 km resolution for contiguous United States (CONUS) in 2022. It exhibits higher regression accuracy compared traditional ANN Regression (GWR) models. holds potential applications high-precision high-resolution scenarios.

Language: Английский

---

Spatial Distribution of Multiple Atmospheric Pollutants in China from 2015 to 2020

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(24), P. 5705 - 5705

Published: Dec. 12, 2023

The pursuit of higher-resolution and more reliable spatial distribution simulation results for air pollutants is important to human health environmental safety. However, the lack high-resolution remote sensing retrieval parameters gaseous (sulfur dioxide ozone) limits effect a 1 km resolution. To address this issue, we sequentially generated optimized distributions near-surface PM2.5, SO2, ozone at resolution in China through two approaches. First, employed sampling, random ID, parameter convolution methods jointly optimize tree-based machine-learning gradient-boosting framework, LightGBM, improve performance pollutant simulations. Second, simulated used PM2.5 result simulate then SO2 ozone. We improved stability km-resolution products proposed sequence multiple-pollutant cross-validation (CV) sample yielded an R2 0.90 RMSE 9.62 µg∙m−3 0.92 3.9 0.94 5.9 ozone, which are values better than those previous related studies. In addition, tested reliability analysis importance analysis. models multiple-air-pollutant (MuAP) by optimization study great value long-term, large-scale, regional-scale pollution monitoring predictions, as well population assessments.

Language: Английский

---

High-Accuracy Pm2.5 Retrieval Based on Satellite Remote Sensing and Hierarchical Machine Learning Model

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

---

Estimation of PM2.5 concentrations in North China with high spatiotemporal resolution using the ERA5 dataset and machine learning models

Advances in Space Research, Journal Year: 2024, Volume and Issue: 74(2), P. 711 - 726

Published: April 24, 2024

Language: Английский

---

Estimating 1-km PM2.5 concentrations based on a novel spatiotemporal parallel network STMSPNet in the Beijing-Tianjin-Hebei region

Atmospheric Environment, Journal Year: 2024, Volume and Issue: 338, P. 120796 - 120796

Published: Sept. 5, 2024

Language: Английский

---

High-accuracy full-coverage PM _2.5 retrieval from 2014 to 2023 over China based on satellite remote sensing and hierarchical deep learning model

International Journal of Digital Earth, Journal Year: 2024, Volume and Issue: 17(1)

Published: Sept. 23, 2024

Language: Английский

---

Spatiotemporal Estimation of Black Carbon Concentration in Tehran Using Aerosol Optical Depth Remote Sensing Data and Meteorological Parameters: Health Risk Assessment and Relationship with Green Spaces

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 117, P. 105986 - 105986

Published: Nov. 14, 2024

Language: Английский

---