Prediction of particulate matter pollution using a long short-term memory model in Zhejiang Province, China DOI Creative Commons
Ahmad Hasnain, Muhammad Zaffar Hashmi, Uzair Aslam Bhatti

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

Abstract The quality of life in cities is impacted by air pollution, which one the most dangerous environmental problems that humans confront. Strategies for evaluating and alerting public to expected levels pollution can be developed using particulate matter (PM) forecasting models. Precise assessments pollutant concentrations forecasts are essential components evaluations serve as cornerstone right strategic decisions. In current study, Long Short-Term Memory (LSTM) model, a deep learning approach, was employed forecast PM along with meteorological variables Zhejiang Province, China. performance model evaluated based on cross-validation (CV), root mean squared error (RMSE), absolute (MAE) determination coefficient R2. According our findings, performed well predicting PM10 (R2 = 0.76, RMSE 11.51 µg/m3 MAE 8.74 µg/m3) PM2.5 0.74, 7.06 5.41 concentrations. Moreover, from 2019 2022, there downward trend concentrations, but Province saw an increase 2023. These results reliable motivate more efforts reduce future.

Language: Английский

Innovative Deep Learning Image Technologies DOI
Muhammad Akram, Sibghat Ullah Bazai, Muhammad Sulaman

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 145 - 180

Published: March 7, 2025

The chapter gives an overview of the applications deep learning and image processing in different industries medicine, automobiles, entertainment, security. Multiple advanced techniques such as CNN, GAN, ViT that have become handy analysis processing. From medical diagnostics to autonomous vehicles, environmental monitoring, surveillance, its show impact on accuracy efficiency. It also discusses critical ethical issues, data privacy, model biases, energy consumption, points out some possible solutions reduce those effects. In general, this contribution provides a advances related by potential for further innovative developments wide range applications.

Language: Английский

Citations

0
Deep Learning Techniques for Image Segmentation and Data Annotation DOI

Muhammad Shoaib,

Ali Raza, Sibghat Ullah Bazai

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 63 - 94

Published: March 7, 2025

This chapter explores the integration of deep learning techniques in image segmentation, emphasizing state-of-the-art architectures, such as FCN, U-Net, and Vision Transformers, that enable precise efficient segmentation for a range applications. It discusses significance data annotation training models, highlighting methods like active learning, semi-supervised automated annotation. The also addresses key challenges, including limited labeled data, model size constraints, performance on edge devices. Additionally, it covers diverse use cases across fields medical imaging, agriculture, civil. Finally, outlines emerging trends field, self-supervised federated development lightweight models real-time applications, offering insights into future potential impact segmentation.

Language: Английский

Citations

0
Analyzing meteorological factors for forecasting PM10 and PM2.5 levels: a comparison between MLR and MLP models DOI
Nastaran Talepour, Yaser Tahmasebi Birgani, Frank J. Kelly

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

Language: Английский

Citations

1
Spatial source, simulating improvement, and short-term health effect of high PM2.5 exposure during mutation event in the key urban agglomeration regions in China DOI
Xin Cheng, Jie Yu,

Die Su

et al.

Environmental Pollution, Journal Year: 2024, Volume and Issue: 359, P. 124738 - 124738

Published: Aug. 13, 2024

Language: Английский

Citations

0
Prediction of particulate matter pollution using a long short-term memory model in Zhejiang Province, China DOI Creative Commons
Ahmad Hasnain, Muhammad Zaffar Hashmi, Uzair Aslam Bhatti

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 3, 2024

Abstract The quality of life in cities is impacted by air pollution, which one the most dangerous environmental problems that humans confront. Strategies for evaluating and alerting public to expected levels pollution can be developed using particulate matter (PM) forecasting models. Precise assessments pollutant concentrations forecasts are essential components evaluations serve as cornerstone right strategic decisions. In current study, Long Short-Term Memory (LSTM) model, a deep learning approach, was employed forecast PM along with meteorological variables Zhejiang Province, China. performance model evaluated based on cross-validation (CV), root mean squared error (RMSE), absolute (MAE) determination coefficient R2. According our findings, performed well predicting PM10 (R2 = 0.76, RMSE 11.51 µg/m3 MAE 8.74 µg/m3) PM2.5 0.74, 7.06 5.41 concentrations. Moreover, from 2019 2022, there downward trend concentrations, but Province saw an increase 2023. These results reliable motivate more efforts reduce future.

Language: Английский

Citations

0