Large-scale deployment of intelligent transportation to help achieve low-carbon and clean sustainable transportation

The Science of The Total Environment, Год журнала: 2024, Номер 949, С. 174724 - 174724

Опубликована: Июль 26, 2024

Язык: Английский

---

Trends of peroxyacetyl nitrate and its impact on ozone over 2018–2022 in urban atmosphere

npj Climate and Atmospheric Science, Год журнала: 2024, Номер 7(1)

Опубликована: Авг. 22, 2024

Abstract Peroxyacetyl nitrate (PAN) is an important photochemical product and affects ozone (O 3 ) formation in the troposphere. Yet, long-term observation of PAN remains scarce, limiting full understanding its impacts on pollution. Here, we observed from 2018 to 2022 urban Fuzhou, Southeastern China. We found that, contrast upward trend O , concentrations shown a significant decreasing at average rate −0.07 ppb/year. NO 2 CO, UVB, T contributed according Machine learning analyses, while effect -represented atmospheric oxidation capacity was fluctuating year year. Chemical box model revealed active PA production depletion Fuzhou. Thus, despite concentration, chemistry effectively promoted by rising RO x levels, leading increases 2.18%–58.4% net different years. Our results provide valuable insights into evolution pollution environments.

Язык: Английский

---

Developing Physiologically Compatible Electron Donors for Reductive Dechlorination by Dissimilatory Iron-Reducing Bacteria Using Machine Learning

ACS ES&T Engineering, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Язык: Английский

---

Time Series Analysis for the Adaptive Prediction of Total Phosphorus in the Yangtze River: A Machine Learning Approach

Water, Год журнала: 2025, Номер 17(4), С. 603 - 603

Опубликована: Фев. 19, 2025

Accurate prediction of total phosphorus (TP) in water quality is critical for monitoring ecosystem stability and eutrophication status. However, the distribution natural environmental data such as tends to undergo complex changes over time. Stable reliable results not only require a certain degree periodicity but also that TP model be highly adaptable random fluctuations distributional drifts data. Therefore, it challenge adapt models drift In this study, spatial temporal variations Yangtze River from 2019 2023 were described detail. Using mining techniques, time series analyzed generate forecast dataset focusing on fluctuations. By comparing various models, MTS-Mixers was finally selected experimental baseline different modes used prediction. The show after parameter adjustment, can achieve high accuracy (MAE: 0.145; MSE: 0.277), which guarantee at 20 steps. These research comprehensively reliably predicted provided effective methods tools management. They provide scientific basis protection improvement Basin help formulation implementation relevant policies promote sustainable development environment. addition, study confirms applicability machine learning hydrological responding changes.

Язык: Английский

---

Multi-year (2015-2023) trend and key factors of bioaerosols in urban atmosphere: A case study in Xi’an

Atmospheric Environment, Год журнала: 2025, Номер unknown, С. 121258 - 121258

Опубликована: Апрель 1, 2025

Язык: Английский

---

Machine learning-based prediction of non-aeration linear alkylbenzene sulfonate mineralization in an oxygenic microalgal-bacteria biofilm

Bioresource Technology, Год журнала: 2024, Номер 419, С. 132028 - 132028

Опубликована: Дек. 28, 2024

Язык: Английский

---

Mechanistic and data-driven perspectives on plant uptake of organic pollutants

The Science of The Total Environment, Год журнала: 2024, Номер 929, С. 172415 - 172415

Опубликована: Апрель 15, 2024

Язык: Английский

---

Unveiling the Spatial Distribution and Temporal Trends of Total Phosphorus in the Yangtze River: Towards a Predictive Time-Series Modeling for Environmental Management

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Дек. 25, 2024

The accurate prediction of total phosphorus in water quality is crucial for monitoring ecosystem stability and eutrophication status. However, the distribution natural environmental data such as (TP) often undergoes complex changes over time. Stable reliable predictive outcomes not only necessitate a degree periodicity within data, but also require that TP models exhibit strong adaptability to random fluctuations drifts data. Therefore, adapting accommodate presents challenge. This study provides detailed description spatiotemporal variations Yangtze River from 2019 2023. Utilizing cleaning mining techniques, time series were analyzed generate dataset, with particular emphasis on investigating fluctuations. By comparing various forecasting models, MTS-Mixers was ultimately selected experimental baseline model, different modes employed prediction. results demonstrate model maintains relatively high accuracy 20 steps. research findings offer comprehensive River, provide effective methods tools management. They serve scientific basis protection improvement Basin, facilitating formulation implementation relevant policies advancing sustainable development environment. Furthermore, confirms applicability machine learning hydrological forecasting, which can be utilized addressing changes. Future directions include ensuring critical exploring time-domain sub-band reconstruction better understand frequency characteristics revealing hidden information features.

Язык: Английский

---

长三角典型城市不同通勤方式的超细颗粒物暴露观测研究

Chinese Science Bulletin (Chinese Version), Год журнала: 2024, Номер unknown

Опубликована: Авг. 1, 2024

---