Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model
Livestock farms are recognized sources of ammonia emissions, impacting nearby regions’ fine dust particle concentrations, though the full extent of this impact remains uncertain. Air dispersion models, commonly employed to estimate particulate matter (PM) levels, are heavily reliant on data quality,...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/12 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589113968033792 |
|---|---|
| author | Dohyeong Kim Heeseok Kim Minseon Hwang Yongchan Lee Choongki Min Sungwon Yoon Sungchul Seo |
| author_facet | Dohyeong Kim Heeseok Kim Minseon Hwang Yongchan Lee Choongki Min Sungwon Yoon Sungchul Seo |
| author_sort | Dohyeong Kim |
| collection | DOAJ |
| description | Livestock farms are recognized sources of ammonia emissions, impacting nearby regions’ fine dust particle concentrations, though the full extent of this impact remains uncertain. Air dispersion models, commonly employed to estimate particulate matter (PM) levels, are heavily reliant on data quality, resulting in varying levels of accuracy. This study compares the performance of both air dispersion models and spatiotemporal deep learning models in estimating PM concentrations in Republic of Korea’s livestock-farming areas. Hourly PM concentration data, alongside temperature, humidity, and air pressure, were collected from seven monitoring stations across the study area. Using a 200 m × 200 m prediction grid, forecasts were generated for both 1 h and 24 h intervals using the Graz Lagrangian model (GRAL) and a one-dimensional convolutional neural network combined with the long short-term memory algorithm (1DCNN-LSTM). Results highlight the potential of the deep learning model to enhance PM prediction, indicating its promise as an effective alternative or supplement to conventional air dispersion models, particularly in data-scarce areas such as those surrounding livestock farms. Gaining a comprehensive understanding and evaluating the advantages and disadvantages of each approach would offer valuable scientific insights for monitoring atmospheric pollution levels within a specific area. |
| format | Article |
| id | doaj-art-576c785c60274aea917a54cfcb74677f |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-576c785c60274aea917a54cfcb74677f2025-01-24T13:21:41ZengMDPI AGAtmosphere2073-44332024-12-011611210.3390/atmos16010012Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning ModelDohyeong Kim0Heeseok Kim1Minseon Hwang2Yongchan Lee3Choongki Min4Sungwon Yoon5Sungchul Seo6School of Economic, Political and Policy Sciences, University of Texas at Dallas, Dallas, TX 75080-3021, USADepartment of Nano, Chemical & Biological Engineering, College of Natural Science & Engineering, Seokyeong University, Seoul 06115, Republic of KoreaWaycen, Inc., Seoul 06009, Republic of KoreaDepartment of Environmental and Energy Engineering, Graduate School, Incheon National University, Inchoen 22012, Republic of KoreaWaycen, Inc., Seoul 06009, Republic of KoreaDepartment of Nano, Chemical & Biological Engineering, College of Natural Science & Engineering, Seokyeong University, Seoul 06115, Republic of KoreaDepartment of Nano, Chemical & Biological Engineering, College of Natural Science & Engineering, Seokyeong University, Seoul 06115, Republic of KoreaLivestock farms are recognized sources of ammonia emissions, impacting nearby regions’ fine dust particle concentrations, though the full extent of this impact remains uncertain. Air dispersion models, commonly employed to estimate particulate matter (PM) levels, are heavily reliant on data quality, resulting in varying levels of accuracy. This study compares the performance of both air dispersion models and spatiotemporal deep learning models in estimating PM concentrations in Republic of Korea’s livestock-farming areas. Hourly PM concentration data, alongside temperature, humidity, and air pressure, were collected from seven monitoring stations across the study area. Using a 200 m × 200 m prediction grid, forecasts were generated for both 1 h and 24 h intervals using the Graz Lagrangian model (GRAL) and a one-dimensional convolutional neural network combined with the long short-term memory algorithm (1DCNN-LSTM). Results highlight the potential of the deep learning model to enhance PM prediction, indicating its promise as an effective alternative or supplement to conventional air dispersion models, particularly in data-scarce areas such as those surrounding livestock farms. Gaining a comprehensive understanding and evaluating the advantages and disadvantages of each approach would offer valuable scientific insights for monitoring atmospheric pollution levels within a specific area.https://www.mdpi.com/2073-4433/16/1/12livestock-farming areasparticulate matterair dispersion modeldeep learningspatiotemporal prediction |
| spellingShingle | Dohyeong Kim Heeseok Kim Minseon Hwang Yongchan Lee Choongki Min Sungwon Yoon Sungchul Seo Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model Atmosphere livestock-farming areas particulate matter air dispersion model deep learning spatiotemporal prediction |
| title | Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model |
| title_full | Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model |
| title_fullStr | Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model |
| title_full_unstemmed | Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model |
| title_short | Enhancing Particulate Matter Estimation in Livestock-Farming Areas with a Spatiotemporal Deep Learning Model |
| title_sort | enhancing particulate matter estimation in livestock farming areas with a spatiotemporal deep learning model |
| topic | livestock-farming areas particulate matter air dispersion model deep learning spatiotemporal prediction |
| url | https://www.mdpi.com/2073-4433/16/1/12 |
| work_keys_str_mv | AT dohyeongkim enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT heeseokkim enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT minseonhwang enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT yongchanlee enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT choongkimin enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT sungwonyoon enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel AT sungchulseo enhancingparticulatematterestimationinlivestockfarmingareaswithaspatiotemporaldeeplearningmodel |