Overview: Random Forest Algorithm for PM2.5 Estimation Based on Remote Sensing
Tinjauan: Algoritma Random Forest untuk Estimasi PM2.5 Berbasis Pengindraan Jauh
Abstract
Studi ini merangkum penelitian tentang estimasi PM2.5 menggunakan algoritme pembelajaran mesin random forest (RF), penginderaan jauh, dan keduanya. Tujuan dari tinjauan ini adalah menyajikan studi yang komprehensif untuk memfasilitasi dan menentukan batasan, luas dan kedalaman pengetahuan yang dieksplorasi untuk memperkirakan konsentrasi PM2.5 di masa depan menggunakan RF dan pengindraan jauh. PM2.5 merupakan parameter lingkungan atmosfer yang penting, terutama karena dampaknya terhadap kesehatan manusia dan lingkungan. Terlepas dari skala spasial-temporal, perkiraan PM2.5 yang akurat penting untuk memahami dan menanggapi berbagai efek buruk dari polusi udara. Oleh karena itu, metode penginderaan jauh dan pembelajaran mesin dikembangkan untuk mendapatkan estimasi PM2.5 resolusi tinggi dan mengurangi kesalahan penilaian yang disebabkan oleh dislokasi spasial. Sejak penggunaan pertama jaringan saraf (NN) untuk mempelajari hubungan kompleks AOD-PM2.5, lebih dari 40 artikel terkait ML telah diterbitkan dalam dekade terakhir, dan lebih dari 90% di antaranya telah diterbitkan dalam lima tahun dan 75% dalam tiga tahun terakhir. Metode validasi yang mempertimbangkan pola spasial dalam validasi model ML mengungkapkan bahwa RF dan BPNN adalah yang paling populer digunakan.
Downloads
References
W. Chen et al., “Estimating PM2.5 with high-resolution 1-km AOD data and an improved machine learning model over Shenzhen, China,” Science of the Total Environment, vol. 746, p. 141093, 2020, doi: 10.1016/j.scitotenv.2020.141093.
J. Wei et al., “Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach,” Remote Sens Environ, vol. 231, no. April, 2019, doi: 10.1016/j.rse.2019.111221.
J. Chen, J. Yin, L. Zang, T. Zhang, and M. Zhao, “Stacking machine learning model for estimating hourly PM2.5 in China based on Himawari 8 aerosol optical depth data,” Science of the Total Environment, vol. 697, p. 134021, 2019, doi: 10.1016/j.scitotenv.2019.134021.
X. Meng, J. L. Hand, B. A. Schichtel, and Y. Liu, “Space-time trends of PM2.5 constituents in the conterminous United States estimated by a machine learning approach, 2005–2015,” Environmental International, vol. 121, no. August, pp. 1137–1147, 2018, doi: 10.1016/j.envint.2018.10.029.
M. D. Yazdi et al., “Predicting fine particulate matter (PM2.5) in the greater london area: An ensemble approach using machine learning methods,” Remote Sens (Basel), vol. 12, no. 6, 2020, doi: 10.3390/rs12060914.
Y. A. Aliyu and J. O. Botai, “Appraising city-scale pollution monitoring capabilities of multi-satellite datasets using portable pollutant monitors,” Atmos Environ, vol. 179, no. November 2017, pp. 239–249, 2018, doi: 10.1016/j.atmosenv.2018.02.034.
ditppu-KLHK, “Kondisi Kualitas Udara Di Beberapa Kota Besar Tahun 2019,” Direktorat Pengendalian Pencemaran Udara- KLHK, 2020. https://ditppu.menlhk.go.id/portal/kontak-kami/?token=E7fKNFZqQzWdtteaDKXW (accessed Feb. 06, 2022).
J. L. Hand, B. a Schichtel, W. C. Malm, M. Pitchford, and N. H. Frank, “Journal of Geophysical Research : Atmospheres aerosols across the United States,” Journal of Geophysical Research : Atmospheres, vol. 119, pp. 832–849, 2014, doi: 10.1002/2014JD022328.Received.
U.S. EPA, “The Particle Pollution Report Current Understanding of Air Quality and Emissions through 2003,” Research Triangle Park, NC: U.S. Environmental Protection Agency, Office of Air Quality Planning and standards; Emissions, Monitoring and Analysis Division, p. 28, 2004.
L. Yang, C. Li, and X. Tang, “The Impact of PM2.5 on the Host Defense of Respiratory System,” Front Cell Dev Biol, vol. 8, no. March, pp. 1–9, 2020, doi: 10.3389/fcell.2020.00091.
T. Schikowski and H. Altuğ, “The role of air pollution in cognitive impairment and decline,” Neurochem Int, vol. 136, no. February, p. 104708, 2020, doi: 10.1016/j.neuint.2020.104708.
Greenpeace International, “The Final Countdown: Now or never to reform the palm oil industry,” Greenpeace, 2018. https://www.greenpeace.org/international/publication/18455/the-final-countdown-forests-indonesia-palm-oil/ (accessed Feb. 20, 2020).
L. Syaufina, “Forest and land fires in Indonesia: Assessment and mitigation,” in Integrating Disaster Science and Management: Global Case Studies in Mitigation and Recovery, Bogor: Elsevier Inc., 2018, pp. 109–121. doi: 10.1016/B978-0-12-812056-9.00008-7.
M. Gross, “Learning to live with landscape fires,” Current Biology, vol. 25, no. 16, pp. R693–R696, 2015, doi: 10.1016/j.cub.2015.07.069.
J.-S. Tan-Soo and S. K. Pattanayak, “Seeking natural capital projects: Forest fires, haze, and early-life exposure in Indonesia,” Proceedings of the National Academy of Sciences, vol. 116, no. 12, pp. 5239 LP – 5245, Mar. 2019, doi: 10.1073/pnas.1802876116.
K. J. Bergen, P. A. Johnson, M. V. De Hoop, and G. C. Beroza, “Machine learning for data-driven discovery in solid Earth geoscience,” Science (1979), vol. 363, no. 6433, 2019, doi: 10.1126/science.aau0323.
D. J. Lary, A. H. Alavi, A. H. Gandomi, and A. L. Walker, “Machine learning in geosciences and remote sensing,” Geoscience Frontiers, vol. 7, no. 1, pp. 3–10, 2016, doi: 10.1016/j.gsf.2015.07.003.
P. Gupta and S. A. Christopher, “Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: 2. A neural network approach,” Journal of Geophysical Research Atmospheres, vol. 114, no. 20, pp. 1–14, 2009, doi: 10.1029/2008JD011497.
Y. Duan, J. S. Edwards, and Y. K. Dwivedi, “Artificial intelligence for decision making in the era of Big Data – evolution, challenges and research agenda,” Int J Inf Manage, vol. 48, no. January, pp. 63–71, 2019, doi: 10.1016/j.ijinfomgt.2019.01.021.
M. Hutson, “AI Glossary: Artificial intelligence, in so many words,” Science (New York, N.Y.), vol. 357, no. 6346, p. 19, 2017. doi: 10.1126/science.357.6346.19.
Q. Di et al., “Assessing NO(2) Concentration and Model Uncertainty with High Spatiotemporal Resolution across the Contiguous United States Using Ensemble Model Averaging.,” Environ Sci Technol, vol. 54, no. 3, pp. 1372–1384, Feb. 2020, doi: 10.1021/acs.est.9b03358.
Q. Di et al., “An ensemble-based model of PM(2.5) concentration across the contiguous United States with high spatiotemporal resolution.,” Environ Int, vol. 130, p. 104909, Sep. 2019, doi: 10.1016/j.envint.2019.104909.
L. Breiman, “Random Forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
A. Liaw and M. Wiener, “Classification and Regression by randomForest,” R News, vol. 2, no. 3, pp. 18–22, 2002.
X. Hu et al., “Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach,” Environ Sci Technol, vol. 51, no. 12, pp. 6936–6944, Jun. 2017, doi: 10.1021/acs.est.7b01210.
J. Liu, F. Weng, and Z. Li, “Satellite-based PM2.5 estimation directly from reflectance at the top of the atmosphere using a machine learning algorithm,” Atmos Environ, vol. 208, pp. 113–122, 2019, doi: https://doi.org/10.1016/j.atmosenv.2019.04.002.
H. Bai, Y. Shi, M. Seong, W. Gao, and Y. Li, “Influence of Spatial Resolution on Satellite-Based PM2.5 Estimation: Implications for Health Assessment,” Remote Sens (Basel), vol. 14, no. 12, 2022, doi: 10.3390/rs14122933.
Y. Xiao and M. Watson, “Guidance on Conducting a Systematic Literature Review,” J Plan Educ Res, vol. 39, no. 1, pp. 93–112, 2019, doi: 10.1177/0739456X17723971.
K. N. Liou, An Introduction to Atmospheric Radiation, 2nd ed. San Diego: Academic Press, 2002.
X. Q. Yap and M. Hashim, “A robust calibration approach for PM10 prediction from MODIS aerosol optical depth,” Atmos Chem Phys, vol. 13, no. 6, pp. 3517–3526, 2013, doi: 10.5194/acp-13-3517-2013.
K. Schäfer, A. Harbusch, S. Emeis, P. Koepke, and M. Wiegner, “Correlation of aerosol mass near the ground with aerosol optical depth during two seasons in Munich,” Atmos Environ, vol. 42, no. 18, pp. 4036–4046, 2008, doi: 10.1016/j.atmosenv.2008.01.060.
NEO, “Aerosol Optical Depth,” NASA EARTH OBSERVATION, 2020. https://neo.sci.gsfc.nasa.gov/view.php?datasetId=MODAL2_M_AER_OD (accessed Jul. 08, 2020).
L. Filip and S. Stefan, “Study of the correlation between the near-ground PM10 mass concentration and the aerosol optical depth,” J Atmos Sol Terr Phys, vol. 73, no. 13, pp. 1883–1889, 2011, doi: 10.1016/j.jastp.2011.04.027.
C. Zheng et al., “Analysis of influential factors for the relationship between PM$_{2.5}$ and AOD in Beijing,” Atmos Chem Phys, vol. 17, no. 21, pp. 13473–13489, 2017, doi: 10.5194/acp-17-13473-2017.
B. Chen et al., “An interpretable self-adaptive deep neural network for estimating daily spatially-continuous PM2.5 concentrations across China,” Science of the Total Environment, vol. 768, p. 144724, 2021, doi: 10.1016/j.scitotenv.2020.144724.
A. Shtein et al., “Estimating Daily PM2.5 and PM10 over Italy Using an Ensemble Model,” Environ Sci Technol, vol. 54, no. 1, pp. 120–128, Jan. 2020, doi: 10.1021/acs.est.9b04279.
G. Zhang et al., “A framework to predict high-resolution spatiotemporal pm2.5 distributions using a deep-learning model: A case study of shijiazhuang, china,” Remote Sens (Basel), vol. 12, no. 17, pp. 1–33, 2020, doi: 10.3390/rs12172825.
Z. Wang, Y. Zhou, R. Zhao, N. Wang, A. Biswas, and Z. Shi, “High-resolution prediction of the spatial distribution of PM2.5 concentrations in China using a long short-term memory model,” J Clean Prod, vol. 297, p. 126493, 2021, doi: 10.1016/j.jclepro.2021.126493.
F. Liang et al., “MAIAC-based long-term spatiotemporal trends of PM2.5 in Beijing, China,” Science of The Total Environment, vol. 616–617, pp. 1589–1598, 2018, doi: https://doi.org/10.1016/j.scitotenv.2017.10.155.
R. Schneider et al., “A Satellite-Based Spatio-Temporal Machine Learning Model to Reconstruct Daily PM2.5 Concentrations across Great Britain,” Remote Sens (Basel), vol. 12, no. 22, 2020, doi: 10.3390/rs12223803.
X. Li, Y. Li, Q. Ma, and S. Wang, “Random Forest Model for PM2.5 Concentration in China Using Himawari-8 Hourly AOD Product,” in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021, pp. 1935–1938. doi: 10.1109/IGARSS47720.2021.9554364.
J. Li et al., “Estimation of ambient PM2.5 in Iraq and Kuwait from 2001 to 2018 using machine learning and remote sensing,” Environ Int, vol. 151, no. January, p. 106445, 2021, doi: 10.1016/j.envint.2021.106445.
G. Geng, X. Meng, K. He, and Y. Liu, “Random forest models for PM2.5 speciation concentrations using MISR fractional AODs,” Environmental Research Letters, vol. 15, no. 3, 2020, doi: 10.1088/1748-9326/ab76df.
B. Guo et al., “Estimating PM2.5 concentrations via random forest method using satellite, auxiliary, and ground-level station dataset at multiple temporal scales across China in 2017,” Science of the Total Environment, vol. 778, 2021, doi: 10.1016/j.scitotenv.2021.146288.
K. Huang et al., “Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain,” Environmental Pollution, vol. 242, pp. 675–683, 2018, doi: 10.1016/j.envpol.2018.07.016.
T. Li, H. Shen, C. Zeng, and Q. Yuan, “A Validation Approach Considering the Uneven Distribution of Ground Stations for Satellite-Based PM2.5 Estimation,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 13, pp. 1312–1321, 2020, doi: 10.1109/JSTARS.2020.2977668.
K. Gui et al., “Construction of a virtual PM2.5 observation network in China based on high-density surface meteorological observations using the Extreme Gradient Boosting model,” Environ Int, vol. 141, p. 105801, 2020, doi: https://doi.org/10.1016/j.envint.2020.105801.
Y. Ding, Z. Chen, W. Lu, and X. Wang, “A CatBoost approach with wavelet decomposition to improve satellite-derived high-resolution PM2.5 estimates in Beijing-Tianjin-Hebei,” Atmos Environ, vol. 249, no. August 2020, p. 118212, 2021, doi: 10.1016/j.atmosenv.2021.118212.
R. B. A. Koelemeijer, C. D. Homan, and J. Matthijsen, “Comparison of spatial and temporal variations of aerosol optical thickness and particulate matter over Europe,” Atmos Environ, vol. 40, no. 27, pp. 5304–5315, 2006, doi: https://doi.org/10.1016/j.atmosenv.2006.04.044.
Y. Liu, M. Franklin, R. Kahn, and P. Koutrakis, “Using aerosol optical thickness to predict ground-level PM2.5 concentrations in the St. Louis area: A comparison between MISR and MODIS,” Remote Sens Environ, vol. 107, no. 1–2, pp. 33–44, 2007, doi: 10.1016/j.rse.2006.05.022.
R. Zhang et al., “A nonparametric approach to filling gaps in satellite-retrieved aerosol optical depth for estimating ambient PM2.5 levels,” Environmental Pollution, vol. 243, pp. 998–1007, 2018, doi: https://doi.org/10.1016/j.envpol.2018.09.052.
L. Han, J. Zhao, Y. Gao, Z. Gu, K. Xin, and J. Zhang, “Spatial distribution characteristics of PM2.5 and PM10 in Xi’an City predicted by land use regression models,” Sustain Cities Soc, vol. 61, p. 102329, 2020, doi: https://doi.org/10.1016/j.scs.2020.102329.
L. Yang, H. Xu, and Z. Jin, “Estimating ground-level PM2.5 over a coastal region of China using satellite AOD and a combined model,” J Clean Prod, vol. 227, pp. 472–482, 2019, doi: 10.1016/j.jclepro.2019.04.231.
C.-D. Wu et al., “Land-use regression with long-term satellite-based greenness index and culture-specific sources to model PM2.5 spatial-temporal variability,” Environmental Pollution, vol. 224, pp. 148–157, 2017, doi: https://doi.org/10.1016/j.envpol.2017.01.074.
J. Zhong et al., “Robust prediction of hourly PM2.5 from meteorological data using LightGBM,” Natl Sci Rev, vol. 8, no. 10, 2021, doi: 10.1093/nsr/nwaa307.
A. Mhawish et al., “Estimation of High-Resolution PM2.5over the Indo-Gangetic Plain by Fusion of Satellite Data, Meteorology, and Land Use Variables,” Environ Sci Technol, vol. 54, no. 13, pp. 7891–7900, 2020, doi: 10.1021/acs.est.0c01769.
Y. Miao, S. Liu, J. Guo, S. Huang, Y. Yan, and M. Lou, “Unraveling the relationships between boundary layer height and PM2.5 pollution in China based on four-year radiosonde measurements,” Environmental Pollution, vol. 243, pp. 1186–1195, 2018, doi: 10.1016/j.envpol.2018.09.070.
W. Qu, J. Wang, X. Zhang, L. Sheng, and W. Wang, Opposite seasonality of the aerosol optical depth and the surface particulate matter concentration over the north China Plain, vol. 127. Elsevier Ltd, 2016. doi: 10.1016/j.atmosenv.2015.11.061.
C. J. Paciorek, Y. Liu, H. Moreno-Macias, and S. Kondragunta, “Spatiotemporal associations between GOES aerosol optical depth retrievals and ground-level PM2.5,” Environ Sci Technol, vol. 42, no. 15, pp. 5800–5806, 2008, doi: 10.1021/es703181j.
Y. Liu, G. Cao, N. Zhao, K. Mulligan, and X. Ye, “Improve ground-level PM2.5 concentration mapping using a random forests-based geostatistical approach,” Environmental Pollution, vol. 235, pp. 272–282, 2018, doi: 10.1016/j.envpol.2017.12.070.
M. Zamani Joharestani, C. Cao, X. Ni, B. Bashir, and S. Talebiesfandarani, “PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data,” Atmosphere (Basel), vol. 10, no. 7, 2019, doi: 10.3390/atmos10070373.
X. Hu et al., “Estimating PM2 . 5 Concentrations in the Conterminous United States Using the Random Forest Approach Department of Environmental Health , Rollins School of Public Health , Emory University , Department of Biostatistics & Bioinformatics , Rollins School of,” Environ Sci Technol, pp. 1–29, 2017.
C. Brokamp, R. Jandarov, M. Hossain, and P. Ryan, “Predicting Daily Urban Fine Particulate Matter Concentrations Using a Random Forest Model,” Environ Sci Technol, vol. 52, no. 7, pp. 4173–4179, 2018, doi: 10.1021/acs.est.7b05381.
G. Geng, X. Meng, K. He, and Y. Liu, “Random forest models for PM2.5 speciation concentrations using MISR fractional AODs,” Environmental Research Letters, vol. 15, no. 3, p. 34056, 2020, doi: 10.1088/1748-9326/ab76df.
C. R. Jung, W. T. Chen, and S. F. Nakayama, “A national-scale 1-km resolution pm2.5 estimation model over japan using maiac aod and a two-stage random forest model,” Remote Sens (Basel), vol. 13, no. 18, 2021, doi: 10.3390/rs13183657.
C. Zhao et al., “Estimating the daily PM2.5 concentration in the Beijing-Tianjin-Hebei region using a random forest model with a 0.01° × 0.01° spatial resolution,” Environment International, vol. 134. 2020. doi: 10.1016/j.envint.2019.105297.
S. Park et al., “Estimation of spatially continuous daytime particulate matter concentrations under all sky conditions through the synergistic use of satellite-based AOD and numerical models,” Science of The Total Environment, vol. 713, p. 136516, 2020, doi: https://doi.org/10.1016/j.scitotenv.2020.136516.
W. Xue et al., “Inferring near-surface pm2.5 concentrations from the viirs deep blue aerosol product in china: A spatiotemporally weighted random forest model,” Remote Sens (Basel), vol. 13, no. 3, pp. 1–17, 2021, doi: 10.3390/rs13030505.
Q. Xiao, H. H. Chang, G. Geng, and Y. Liu, “An Ensemble Machine-Learning Model to Predict Historical PM2.5 Concentrations in China from Satellite Data,” Environ Sci Technol, vol. 52, no. 22, pp. 13260–13269, 2018, doi: 10.1021/acs.est.8b02917.
Y. Feng, S. Fan, K. Xia, and L. Wang, “Estimation of Regional Ground-Level PM2.5 Concentrations Directly from Satellite Top-of-Atmosphere Reflectance Using A Hybrid Learning Model,” Remote Sens (Basel), vol. 14, no. 11, 2022, doi: 10.3390/rs14112714.
T. K. Ho, “Random decision forests,” Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 1, pp. 278–282, 1995, doi: 10.1109/ICDAR.1995.598994.
T. Li, H. Shen, C. Zeng, and Q. Yuan, “A validation approach considering the uneven distribution of ground stations for satellite-based PM2.5 Estimation,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 13, pp. 1312–1321, 2020, doi: 10.1109/JSTARS.2020.2977668.
J. Bi, J. H. Belle, Y. Wang, A. I. Lyapustin, A. Wildani, and Y. Liu, “Impacts of snow and cloud covers on satellite-derived PM2.5 levels,” Remote Sens Environ, vol. 221, pp. 665–674, 2019, doi: https://doi.org/10.1016/j.rse.2018.12.002.
Abstract views: 594 , 
pdf (Bahasa Indonesia) downloads: 510
