{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:59:43Z","timestamp":1783745983417,"version":"3.55.0"},"reference-count":40,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Forecasting particulate matter with a diameter of 2.5 \u03bcm (PM2.5) is critical due to its significant effects on both human health and the environment. While ground-based pollution measurement stations provide highly accurate PM2.5 data, their limited number and geographic coverage present significant challenges. Recently, the use of aerosol optical depth (AOD) has emerged as a viable alternative for estimating PM2.5 levels, offering a broader spatial coverage and higher resolution. Concurrently, long short-term memory (LSTM) models have shown considerable promise in enhancing air quality predictions, often outperforming other prediction techniques. To address these challenges, this study leverages geographic information systems (GIS), remote sensing (RS), and a hybrid LSTM architecture to predict PM2.5 concentrations. Training LSTM models, however, is an NP-hard problem, with gradient-based methods facing limitations such as getting trapped in local minima, high computational costs, and the need for continuous objective functions. To overcome these issues, we propose integrating the novel orchard algorithm (OA) with LSTM to optimize air pollution forecasting. This paper utilizes meteorological data, topographical features, PM2.5 pollution levels, and satellite imagery from the city of Tehran. Data preparation processes include noise reduction, spatial interpolation, and addressing missing data. The performance of the proposed OA-LSTM model is compared to five advanced machine learning (ML) algorithms. The proposed OA-LSTM model achieved the lowest root mean square error (RMSE) value of 3.01 \u00b5g\/m3 and the highest coefficient of determination (R2) value of 0.88, underscoring its effectiveness compared to other models. This paper employs a binary OA method for sensitivity analysis, optimizing feature selection by minimizing prediction error while retaining critical predictors through a penalty-based objective function. The generated maps reveal higher PM2.5 concentrations in autumn and winter compared to spring and summer, with northern and central areas showing the highest pollution levels.<\/jats:p>","DOI":"10.3390\/ijgi14020042","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T09:01:13Z","timestamp":1737622873000},"page":"42","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A Novel Evolutionary Deep Learning Approach for PM2.5 Prediction Using Remote Sensing and Spatial\u2013Temporal Data: A Case Study of Tehran"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2660-4158","authenticated-orcid":false,"given":"Mehrdad","family":"Kaveh","sequence":"first","affiliation":[{"name":"Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology, Tehran 19967-15433, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2119-5164","authenticated-orcid":false,"given":"Mohammad Saadi","family":"Mesgari","sequence":"additional","affiliation":[{"name":"Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology, Tehran 19967-15433, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0752-8054","authenticated-orcid":false,"given":"Masoud","family":"Kaveh","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Aalto University, 02150 Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kumar, R.P., Prakash, A., Singh, R., and Kumar, P. (2024). Machine learning-based prediction of hazards fine PM2.5 concentrations: A case study of Delhi, India. Discov. Geosci., 2.","DOI":"10.1007\/s44288-024-00043-z"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Natsagdorj, N., and Zhou, H. (2023). Prediction of PM2.5 concentration in Ulaanbaatar with deep learning models. Urban Clim., 47.","DOI":"10.1016\/j.uclim.2022.101357"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1007\/s11869-024-01524-3","article-title":"Spatiotemporal estimation of hourly PM2.5 using AOD derived from geostationary satellite Fengyun-4A and machine learning models for Greater Bangkok","volume":"17","author":"Aman","year":"2024","journal-title":"Air Qual. Atmos. Health"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"G\u00fcndo\u011fdu, S., and Elbir, T. (2024). Elevating hourly PM2.5 forecasting in Istanbul, T\u00fcrkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis. Chemosphere, 364.","DOI":"10.1016\/j.chemosphere.2024.143096"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Shogrkhodaei, S.Z., Razavi-Termeh, S.V., and Fathnia, A. (2021). Spatio-temporal modeling of PM2.5 risk mapping using three machine learning algorithms. Environ. Pollut., 289.","DOI":"10.1016\/j.envpol.2021.117859"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Taghavi, M., Ghanizadeh, G., Ghasemi, M., Fass\u00f2, A., Hoek, G., Hushmandi, K., and Raei, M. (2023). Application of functional principal component analysis in the spatiotemporal land-use regression modeling of PM2.5. Atmosphere, 14.","DOI":"10.3390\/atmos14060926"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Habibi, R., Alesheikh, A.A., Mohammadinia, A., and Sharif, M. (2017). An assessment of spatial pattern characterization of air pollution: A case study of CO and PM2.5 in Tehran, Iran. ISPRS Int. J. Geo-Inf., 6.","DOI":"10.3390\/ijgi6090270"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Razavi-Termeh, S.V., Sadeghi-Niaraki, A., and Choi, S.M. (2021). Effects of air pollution in spatio-temporal modeling of asthma-prone areas using a machine learning model. Environ. Res., 200.","DOI":"10.1016\/j.envres.2021.111344"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ghajari, Y.E., Kaveh, M., and Mart\u00edn, D. (2023). Predicting PM10 Concentrations Using Evolutionary Deep Neural Network and Satellite-Derived Aerosol Optical Depth. Mathematics, 11.","DOI":"10.3390\/math11194145"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Delavar, M.R., Gholami, A., Shiran, G.R., Rashidi, Y., Nakhaeizadeh, G.R., Fedra, K., and Hatefi Afshar, S. (2019). A novel method for improving air pollution prediction based on machine learning approaches: A case study applied to the capital city of Tehran. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8020099"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.scitotenv.2018.02.096","article-title":"Source apportionment of ambient PM2.5 in two locations in central Tehran using the Positive Matrix Factorization (PMF) model","volume":"628","author":"Taghvaee","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1007\/s11869-019-00739-z","article-title":"Evaluation of linear, nonlinear, and hybrid models for predicting PM2.5 based on a GTWR model and MODIS AOD data","volume":"12","author":"Mirzaei","year":"2019","journal-title":"Air Qual. Atmos. Health"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wu, Y., Xu, Z., Xu, L., and Wei, J. (2024). Approach Considering Spatiotemporal Heterogeneity for PM2.5 Prediction: A Case Study of Xinjiang, China. Atmosphere, 15.","DOI":"10.3390\/atmos15040460"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pu, Q., and Yoo, E.H. (2022). A gap-filling hybrid approach for hourly PM2.5 prediction at high spatial resolution from multi-sourced AOD data. Environ. Poll., 315.","DOI":"10.1016\/j.envpol.2022.120419"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1109\/LGRS.2019.2900270","article-title":"Deep learning architecture for estimating hourly ground-level PM 2.5 using satellite remote sensing","volume":"16","author":"Sun","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nguyen, P.H., Dao, N.K., and Nguyen, L.S.P. (2024). evelopment of machine learning and deep learning prediction models for PM2.5 in Ho Chi Minh City, Vietnam. Atmosphere, 15.","DOI":"10.3390\/atmos15101163"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Karimian, H., Li, Y., Chen, Y., and Wang, Z. (2023). Evaluation of different machine learning approaches and aerosol optical depth in PM2.5 prediction. Environ. Res., 216.","DOI":"10.1016\/j.envres.2022.114465"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kianian, B., Liu, Y., and Chang, H.H. (2021). Imputing satellite-derived aerosol optical depth using a multi-resolution spatial model and random forest for PM2.5 prediction. Remote Sens., 13.","DOI":"10.3390\/rs13010126"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Feng, H., Zou, B., and Tang, Y. (2017). Scale-and region-dependence in landscape-PM2. 5 correlation: Implications for urban planning. Remote Sens., 9.","DOI":"10.3390\/rs9090918"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wei, J., Huang, W., Li, Z., Xue, W., Peng, Y., Sun, L., and Cribb, M. (2019). Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach. Remote Sens. Environ., 231.","DOI":"10.1016\/j.rse.2019.111221"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.1007\/s12524-020-01154-z","article-title":"Comparison of six machine learning methods for estimating PM2.5 concentration using the Himawari-8 aerosol optical depth","volume":"48","author":"Zuo","year":"2020","journal-title":"J. Indian Soc. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wang, Z., Cao, C., Xu, M., Yang, X., Wang, K., Guo, H., Gao, X., Li, J., and Shi, Z. (2024). Estimation of PM2.5 concentration across china based on multi-source remote sensing data and machine learning methods. Remote Sens., 16.","DOI":"10.3390\/rs16030467"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.rse.2016.08.027","article-title":"Satellite-based ground PM2.5 estimation using timely structure adaptive modeling","volume":"186","author":"Fang","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1016\/j.apr.2018.12.017","article-title":"Assessing PM2.5 concentrations in Tehran, Iran, from space using MAIAC, deep blue, and dark target AOD and machine learning algorithms","volume":"10","author":"Nabavi","year":"2019","journal-title":"Atmos. Pollut. Res."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Bagheri, H. (2023). Using deep ensemble forest for high-resolution mapping of PM2.5 from MODIS MAIAC AOD in Tehran, Iran. Environ. Monit. Assess., 195.","DOI":"10.1007\/s10661-023-10951-1"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.1016\/j.asr.2022.02.032","article-title":"A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data","volume":"69","author":"Bagheri","year":"2022","journal-title":"Adv. Space Res."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Faraji, M., Nadi, S., Ghaffarpasand, O., Homayoni, S., and Downey, K. (2022). An integrated 3D CNN-GRU deep learning method for short-term prediction of PM2.5 concentration in urban environment. Sci. Total Environ., 834.","DOI":"10.1016\/j.scitotenv.2022.155324"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zamani Joharestani, M., Cao, C., Ni, X., Bashir, B., and Talebiesfandarani, S. (2019). PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data. Atmosphere, 10.","DOI":"10.3390\/atmos10070373"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Handschuh, J., Erbertseder, T., and Baier, F. (2024). On the added value of satellite AOD for the investigation of ground-level PM2.5 variability. Atmos. Environ., 331.","DOI":"10.1016\/j.atmosenv.2024.120601"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1002\/2017GL075710","article-title":"Estimating ground-level PM2.5 by fusing satellite and station observations: A geo-intelligent deep learning approach","volume":"44","author":"Li","year":"2017","journal-title":"Geophys. Res. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, T., Gong, W., Wang, W., Ji, Y., Zhu, Z., and Huang, Y. (2016). Ground level PM2.5 estimates over China using satellite-based geographically weighted regression (GWR) models are improved by including NO2 and enhanced vegetation index (EVI). Int. J. Environ. Res. Public Health, 13.","DOI":"10.3390\/ijerph13121215"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.scitotenv.2018.04.251","article-title":"A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information","volume":"636","author":"Chen","year":"2018","journal-title":"Sci. Total Environ."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ma, X., Zou, B., Deng, J., Gao, J., Longley, I., Xiao, S., Guo, B., Wu, Y., Xu, T., and Xu, X. (2024). A comprehensive review of the development of land use regression approaches for modeling spatiotemporal variations of ambient air pollution: A perspective from 2011 to 2023. Environ. Int., 183.","DOI":"10.1016\/j.envint.2024.108430"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Al-Selwi, S.M., Hassan, M.F., Abdulkadir, S.J., Muneer, A., Sumiea, E.H., Alqushaibi, A., and Ragab, M.G. (2024). RNN-LSTM: From applications to modeling techniques and beyond\u2014Systematic review. J. King Saud Univ.-Comput. Inf. Sci., 321.","DOI":"10.1016\/j.jksuci.2024.102068"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Abou Houran, M., Bukhari, S.M.S., Zafar, M.H., Mansoor, M., and Chen, W. (2023). COA-CNN-LSTM: Coati optimization algorithm-based hybrid deep learning model for PV\/wind power forecasting in smart grid applications. Appl. Energy, 349.","DOI":"10.1016\/j.apenergy.2023.121638"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wan, A., Chang, Q., Khalil, A.B., and He, J. (2023). Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism. Energy, 282.","DOI":"10.1016\/j.energy.2023.128274"},{"key":"ref_37","unstructured":"Zhang, Q., Kong, W., Zhou, G., Wu, C., and Cui, E. (2024). ISSA-LSTM: A new data-driven method of heat load forecasting for building air conditioning. Energy Build., 36."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4519","DOI":"10.1007\/s11063-022-11055-6","article-title":"Application of meta-heuristic algorithms for training neural networks and deep learning archi-tec-tures: A comprehensive review","volume":"55","author":"Kaveh","year":"2022","journal-title":"Neural Process. Lett."},{"key":"ref_39","first-page":"2819","article-title":"Improved IChOA-Based Reinforcement Learning for Secrecy Rate Optimization in Smart Grid Communications","volume":"81","author":"Shoeibi","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.matcom.2022.12.027","article-title":"Orchard Algorithm (OA): A new meta-heuristic algorithm for solving discrete and continuous optimization problems","volume":"208","author":"Kaveh","year":"2023","journal-title":"Math. Comput. Simul."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/2\/42\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:34:45Z","timestamp":1759919685000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/2\/42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["ijgi14020042"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14020042","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,23]]}}}