Remote Sensing and GIS Applications in Environmental Sciences

A Comparative Study of Multiple Linear Regression and Random Forest in the Estimation of Land Surface Temperature: A Case Study of Tabriz City

Document Type : Original Article

Authors

University of Tabriz

10.22034/rsgi.2024.61983.1079

Abstract

Land surface temperature, as one of the important and fundamental parameters in climatology, indicates the relationship between the atmosphere and the Earth. Considering the environmental issues of cities, including the intensification of urban heat islands, accurately estimating LST and identifying its influencing factors play a significant role in urban thermal management and adopting adaptive strategies for heat islands. In this regard, this study compares two regression methods: multiple linear regression and random forest in order to estimate the LST. Daily nighttime MODIS images were used to extract the LST of Tabriz city during the summer. These images were processed in the Google Earth Engine platform and averaged for the period from 2018 to 2022. According to the results, the random forest showed significantly better performance with a coefficient of determination of 0.924 (RMS = 0.009) compared to multiple linear regression. The random forest was also used to determine the importance of the indices. Based on the index importance results, night lights (51/06%), sky view factor (48/01%) and frontal area index (45/27%) were the most important factor affecting the nighttime summer LST in Tabriz city, respectively. The findings of this study, in addition to revealing the strength of the random forest regression in estimating LST, also highlight the importance of various indices in the LST. In this context, the study's results will be practical for managing the thermal environment of Tabriz city and adopting mitigation strategies for its heat islands.

Keywords

Main Subjects

دمای سطح زمین به‌عنوان یکی از پارامترهای مهم و پایه‌ای در مباحث اقلیمی، نشان‌دهنده رابطه بین اتمسفر و زمین می‌باشد. با درنظرداشتن مشکلات زیست‌محیطی شهرها از جمله شدت یافتن جزایر حرارتی شهری، تخمین دمای سطح زمین با دقت مطلوب و همچنین استخراج عوامل مؤثر بر آن نقش قابل‌توجهی را در مدیریت حرارتی محیط‌های شهری و همچنین اتخاذ استراتژی‌های انطباقی با جزایر حرارتی دارد. پژوهش حاضر در این راستا به مقایسه دو روش رگرسیونی خطی چندگانه و جنگل تصادفی پرداخته است. از تصاویر مادیس روزانه در بازه شب (10:30) جهت استخراج دمای سطح زمین فصل تابستان شهر تبریز بهره گرفته شد. تصاویر مذکور در سامانه گوگل ارث انجین پردازش شده و برای بازه 2018 الی 2022 میانگین‌گیری گردید. بر اساس نتایج پژوهش، جنگل تصادفی با ضریب تعیین 924/0 (009/0 = RMS) عملکرد بسیار بهتری را نسبت به رگرسیون خطی چندگانه از خود نشان داد. جهت استخراج اهمیت شاخص‌ها نیز از جنگل تصادفی بهره گرفته شد. بر اساس نتایج اهمیت شاخص‌ها، شاخص‌های نور شب (06/51 درصد)، ضریب دید به آسمان (01/48 درصد) و مساحت ناحیه رو به باد (27/45) به ترتیب مهم‌ترین شاخص‌های اثرگذار بر متوسط دمای سطح زمین شبانه فصل تابستان شهر تبریز هستند. نتایج پژوهش حاضر علاوه بر آشکار نمودن قوت رگرسیون جنگل تصادفی در تخمین دمای سطح زمین، اهمیت شاخص‌های متعدد بر آن را نیز آشکار می‌کند. در این راستا، یافته‌های این مطالعه برای مدیریت حرارتی محیط شهری تبریز و اتخاذ استراتژی‌های سازگاری با جزایر حرارتی آن کاربردی خواهد بود.

  1. Abbot, M. L. (2017). Using Statistics in the Social and Health Sciences with SPSS and Excel. John Wiley & Sons. DOI: 10.1002/9781119121077
  2. Abrougui, K. & Gabsi, K. & Mercatoris, B. & Khemis, C. & Amami, R. &
  3.  
  4. Chehaibi, Sa. (2019). Prediction of organic potato yield using tillage systems and soil properties by artificial neural network and multiple linear regressions. Soil and Tillage Research. Vol. 190. pp 202-208. DOI: 10.1016/j.still.2019.01.011.
  5. Andrés-Anaya, P., Sánchez-Aparicio, M., del Pozo, S., & Lagüela, S. (2021). Correlation of Land Surface Temperature with IR Albedo for the Analysis of Urban Heat Island. Engineering Proceedings, 8(1). https://doi.org/10.3390/engproc2021008009
  6. Azadi Mubaraky, M., & Ahmadi, M. (2021). Investigation of urban heat islands of Tabriz metropolis using multi-time data of LANDSAT8 satellite based on hot spot analysis method. Regional Planning, 11(43), 47–63. https://doi.org/10.30495/jzpm.2021.3992 (In Persian).
  7. Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
  8. Bernard, J., Bocher, E., Petit, G., Palominos, S. (2018). "Sky View Factor Calculation in Urban Context: Computational Performance and Accuracy Analysis of Two Open and Free GIS Tools" Climate 6(3). https://doi.org/10.3390/cli6030060
  9. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  10. Breiman, L. (2002). Manual on setting up, using, and understanding random forests v3.1. https://www.stat.berkeley.edu/~breiman/Using_random_forests_V3.1.pdf
  11. Carlson, T. N., & Riziley, D. A. (1997). On the Relation between NDVI, Fractional Vegetation Cover, and Leaf Area Index. Remote Sensing of Environment, 62(3), 241–252. https://doi.org/10.1016/S0034-4257(97)00104-1
  12. Chan, J. C.-W., & Paelinckx, D. (2008). Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sensing of Environment, 112(6), 2999-3011. https://doi.org/10.1016/j.rse.2008.02.011
  13. Chen, Q., Cheng, Q., Chen, Y., Li, K., Wang, D., & Cao, S. (2021). The Influence of Sky View Factor on Daytime and Nighttime Urban Land Surface Temperature in Different Spatial-Temporal Scales: A Case Study of Beijing. Remote Sensing, 13(20). https://doi.org/10.3390/rs13204117
  14. Gadekar, K., Pande, C.B., Rajesh, J., Gorantiwar, S.D., Atre, A.A. (2023). Estimation of Land Surface Temperature and Urban Heat Island by Using Google Earth Engine and Remote Sensing Data. In: Pande, C.B., Moharir, K.N., Singh, S.K., Pham, Q.B., Elbeltagi, A. (eds) Climate Change Impacts on Natural Resources, Ecosystems and Agricultural Systems. Springer Climate. Springer, Cham. https://doi.org/10.1007/978-3-031-19059-9_14
  15. George, D. & Mallery, P. (2020). IBM SPSS Statistics 26 Step by Step: A Simple Guide and Reference. 16th Edition. Routledge: Taylor & Francis Group. https://www.routledge.com/IBM-SPSS-Statistics-26-Step-by-Step-A-Simple-Guide-and-Reference/George-Mallery/p/book/9780367174354
  16. Gong, D., Dai, X., Zhou, L. (2023). Satellite-Based Optimization and Planning of Urban Ventilation Corridors for a Healthy Microclimate Environment. Sustainability, 15(21):15653. https://doi.org/10.3390/su152115653
  17. Guha, S., Govil, H. (2020). Land surface temperature and normalized difference vegetation index relationship: a seasonal study on a tropical city. SN Appl. Sci. 2, 1661. https://doi.org/10.1007/s42452-020-03458-8
  18. Haghverdi, A., Noori, R., & Tisseyre, B. (2021). Estimating Land Surface Temperature using MODIS data: A Random Forest approach. Journal of Environmental Management, 298, 113491. https://doi.org/10.1016/j.jenvman.2021.113491
  19. Hodul, M., Knudby, A., Chak, H. (2016). "Estimation of Continuous Urban Sky View Factor from Landsat Data Using Shadow Detection" Remote Sensing 8(7). https://doi.org/10.3390/rs8070568
  20. Keerthi Naidu, B., Chundeli, F.A. (2023). Assessing LULC changes and LST through NDVI and NDBI spatial indicators: a case of Bengaluru, India. GeoJournal 88, 4335–4350. https://doi.org/10.1007/s10708-023-10862-1
  21. Koushesh Vatan, M. A., & Asghari Zamani, A. (2021). Study of land surface temperature concerning land-use in Tabriz city using the Landsat 8 data. Journal of Economic Geography Researches, 2(3), 49–58. https://jurs.znu.ac.ir/article_244529.html (In Persian).
  22. Koushesh Vatan, M. A., Asghari Zamani, A., Nemati, M., & Pourmohammad, F. (2021). A Comparison of Multiple Linear Regression and Random Forest Regression to Evaluate the Price of Residential Units (Case Study: North Valiasr, Tabriz). Geography and Territorial Spatial Arrangement, 11(40), 57–82. https://doi.org/10.22111/gaij.2021.6486 (In Persian).
  23. Li, H., Li, Y., Wang, T., Wang, Z., Gao, M., & Shen, H. (2021). Quantifying 3D building form effects on urban land surface temperature and modeling seasonal correlation patterns.

 

 

 

  1. Building and Environment, 204, 108132. https://doi.org/https://doi.org/10.1016/j.buildenv.2021.108132
  2. Li, L., Zhao, Z., Wang, H., Shen, L., Liu, N., & He, B.-J. (2022). Variabilities of Land Surface Temperature and Frontal Area Index Based on Local Climate Zone. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 2166–2174. https://doi.org/10.1109/JSTARS.2022.3153958
  3. Li, Z. L., Tang, R., Wan, Z., Bi, Y., Zhou, C., Tang, B., ... & Zhang, X. (2013). A review of current methodologies for regional evapotranspiration estimation from remotely sensed data. Sensors, 13(5), 5977-6010. https://doi.org/10.3390/s130505977
  4. Li, Z., Wu, F., Ma, H., Xu, Z., Wang, S. (2022). Spatiotemporal Evolution and Relationship between Night Time Light and Land Surface Temperature: A Case Study of Beijing, China. Land. 211(4):548. https://doi.org/10.3390/land11040548
  5. Liang, S. (2000). Narrowband to broadband conversions of land surface albedo I Algorithms. Remote Sensing of Environment, 76, 213–238. www.elsevier.com/locate/rse
  6. Liaw, Andy & Wiener, Matthew. (2001). Classification and Regression by RandomForest. RNews. 23. https://www.researchgate.net/publication/228451484_Classification_and_Regression_by_RandomForest
  7. Makhija R., Ali S., Jaya Krishna R. (2021) Detecting Influencers in Social Networks Through Machine Learning Techniques. In: Hassanien A., Bhatnagar R., Darwish A. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2020. Advances in Intelligent Systems and Computing, vol 1141. Springer, Singapore. https://doi.org/10.1007/978-981-15-3383-9_23.
  8. Mallick, J., Rahman, A., & Singh, C. K. (2013). Modeling urban heat islands in heterogeneous land surface and its correlation with impervious surface area by using night-time ASTER satellite data in highly urbanizing city, Delhi-India. Advances in Space Research, 52(4), 639–655. https://doi.org/10.1016/j.asr.2013.04.025
  9. Mansourmoghaddam, M., Rousta, I., Ghafarian Malamiri, H., Sadeghnejad, M., Krzyszczak, J., Ferreira, CSS. (2024). Modeling and Estimating the Land Surface Temperature (LST) Using Remote Sensing and Machine Learning (Case Study: Yazd, Iran). Remote Sensing, 16(3):454. https://doi.org/10.3390/rs16030454
Remote Sensing and GIS Applications in Environmental Sciences
Volume 4, Issue 10
April 2024
Pages 94-78
  • Receive Date: 06 June 2024
  • Revise Date: 20 June 2024
  • Accept Date: 14 July 2024