Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.5.4.4

A Study for Estimation of High Resolution Temperature Using Satellite Imagery and Machine Learning Models during Heat Waves  

Lee, Dalgeun (National Disaster Management Research Institute, MOIS)
Lee, Mi Hee (National Disaster Management Research Institute, MOIS)
Kim, Boeun (National Disaster Management Research Institute, MOIS)
Yu, Jeonghum (National Disaster Management Research Institute, MOIS)
Oh, Yeongju (National Disaster Management Research Institute, MOIS)
Park, Jinyi (National Disaster Management Research Institute, MOIS)
Publication Information
Korean Journal of Remote Sensing / v.36, no.5_4, 2020 , pp. 1179-1194 More about this Journal
Abstract
This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R2 (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R2 = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.
Keywords
Remote Sensing; Machine Learning; Disaster Management; Heat Wave;
Citations & Related Records
Times Cited By KSCI : 5  (Citation Analysis)
연도 인용수 순위
1 Choi, M. H., N. J. Jung, K. C. Lee, J. S. Jeong, and I. Y. Seo, 2019. Development of artificial neural network algorithm for the prediction of power failures by natural disaster, Transactions of the Korean Institute of Electrical Engineers, 68(9): 1085-1093.   DOI
2 Fu, P. and P. M. Rich, 2000. The solar analyst 1.0 user manual, Helios Environmental Modeling Institute (HEMI), USA, p. 1616.
3 Fu, P. and P. M. Rich, 2002. A geometric solar radiation model with applications in agriculture and forestry, Computers and Electronics in Agriculture, 37(1-3): 25-35.   DOI
4 Gardner, M. W. and S. R. Dorling, 1998. Artificial neural networks (the multilayer perceptron) - A review of applications in the atmospheric sciences, Atmospheric Environments, 32(14-15): 2627-2636.   DOI
5 Gu, H., L. Dai, G. Wu, D. Xu, S. Wang, and H. Wang, 2006. Estimation of forest volumes by integrating Landsat TM imagery and forest inventory data, Science in China Series E: Technological Sciences, 49(1): 54-62.   DOI
6 Han, D., Y. J. Kim, J. Im, S. Lee, Y. Lee, and H. Kim, 2018. The estimation of arctic air temperature in summer based on Machine Learning approaches using IABP Buoy and AMSR2 satellite data, Korean Journal of Remote Sensing, 34(6-2): 1261-1272.   DOI
7 JAXA EORC (Japan Aerospace Exploration Agency Earth Observation Research Center), May 2020. ALOS Global Digital Surface Model (DSM) ALOS World 3D-30 m (AW3D30), Product Description Ver.3.1.
8 Jedlovec, G., D. Crane, and D. Quattrochi, 2017. Urban heat wave hazard and risk assessment, Results in Physics, 7: 4249-4295
9 Jin, S., C. Homer, L. Yang, G. Xian, J. Fry, P. Danielson, and P. A. Townsend, 2013. Automated cloud and shadow detection and filling using two-date Landsat imagery in the USA, International Journal of Remote Sensing, 34(5): 1540-1560.   DOI
10 Jung, J. H., J. Heo, S. H. Yoo, K. M. Kim, and J. B. Lee, 2010. Estimation of aboveground biomass carbon stock in Danyang area using kNN algorithm and Landsat TM seasonal satellite images, Journal of Korean Society for Geospatial Information Science, 18(4): 119-129.
11 Jung, M. H., S. H. Lee, E, M. Chang, S. W. Hong, 2012, Method of monitoring forest vegetation change based on change of MODIS NDVI time series pattern, Journal of Korea Spatial Information Society, 20(4): 47-55.   DOI
12 Katila, M. and E. Tomppo. 2001. Selecting estimation paramters for the finish multisource national forest inventory, Remote Sensing of Environment, 767: 16-32.   DOI
13 KMA (Korea Meteorological Administration), 2020. Korean Climate Change Assessment Report 2020, Korea Meteorological Administration, KR, pp. 307-328.
14 Keramitsoglou, I., C. T. Kiranoudis, B. Maiheu, K. Ridder, I. A. Daglis, P. Manunta, and M. Paganimi, 2013. Heat wave hazard classification and risk assessment using artificial intelligence fuzzy logic, Environmental Monitoring and Assessment, 185: 8239-8258.   DOI
15 Kim, B. H., Y. H. Kim, Y. K. Han, W. S. Choi, and Y. I. Kim, 2014. Fully automated generation of cloud-free imagery using Landsat-8, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 32(2): 133-142 (in Korean with English abstract).   DOI
16 Kim, M., 2020. The hazard Viz-platform for the establishment of heatwave response strategies, Journal of Korea Multimedia Society, 23(5): 683-699.   DOI
17 Koo, Y. H., S. M. Kim, M. Oh, and H. D. Park, 2019. Estimation of solar irradiance at weather stations in Korea using regionally trained artificial neural network models, Journal of the Korean Society of Mineral and Energy Resources Engineers, 56(2): 155-171.   DOI
18 Lee, G. W. and S. W. Son, 2016. Geo-Spatial Information System, Seoul, Goomibook.
19 Lee, C. H., 2005. Calculating attribute weights in k-nearest neighbor algorithms using information theory, The Korean Institute of Information Scientists and Engineers, 32(9): 920-926.
20 Lee, E. J., C. H. Min, and T. S. Kim, 2008. Development of the KOSPI (Korea Composite Stock Price Index) forecast model using neural network and statistical methods, The Institute of Electronics and Information Engineers, 45(5): 95-101.
21 Noi, P. T., J. Degener, and M. Kappas, 2017. Comparison of multiple linear regression, cubist regression, and random forest algorithms to estimate daily air surface temperature from dynamic combinations of MODIS LST data, Remote Sensing, 9(5): 398.   DOI
22 Lee, M., Y. Kim, Y. Jun, and Y. Shin, 2019. Random forest based prediction of road surface condigion using spatio-temporal features, Journal of Korean Society of Transportation, 37(4): 338-349 (in Korean with English abstract). .   DOI
23 NDMI (National Disaster Management Research Institute), 2017. Development of Analysis Technique Using Land Surface Temperature Based on Satellite Data, Research Report, National Disaster Management Research Institute, KR.
24 Nilson, M., J. Bohlin, H. Olsson, S. A. Svensson, and M. Haapaniemi, 2005. Operational use of remote sensing for regional level assessment of forest estate values, New Strategies for European Remote Sensing, 24: 263-268.
25 Park, W. S. and M. S. Suh, 2011. Characteristics and trends of tropical night occurrence in South Korea for recent 50 years (1958-2007), Atmosphere, 21(4): 361-371.   DOI
26 Reese, H., M. Nilson, P. Sandstrm, and H. Olsson. 2002. Applications using estimates of forest paramters derived from satellite and forest inventory data, Computers and Electronics in Agriculture, 37(1): 37-55.   DOI
27 Rouse, J. W., R. H. Haas, J. A. Schell and D. W. Deeringm, 1974. Monitoring vegetation systems in the Great Plains with ERTS, Proc. of 1974 3rd Earth Resource Techonology Satellite (ERTS) Symposium, Washington D.C, USA, Dec. 10-14, pp. 309-317.
28 Teixeira Pinto, C., X. Jing, and L. Leigh, 2020. Evaluation analysis of Landsat level-1 and level-2 data products using In situ measurements, Remote Sensing, 12(16): 2597.   DOI
29 Wu, C., H. Shen, A. Shen, J. Deng, M. Gan, J. Zhu, H. Xu, and K. Wang, 2016. Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery, Journal of Applied Remote Sensing, 10(3): 03510.
30 Wan, Z., 2006. MODIS land surface temperature products users' guide, Institute for Computational Earth System Science, University of California: Santa Barbara, CA, USA.
31 Yim, J. S., G. S. Kong, S. H. Kim, and M. Y. Shin, 2007. Forest thematic maps and forest statistics using the k-nearest neighbor technique for Pyeongchang-gun, Gangwon-do, Journal of Korean Society of Forest Science, 96(3): 259-268 (in Korean with English abstract).
32 Yoo, C., J. Im, S. Park, and L. J. Quackenbush, 2018. Estimation of daily maximum and minimum air temperatures in urban landscapes using MODIS time series satellite data, ISPRS Journal of Photogrammetry and Remote Sensing, 137: 149-162.   DOI
33 Zhang, J., Y. Wang, and Y. Li, 2006. A C++ program for retrieving land surface temperature from the data of Landsat TM/ETM+ band6, Computers & Geosciences, 32(10): 1796-1805.   DOI
34 Burrough, P. A., R. McDonnell, R. A. McDonnell, and L. D. Lloyd, 2015. Principles of Geographical Information Systems, Oxford University Press, NY, USA, p. 190.
35 Beers, T. W., P. E. Dress, and L. C. Wensel, 1966. Notes and observations : aspect transformation in site productivity research, Journal of Forest, 64(10): 691-692.
36 Bishop, C. M., 1995. Neural Networks for Pattern Recognition, Oxford University Press, New York, p. 482.
37 Breiman, L., 2001. Random Forests, Machine Learning, 45(1): 5-32.   DOI
38 Cao, X. H., I. Stojkovic, and Z. Obradovic, 2016. A robust data scaling algorithm to improve classification accuracies in biomedical data, BMC Bioinformatics, 17(1): 359.   DOI
39 Cho, H. M. and Y. H. Lee, 2018. The Improvement plan for Seoul heat response, Policy Report, 257: 4.