All Issue

2026 Vol.68, Issue 5 Preview Page
AI-Driven Estimation of Agricultural Drought Damage Using Satellite Remote Sensing

위성영상과 딥러닝 융합 기반 농업가뭄 피해 추정

Hyeok-Jae Choia
,
Won-Ho Namb†
,
Hee-Jin Leec
,
Ho-Sun Leed
최 혁재a
,
남 원호b†
,
이 희진c
,
이 호선d
aGraduate Student, School of Social Safety and Systems Engineering, Hankyong National University
bProfessor, School of Social Safety and Systems Engineering, Institute of Agricultural Environmental Science, National Agricultural Water Research Center, Hankyong National University
cSenior Researcher, National Agricultural Water Research Center, Hankyong National University
dPrincipal Specialist, Drought Information Analysis Center, Korea Water Resources Corporation (K-water)
† Corresponding author Tel.: +82-31-670-5137, Fax: +82-31-670-5139 E-mail: wonho.nam@hknu.ac.kr
30 September 2026. pp. 71-84
PDF XML Citation
Abstract

Agricultural drought impacts on crop production are becoming increasingly severe under intensifying climate variability and extreme weather conditions. This study presents a satellite-based deep learning framework for estimating rice yield reduction as supplementary information for agricultural drought impact assessment by integrating multi-source Moderate Resolution Imaging Spectroradiometer (MODIS) observations with data-driven modeling. Nineteen variables derived from MODIS data, including vegetation indices, land surface temperature, evapotranspiration-related variables, productivity variables, and surface reflectance bands, were used to characterize crop growth and environmental conditions. A Convolutional Neural Network (CNN) model was developed to estimate municipal-scale rice yield using satellite-derived variables. Rice yield reduction was quantified using a yield anomaly (YA) approach, in which CNN-predicted rice yields were compared with long-term baseline yields. The estimated yield reduction was subsequently used as an indirect indicator to examine the spatial distribution of potential agricultural drought impacts. The results demonstrated that the integration of multi-source MODIS observations and deep learning successfully reproduced spatial variations in rice yield and provided useful supplementary information for identifying areas vulnerable to drought-related production losses. The proposed framework enables spatially explicit monitoring of rice yield reduction and supports agricultural drought impact assessment by offering timely information on potential crop damage. These findings highlight the potential of satellite remote sensing and artificial intelligence approaches to complement conventional drought monitoring systems and improve impact-based agricultural drought assessment.

Keywords
Agricultural drought
MODIS
deep learning
yield prediction
rice yield reduction
yield anomaly
References
1

Farooq, M., A. Wahid, N. Kobayashi, D. Fujita, and S. M. A. Basra, 2009. Plant drought stress: Effects, mechanisms, and management. Agronomy for Sustainable Development 29(1): 185-212. doi:10.1051/agro:2008021.

10.1051/agro:2008021
2

Hong, J. P., I. H. Song, S. J. Jang, J. S. Park, and H. J. Shin, 2022. Classification of summer paddy and winter cropping fields using Sentinel-2 images. Journal of the Korean Society of Agricultural Engineers 64(1): 51-63 (in Korean). doi:10.5389/KSAE.2022.64.1.051.

10.5389/KSAE.2022.64.1.051
3

Jeon, M. G., W. H. Nam, H. J. Lee, E. M. Hong, S. Hwang, and S. O. Hur, 2021. Drought risk assessment for upland crops using satellite-derived evapotranspiration and soil available water capacity. Journal of the Korean Society of Hazard Mitigation 21(1): 25-33 (in Korean). doi:10.9798/KOSHAM.2021.21.1.25.

10.9798/KOSHAM.2021.21.1.25
4

Jeong, J. H., D. Kim, and M. H. Choi, 2017. A study on the utilization of geostationary ocean color imager on communication, ocean and meteorological satellite for drought monitoring. Journal of the Korean Society of Hazard Mitigation 17(3): 69-77 (in Korean). doi:10.9798/KOSHAM.2017.17.3.69.

10.9798/KOSHAM.2017.17.3.69
5

Khlif, M., M. J. Escorihuela, A. Chahbi Bellakanji, G. Paolini, and Z. L. Chabaane, 2023. Remotely sensed agricultural drought indices for assessing the impact on cereal yield. Remote Sensing 15(17): 4298. doi:10.3390/rs15174298.

10.3390/rs15174298
6

Kogan, F. N., 1995. Application of vegetation index and brightness temperature for drought detection. Advances in Space Research 15(11): 91-100. doi:10.1016/0273-1177(95)00079-T.

10.1016/0273-1177(95)00079-T
7

Kolipaka, V. R. R., and A. Namburu, 2023. Integrating temporal fluctuations in crop growth with stacked bidirectional LSTM and 3D CNN fusion for enhanced crop yield prediction. International Journal on Recent and Innovation Trends in Computing and Communication 11(9): 376-383. doi:10.17762/ijritcc.v11i9.8543.

10.17762/ijritcc.v11i9.8543
8

Lee, D. R., D. H. Lee, and S. W. Kang, 2003. Drought triggers and monitoring system. Journal of Korea Water Resources Association 36(3): 375-384 (in Korean). doi:10.3741/JKWRA.2003.36.3.375.

10.3741/JKWRA.2003.36.3.375
9

Lee, H. J., W. H. Nam, D. H. Yoon, H. Y. Kim, S. Woo, and D. E. Kim, 2021. Drought monitoring for paddy fields using satellite-derived evaporative stress index. Journal of the Korean Society of Agricultural Engineers 63(3): 47-57 (in Korean). doi:10.5389/KSAE.2021.63.3.047.

10.5389/KSAE.2021.63.3.047
10

Lesk, C., P. Rowhani, and N. Ramankutty, 2016. Influence of extreme weather disasters on global crop production. Nature 529(7584): 84-87. doi:10.1038/nature16467.

10.1038/nature16467
11

Lewis, C. D., 1982. Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting. London, UK: Butterworth Scientific.

12

Liu, W. T., and F. N. Kogan, 1996. Monitoring regional drought using the vegetation condition index. International Journal of Remote Sensing 17(14): 2761-2782. doi:10.1080/01431169608949106.

10.1080/01431169608949106
13

Liu, Y., L. Sun, B. Liu, Y. Wu, J. Ma, W. Zhang, B. Wang, and Z. Chen, 2023. Estimation of winter wheat yield using multiple temporal vegetation indices derived from UAV-based multispectral and hyperspectral imagery. Remote Sensing 15(19): 4800. doi:10.3390/rs15194800.

10.3390/rs15194800
14

Lobell, D. B., W. Schlenker, and J. Costa-Roberts, 2011. Climate trends and global crop production since 1980. Science 333(6042): 616-620. doi:10.1126/science.1204531.

10.1126/science.1204531
15

Mu, H., L. Zhou, X. Dang, and B. Yuan, 2019. Winter wheat yield estimation from multitemporal remote sensing images based on convolutional neural networks. In Proc. the 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), 1-4. Shanghai, China: IEEE. doi:10.1109/Multi-Temp.2019.8866918.

10.1109/Multi-Temp.2019.8866918
16

Mun, Y., W. H. Nam, M. G. Jeon, T. G. Kim, E. M. Hong, M. J. Hayes, and T. Tadesse, 2019. Application of meteorological drought index using climate hazards group infrared precipitation with station data in Korea. Journal of the Korean Society of Agricultural Engineers 61(2): 1-11 (in Korean). doi:10.5389/KSAE.2019.61.2.001.

10.5389/KSAE.2019.61.2.001
17

Nam, W. H., B. D. Wardlow, M. W. Jang, S. Y. Hong, and T. Tadesse, 2015a. Satellite-based hybrid drought assessment using vegetation drought response index in South Korea (VegDRI-SKorea). Journal of the Korean Society of Agricultural Engineers 57(4): 1-9 (in Korean). doi:10.5389/KSAE.2015.57.4.001.

10.5389/KSAE.2015.57.4.001
18

Nam, W. H., J. Y. Choi, S. H. Yoo, and B. A. Engel, 2012. A real-time online drought broadcast system for monitoring soil moisture index. KSCE Journal of Civil Engineering 16(3): 357-365. doi:10.1007/s12205-012-1357-3.

10.1007/s12205-012-1357-3
19

Nam, W. H., M. J. Hayes, D. A. Wilhite, and M. D. Svoboda, 2015b. Projection of temporal trends on drought characteristics using the standardized precipitation evapotranspiration Index (SPEI) in South Korea. Journal of the Korean Society of Agricultural Engineers 57(1): 37-45 (in Korean). doi:10.5389/KSAE.2015.57.1.037.

10.5389/KSAE.2015.57.1.037
20

Nam, W. H., T. Tadesse, B. D. Wardlow, M. J. Hayes, M. D. Svoboda, E. M. Hong, Y. Pachepsky, and M. W. Jang, 2018. Developing the vegetation drought response index for South Korea (VegDRI-SKorea) to assess vegetation condition during drought events. International Journal of Remote Sensing 39(5): 1548-1574. doi:10.1080/01431161.2017.1407047.

10.1080/01431161.2017.1407047
21

Park, H., Y. Lee, and S. Park, 2023. Satellite-based cabbage and radish yield prediction using deep learning in Gangwon-do. Korean Journal of Remote Sensing 39(5): 1031-1042 (in Korean). doi:10.7780/kjrs.2023.39.5.3.11.

10.7780/kjrs.2023.39.5.3.11
22

Park, J., B. Kim, S. Oh, and J. H. Park, 2013. Applicability of vegetation indices from Terra MODIS and COMS GOCI imageries. Journal of the Korean Society of Agricultural Engineers 55(6): 47-55 (in Korean). doi:10.5389/KSAE.2013.55.6.047.

10.5389/KSAE.2013.55.6.047
23

Park, S., J. Lee, J. Yeom, E. Seo, and J. Im, 2022. Performance of drought indices in assessing rice yield in North Korea and South Korea under different agricultural systems. Remote Sensing 14(23): 6161. doi:10.3390/rs14236161.

10.3390/rs14236161
24

Ray, D. K., N. D. Mueller, P. C. West, and J. A. Foley, 2015. Climate variation explains a third of global crop yield variability. Nature Communications 6: 5989. doi:10.1038/ncomms6989.

10.1038/ncomms698925609225PMC4354156
25

Sur, C., and W. H. Nam, 2023. Application of VIIRS land products for agricultural drought monitoring. Journal of Korea Water Resources Association 56(11): 729-735 (in Korean). doi:10.3741/JKWRA.2023.56.11.729.

10.3741/JKWRA.2023.56.11.729
26

Tadesse, T., B. D. Wardlow, M. J. Hayes, M. D. Svoboda, and J. F. Brown, 2010. The Vegetation Outlook (VegOut): A new method for predicting vegetation seasonal greenness. GIScience & Remote Sensing 47(1): 25-52. doi:10.2747/1548-1603.47.1.25.

10.2747/1548-1603.47.1.25
27

Wilhite, D. A., and M. H. Glantz, 1985. Understanding the drought phenomenon: The role of definitions. Water International 10(3): 111-120. doi:10.1080/02508068508686328.

10.1080/02508068508686328
28

Wilhite, D. A., M. J. Hayes, C. Knutson, and K. Smith, 2000. Planning for drought: Moving from crisis to risk management. Journal of the American Water Resources Association 36(4): 697-710. doi:10.1111/j.1752-1688.2000.tb04299.x.

10.1111/j.1752-1688.2000.tb04299.x
29

Yoo, C., D. Kang, and S. Park, 2022. Identifying the impact of regional meteorological parameters on US crop yield at various spatial scales using remote sensing data. Remote Sensing 14(15): 3508. doi:10.3390/rs14153508.

10.3390/rs14153508
30

Yoon, D. H., W. H. Nam, H. J. Lee, E. M. Hong, and T. G. Kim, 2020. Drought hazard assessment using MODIS-based evaporative stress index and ROC analysis. Journal of the Korean Society of Agricultural Engineers 62(3): 51-61 (in Korean). doi:10.5389/KSAE.2020.62.3.051.

10.5389/KSAE.2020.62.3.051
31

Yoon, D. H., W. H. Nam, H. J. Lee, E. M. Hong, T. G. Kim, D. E. Kim, A. K. Shin, and M. D. Svoboda, 2018. Application of evaporative stress index for satellite-based agricultural drought monitoring in South Korea. Journal of the Korean Society of Agricultural Engineers 60(6): 121-131 (in Korean). doi:10.5389/KSAE.2018.60.6.121.

10.5389/KSAE.2018.60.6.121
32

You, J., X. Li, M. Low, D. Lobell, and S. Ermon, 2017. Deep gaussian process for crop yield prediction based on remote sensing data. In Proc. the AAAI Conference on Artificial Intelligence 31(1): 1617-1624. doi:10.1609/aaai.v31i1.11172.

10.1609/aaai.v31i1.11172
33

Zhang, L., and T. Zhou, 2015. Drought over East Asia: A review. Journal of Climate 28(8): 3375-3399. doi:10.1175/JCLI-D-14-00259.1.

10.1175/JCLI-D-14-00259.1
34

Zhao, Y., J. Zhang, Y. Bai, S. Zhang, S. Yang, M. Henchiri, A. M. Seka, and L. Nanzad, 2022. Drought monitoring and performance evaluation based on machine learning fusion of multi-source remote sensing drought factors. Remote Sensing 14(24): 6398. doi:10.3390/rs14246398.

10.3390/rs14246398
Information
  • Publisher :The Korean Society of Agricultural Engineers
  • Publisher(Ko) :한국농공학회
  • Journal Title :Journal of Korean Society of Agricultural Engineers
  • Journal Title(Ko) :한국농공학회논문집
  • Volume : 68
  • No :5
  • Pages :71-84
  • Received Date : 2026-04-06
  • Revised Date : 2026-06-22
  • Accepted Date : 2026-06-25
  • DOI :https://doi.org/10.5389/KSAE.2026.68.5.071
Journal Informaiton Journal of Korean Society of Agricultural Engineers Journal of Korean Society of Agricultural Engineers
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close