Archives
 
Year 2025
 
Vol 66, Issue 5, [10 - 2025]

Drought risk prediction using remote sensing data and machine learning: A case study in Quang Tri province

DOI:10.46326/JMES.2025.66(5).02

  • Affiliations:

    1 Hanoi University of Mining and Geology, Hanoi, Vietnam
    2 Le Quy Don Technical University, Hanoi, Vietnam

  • *Corresponding:
    This email address is being protected from spambots. You need JavaScript enabled to view it.
  • Received: 30th-Nov--000
  • Revised: 13th-Aug-2025
  • Accepted: 23rd-Aug-2025
  • Online: 1st-Oct-2025
Pages: 12 - 24
Views: 52
View onlineView online
Downloads: 2
Downdload PDF
★★★★★Rating: , Total rating: 0
  • ★
  • ★
  • ★
  • ★
  • ★
Yours rating

Abstract:

Quang Tri Province was located in Vietnam’s North Central Coast, frequently experiences severe climatic conditions including prolonged droughts. These conditions adversely affect agricultural production and local livelihoods. This study proposes a drought risk prediction model by integrating remote sensing data with machine learning techniques to support water resource management and mitigate drought-related damages.​ Remote sensing data from Landsat and Sentinel-2 satellites covering the period from 2016 to 2025 were collected and processed using the Google Earth Engine (GEE) cloud platform. Drought indices including NDVI, LSWI, NDWI, MSI, NDDI, SAVI, VCI, TCI, TVDI, and VHI were computed to assess temperature conditions, soil moisture, and vegetation health. Based on the TVDI index, data were categorized into five drought severity levels: no drought, mild drought, moderate drought, severe drought, and extreme drought. A training dataset was constructed by randomly selecting pixel samples representing each drought level. Three machine learning models including Random Forest (RF), Support Vector Machine (SVM), and Gradient Tree Boosting (GTB) were employed to classify and predict drought risk.​ The GTB model achieved the highest accuracy with an overall accuracy of 91.67% and a Kappa coefficient of 0.89, outperforming both SVM and RF models. The drought risk distribution map generated using the GTB model clearly highlights areas with high drought risk, particularly in the eastern and central regions of Quang Tri Province. In addition, 2019 and 2022 recorded severe and extreme drought areas exceeding 90% of the total area of ​​the region.

How to Cite
Tran, T.Thu Thi, Trinh, H.Le, Do, T.Phuong Thi, Nguyen, H.Mai and Le, P.Van 2025. Drought risk prediction using remote sensing data and machine learning: A case study in Quang Tri province (in Vietnamese). Journal of Mining and Earth Sciences. 66, 5 (Oct, 2025), 12-24. DOI:https://doi.org/10.46326/JMES.2025.66(5).02.
References

Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.

Chen,A.,Jiang,J.,Luo,Y.,Zhang,G.,Hu,B.,Wang,X.,andZhang,S.(2023). Temperature vegetation dryness index (TVDI) for drought monitoring in the Guangdong Province from 2000 to 2019. PeerJ, 11, e16337.

Cổng thông tin điện tử tỉnh Quảng Trị (2025a). Điều kiện tự nhiên. https://www.quangtri.gov. vn/new-chi-ti%E1%BA%BFt-tin-t%E1%BB %95ng-quan/-/view-article/1/1573433122 481/1717639121658. Truy cập ngày 22-4-2025.

Cổng thông tin điện tử tỉnh Quảng Trị (2025b). Kiểm tra tình hình ứng phó với hạn hán, nắng nóng tại Vĩnh Linh, Gio Linh. https://www. quangtri.gov.vn/chi-tiet-tin/-/view-article/1/ 138482 41113627/1577456441574. Truy cập ngày 22-4-2025.

Danandeh Mehr, A. (2021). Drought classification using gradient boosting decision tree. Acta Geophysica, 69(3), 909-918.

Dũng, L. H., Lê Giang, N., and Phương, T. T. (2016). Hạn hán năm 2015-2016 trên hai lưu vực sông chính ở Tây Nguyên. Bản B của Tạp chí Khoa học và Công nghệ Việt Nam, 58(6).

Elbeltagi, A., Pande, C.B., Kumar, M. et al. Prediction of meteorological drought and standardized precipitation index based on the random forest (RF), random tree (RT), and Gaussian process regression (GPR) models. Environ Sci Pollut Res 30, 43183-43202 (2023). https://doi.org/10,1007/ s11356-023-25221-3.

Friedman, J. H. (2002). Stochastic gradient boosting. Computational statistics and data analysis, 38(4), 367-378.

Gao, B. C. (1996). NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote sensing of environment, 58(3), 257-266.

Gu, Y., Brown, J. F., Verdin, J. P., and Wardlow, B. D. (2007). A five-year analysis of MODIS NDVI and NDWI for grassland drought assessment over the central Great Plains of the United States. Geophysical Research Letters, 34(6).​

Ha,D.H.,Duc,P.N.,Luong,T.H.,Duc,T.T.,Ngoc,T.T.,Minh,T.N.,andMinh,T.N.(2024). Application of Artificial Intelligence to Forecast Drought Index for the Mekong Delta. Applied Sciences, 14(15), 6763. https://doi.org/10,3 390/app14156763.

He, Z., Gu, X., Wang, M., and Xu, M. (2025). The coupled effect of climate change and LUCC on meteorological drought in a karst drainage basin, Southwest China. Scientific Reports, 15(1), 9134. https://doi. org/10,1038/s4159 8-025-93035-z.

Huete, A. R., (1988). A Soil-adjusted Vegetation Index (SAVI). Remote Sensing of Environment, 25(3): 295-309. DOI:10,1016/0034-4257(88)90106-X.

Hunt, E. R., and Rock, B. N. (1989). Detection of changes in leaf water content using near- and middle-infrared reflectances. Remote Sensing of Environment, 30(1), 43-54.

Khảm, D. V., Khánh, Đ. Q. (2022). Đánh giá đặc điểm khí hậu và điều kiện khí hậu nông nghiệp huyện Kỳ Anh tỉnh Hà Tĩnh. Tạp chí Khí tượng Thủy văn 2022, 733, 15-28; doi:10,36335/ VNJHM. 2022(733).15-28.

Kogan, F.N. (1995). Application of vegetation index and brightness temperature for drought detection. Advances in Space Research, 15(11), 91-100. https://doi.org/10,1016/0273-1177(95)00079-T.

Kogan, F. N. (1997). Global drought watch from space. Bulletin of the American meteorological society, 78(4), 621-636.

Mallick,J.,Alqadhi,S.,Alsubih,M.,andAlkahtanis,M.(2025).Integratingtraditionalandadvancedtechnologiesfordroughtmonitoringandmanagement:asystematicreviewofglobalmethodologiesandapplications.TheoreticalandAppliedClimatology,156(5),1-18.https://doi.org/10,1007/s00704-025-05469-0.

Maxwell, A. E., Warner, T. A., and Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International journal of remote sensing, 39(9), 2784-2817.

Mukherjee, S., Mishra, A. and Trenberth, K.E. (2018) Climate Change and Drought: a Perspective on Drought Indices. Curr Clim Change Rep 4, 145-163 (2018). https://doi.org/10,1007/s40641 -018-0098-x.

Liu, Z. N., Li, Q. F., Nguyen, L. B., Xu, G. H. (2018). Comparing Machine-Learning Models for Drought Forecasting in Vietnam’s Cai River Basin. Polish Journal of Environmental Studies, 27(6), 2633-2646. https://doi.org/10 .15244/pjoes/80866.

Oyarzabal, R. S., Santos, L. B., Cunningham, C., Broedel, E., de Lima, G. R., Cunha-Zeri, G., ... andCunha,A.P.(2025).Forecastingdroughtusingmachinelearning:asystematicliteraturereview.NaturalHazards,1-29. https://doi.org/10,1007/ s11069-025-07195-2.

Phùng, M. L., and Nguyễn, Á. T. (2023). Tác động của thiên tai và biến đổi khí hậu tới sản xuất nông nghiệp và thủy sản của hộ nông dân khu vực miền Trung và Tây Nguyên Việt Nam. Tạp chí Khoa học Thăng Long: Khoa học Ứng dụng, 1, 47-60. https://science.thanglong.edu.vn /index.php/vola/article/view/9.

Phan, V. T., and Ngô, Đ. T. (2013). Biến đổi khí hậu ở Việt Nam: Một số kết quả nghiên cứu, thách thức và cơ hội trong hội nhập quốc tế. VNU Journal of Science: Earth and Environmental Sciences, 29(2).

Quiring, S. M. and Ganesh, S. (2010). Evaluating the utility of the Vegetation Condition Index (VCI) for monitoring meteorological drought in Texas. Agricultural and Forest Meteorology, 150(3), 330-339. https://doi.org/10,1016/j.agrformet.2009,11,015.

Sandholt,I.,Rasmussen,K.,andAndersen,J.(2002). A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status. Remote Sensing of Environment, 79(2-3), 213-224.

Serban, C., and Maftei, C. (2025). Remote Sensing Evaluation of Drought Effects on Crop Yields Across Dobrogea, Romania, Using Vegetation Health Index (VHI). Agriculture, 15(7), 668.

Sở Tài nguyên và Môi trường tỉnh Quảng Trị. (2022). Báo cáo 2022. https://quang triclimate.vn/2022/ 10/page/2/. Truy cập ngày 22-4-2025.

Suthaharan, S. (2016). Support vector machine. In Machine learning models and algorithms for big data classification: thinking with examples for effective learning (pp. 207-235). Boston, MA: Springer US.

Tamrakar, Y., Das, I.C. and Sharma, S. Machine learning for improved drought forecasting in Chhattisgarh India: a statistical evaluation. Discov Geosci 2, 84 (2024). https://doi.org/10,1007/s44288-024-00089-z.

Trịnh, L.H. (2014). Ứng dụng dữ liệu viễn thám hồng ngoại nhiệt Landsat nghiên cứu độ ẩm đất trên cơ sở chỉ số khô hạn nhiệt độ thực vật. Tạp chí Các khoa học về Trái Đất, 36(3), 262-270.

Trịnh L. H., and Đào K. H. (2019). Ứng dụng viễn thám đánh giá nguy cơ hạn hán khu vực huyện Bắc Bình, tỉnh Bình Thuận. HCMUE Journal of Science, 5(70), 128. https://doi.org/10. 54607/hcmue.js.0,5(70).539(2015).

Tucker, C. J. (1979). Red and photographic infrared linear combinations for monitoring vegetation. Remote sensing of Environment, 8(2), 127-150.

Wu, J., and Chen, Y. F. (2017), August). Research of using RF model to drought forecast on Huaihe River. In IOP Conference Series: Earth and Environmental Science (Vol. 82, No. 1, p. 0120 16). IOP Publishing.

Xiang, K., Yuan, W., Wang, L., and Deng, Y. (2020). An LSWI-Based Method for Mapping Irrigated Areas in China Using Moderate-Resolution Satellite Data. Remote Sensing, 12(24), 4181. https://doi.org/10,3390/rs12244181

Zamani,H.,Pakdaman,Z.,Shakari,M.etal. Enhancing drought monitoring with a multivariate hydrometeorological index and machine learning-based prediction in the south of Iran. Environ Sci Pollut Res 32, 5605-5627 (2025). https://doi.org/10,1007/ s113 56-025-36049-4.

Other articles