Archives
 
English Issues
 
Vol 65, Issue 5, [10 - 2024]

Forest fire risk prediction using geospatial data and machine learning techniques, a case study in the western region of Nghe An province

DOI:10.46326/JMES.2024.65(5).06

  • 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: 27th-Mar-2024
  • Revised: 28th-July-2024
  • Accepted: 26th-Aug-2024
  • Online: 1st-Oct-2024
Pages: 50 - 60
Views: 197
View onlineView online
Downloads: 6
Downdload PDF
★★★★★Rating: , Total rating: 0
  • ★
  • ★
  • ★
  • ★
  • ★
Yours rating

Abstract:

Nghe An is the province with the largest area of forests and forestry land in the country with more than 1 million hectares of forest, coverage rate reaching 58,33%. Due to the influence of climate change and human activities, forest cover in Nghe An has profound fluctuations, of which forest fires are one of the main causes. This article presents the results of developing a forest fire risk prediction model in the western region of Nghe An province from geospatial data and machine learning algorithms. From the analysis of natural and social conditions in the study area, 9 input data layers include: (1) elevation, (2) slope, (3) aspect, (4) vegetation cover density, (5) population density, (6) land surface temperature, (7) evapotranspiration, (8) wind speed and (9) average monthly rainfall is used to build a forest fire risk prediction model. In the study, we tested with 02 machine learning algorithms, including Random Forest (RF) and Gradient Tree Boosting (GTB), then selected the appropriate algorithm by evaluating accuracy using the fire point data set as well as model performance. The obtained results showed that the AUC (Area Under the Curve) value of the GTB(350) algorithm reached 0,948, higher than the RF(100) (0,947). From this result, the study used the GTB algorithm with 350 trees to create a forest fire risk prediction map in the western region of Nghe An province.

How to Cite
Doan, P.Nam Thi, Trinh, H.Le, Nguyen, T.Van, Le, H.Thu Thi and Le, P.Van 2024. Forest fire risk prediction using geospatial data and machine learning techniques, a case study in the western region of Nghe An province. Journal of Mining and Earth Sciences. 65, 5 (Oct, 2024), 50-60. DOI:https://doi.org/10.46326/JMES.2024.65(5).06.
References

Arpaci A., Malowerschnig, B., Sass, O., Vacik, H. (2014). Using multivariate data mining  

 techniques for estimating fire susceptibility of Tyrolean forests, Applied Geography, 53, 258 - 270.

Breiman, L. (2001). Random Forests, Machine Learning 45, 5-32, https://doi.org/10.1023/ A:1010933404324.

Dieu, T. B., Pradhan, B., Lofman, O., Revhaug, I., Dick, O. B. (2012). Spatial prediction of landslide hazards in Hoa Binh province (Vietnam): A comparative assessment of the efficacy of evidential belief functions and fuzzy logic models, CATENA 96, 28-40.

Dieu, T. B., Thoa, L. T. K., Van, N. C., Duc, L. H.,  Revhaug, I. (2016). Tropical forest fire susceptibility mapping at the Cat Ba national park area, Hai Phong city, Vietnam, using GIS-based kernel logistic regression, Remote Sensing, 8, 347, doi:10.3390/rs8040347.

Đoàn, T. N. P. (2023). Lựa chọn mô hình dự báo nguy cơ cháy rừng từ dữ liệu viễn thám và hệ thông tin địa lý, Luận án tiến sĩ kỹ thuật, Hà Nội.

Đặng, N.B.T., Nguyễn, N.T., Phạm, X.C. (2017). Ứng dụng viễn thám và GIS thành lập bản đồ nguy cơ cháy rừng phục vụ phòng chống, giảm thiểu thiệt hại do cháy rừng tại tỉnh Sơn La, Việt Nam, Hội thảo GIS toàn quốc, tr.252-261.

Enoh, M., Okeke, U., Narinua, N. (2021). Identification and modelling of forest fire severity and risk zones in the Cross - Niger transition forest with remotely sensed satellite data, The Egyptian Journal of Remote Sensing and Space Science, 24(3), 879 - 887.

Fernandez, J., Chuvieco, E., Koutsias, N. (2012). Modelling long-term fire occurrence factors in Spain by accounting for local variations with geographically weighted regression, Natural Hazards Earth System Sciences, 12, 1-17.

Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine, Annals of Statistics,  29(5), 1189-1232.

Hoang, V. T., Chou, T., Fang, Y., Nguyen, N. T., Nguyen, Q. H., Pham, X. C., Dang, N. B. T., Nguyen, X. L., Meadows, M. (2020). Mapping forest fire risk and development of early warning system for NW Vietnam using AHP and MCA/GIS methods, Applied Sciences, 10(12), 4348.

Iban, M., Sekertekin, A. (2022). Machine learning based wildfire susceptibility mapping using remotely sensed fire data and GIS: A case study of Adana and Mersin provinces, Turkey, Ecological Informatics, 69, 101647.

Lê, S. D., Vương, V. Q. (2014). Phương pháp dự báo nguy cơ cháy rừng theo điều kiện khí hậu ở Việt Nam, Tạp chí Khoa học Công nghệ lâm nghiệp, số 1, trang 3-10.

Nguyễn, V. L., Trần, M. Đ., Nguyễn, P. V. (2017). Thực trạng và giải pháp quản lý cháy rừng ứng phó với biến đổi khí hậu tại tỉnh Quảng Bình, Tạp chí Khoa học Lâm nghiệp, số 4, trang 139 - 150.

Nguyễn, P.V (2019). Nghiên cứu thực trạng và đề xuất giải pháp quản lý cháy rừng thích ứng với biến đổi khí hậu tại tỉnh Quảng Bình, Luận án tiến sĩ Lâm nghiệp.

Nguyen, N.T., Dang, B.T.N, Pham, X.C., Nguyen, H.T., Bui, H.T., Hoang, N.D., Bui, D.T. (2018). Spatial pattern assessment of tropical forest fire danger at Thuan Chau area (Vietnam) using GIS-based advanced machine learning algorithms: A comparative study, Ecological Informatics, vol.46, pp.74-85.

Oliveira, S., Oehler, F., Ayanz, J., Camia, A., Pereira, J. (2012). Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest, Forest Ecology and Management, 275, 117 - 129

Phạm, N. H. (1988). Xây dựng phương pháp dự báo cháy rừng Thông nhựa (Pinus merkusii J.) ở Quảng Ninh, Luận án PTS khoa học Nông nghiệp, Hà Nội.

Pourghasemi, H. (2015). GIS-based forest fire susceptibility mapping in Iran: A comparison between evidential belief function and binary logistic regression models, Scandinavian Journal of Forest Research, 40 pp., DOI: 10.1080/02827581.2015.1052750.

Ruano, A., Jolly, W., Freeborn, P., Nieva, D., Vega, N., Herrera, C., Rodrigues, M. (2022). Spatial predictions of human and natural-caused

wildfire likelihood across Montana (USA), Remote Sensing, 13(8), 1200.

Sharma, V., Ghosh, S. K. (2023). Evaluating the potential of 8 band Planet scope dataset for crop classification using Random Forest and Gradient Tree Booting by Google Earth Engine, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-M-1-2023, 325-330.

Trần, Q. B. (2017). Nghiên cứu sử dụng công nghệ không gian địa lý (RS, GIS, GPS) trong phát hiện cháy rừng và giám sát tài nguyên rừng, Đề tài nghiên cứu khoa học cấp Bộ.

Trinh, L. H., Zablotskii, V. R. (2017). The application of Landsat multi-temporal thermal infrared data to identify coal fire in the Khanh Hoa coal mine, Thai Nguyen province, Vietnam, Izvestiya, Atmospheric and Oceanic Physics, 53(9), 11850 - 6088.

Vasilakos, C., Kalabokidis, K., Hatzopoulos, J., Matsinos, T. (2009). Identifying wildland fire ignition factors through sensitivity analysis of a neural network, Natural Hazards, 50, 125 - 143.

Võ, Đ. T. (1995). Phương pháp dự báo, lập bản đồ, khoanh vùng trọng điểm cháy rừng ở Bình Thuận, Tạp chí Lâm nghiệp, số 10, trang 11 - 14.

Other articles