Estimation and mapping of vegetation biomass in forest-steppe and steppe zones of Mongolia using MODIS data

Authors

  • Amarsaikhan Damdinsuren
  • Byambadolgor Batdorj
  • Nyamjargal Erdenebaatar

DOI:

https://doi.org/10.5564/mjgg.v60i44.2939

Keywords:

Vegetation index, RF, SVM, PLSR, Biomass

Abstract

In recent years, digital remote sensing optical datasets and various indices calculated by using them have been intensively applied for green vegetation biomass evaluation and other thematic studies. The main goals of this study were to evaluate the vegetation biomass in the forest-steppe and steppe zones of Mongolia using the indices calculated from medium-resolution satellite data and map the biomass distribution. Indices were calculated from different visible, near, and mid-infrared bands of MODIS data acquired on August 21, 2016, and then classified and compared using machine learning methods such as random forest (RF), support vector machine (SVM), and partial least square regression (PLSR). Among the selected methods for biomass mapping in the forest-steppe and steppe areas, the RF method demonstrated the highest accuracy with a coefficient of determination (R2) of 0.889, and a root mean square error (RMSE) of 0.713 c/ha. The PLSR method had an R2 of 0.296 and an RMSE of 1.854 c/ha, while the SVM method showed the lowest accuracy with an R2 of 0.273 and an RMSE of 1.889 c/ha. Our finding indicates that the RF is a more applicable approach for assessing and mapping the vegetation biomass in the forest-steppe and steppe zones of Mongolia.

MODIS дагуулын мэдээ ашиглан Монгол орны ойт хээр болон хээрийн бүсийн ургамлын биомассыг үнэлэн зураглах нь

ХУРААНГУЙ: Сүүлийн үед зайнаас тандсан оптикийн тоон өгөгдлүүд, тэдгээр дээр суурилан тооцоолсон төрөл бүрийн индексүүдийг ногоон ургамлын биомассын үнэлгээ болон бусад сэдэвчилсэн судалгаанд эрчимтэй ашиглаж байна. Судалгааны ажлын үндсэн зорилго нь Монгол орны ойт хээрийн ба хээрийн бүсийн ургамлын биомассыг дунд нарийвчлал бүхий хиймэл дагуулын мэдээг ашиглан тооцоолсон индексүүдийн тусламжтайгаар үнэлэх, улмаар биомассын тархалтыг зураглахад оршино. Энэ зорилгоор 2016 оны 8 дугаар сарын 21-ний өдрийн MODIS хиймэл дагуулын үзэгдэх гэрэл, ойрын болон дундын нэл улаан туяаны мужийн сувгуудын мэдээг ашиглан индексүүдийг тооцоолж, дараа нь санамсаргүй форестын арга (RF), тулах векторын арга (SVM), хэсэгчилсэн хамгийн бага квадратын регресс (PLSR)-ийн арга зэрэг машин сургалтын аргуудыг ашиглан уг индексүүдийг ангилж, харьцуулсан дүн шинжилгээг хийж гүйцэтгэлээ. Ойт хээрийн ба хээрийн бүсийн биомассыг зураглах аргуудаас RF аргын детерминацийн коэффициент (R2) 0.889, дундаж квадратын алдаа (RMSE) 0.713 ц/га буюу хамгийн өндөр нарийвчлалыг харуулсан бол PLSR аргын R2 нь 0.296, RMSE 1.854 ц/га, харин SVM аргын R2 0.273, RMSE 1.889 ц/га буюу хамгийн бага нарийвчлалтайгаар үнэлсэн байлаа. Энэхүү судалгааны үр дүнд RF арга нь Монгол орны ойт хээрийн ба хээрийн бүсийн ургамлын биомассыг үнэлэх, зураглахад илүү тохиромжтой болохыг харуулж байна.

Түлхүүр үгс: Ургамлын индекс, RF, SVM, PLSR, Биомасс

Downloads

Download data is not yet available.
Abstract
63
PDF
117

References

. "Газрын нэгдмэл сангийн улсын нэгдсэн тайлан," Улаанбаатар, Монгол, 2022.

. "Монголын бэлчээрийн менежментийн холбоо," Улаанбаатар, Монгол, Гар бичмэл, 2008.

. Д. Амарсайхан, ба М.Ганзориг, "Газарзүйн мэдээллийн системийг байгалийн нөөцийн менежментэд ашиглах зарчмууд", Улаанбаатар, Монгол, 2010.

. P. Du et al., "Advances of four machine learning methods for spatial data handling: A review," J. Geovisualization Spat. Anal., vol. 4, p. 13, 2020. https://doi.org/10.1007/s41651-020-00048-5

. A. Sharifi, "Estimation of biophysical parameters in wheat crops in Golestan province using ultra-high resolution images," Remote Sens. Lett., vol. 9, no. 6, pp. 559-568, Jun. 2018, https://doi.org/10.1080/2150704X.2018.1452058

. Z.Y. Han et al., "Hyperspectral estimation of apple tree canopy LAI based on SVM and RF regression," Spectrosc. Spectr. Anal., vol. 36, pp. 800-805, 2016.

. B. Duan, et al., "Remote estimation of rice LAI based on Fourier spectrum texture from UAV image," Plant Methods, vol. 15, no. 1, p. 124, 2019. https://doi.org/10.1186/s13007-019-0507-8

. M. Otgonbayar, C. Atzberger, J. Chambers, and A. Damdinsuren, "Mapping pasture biomass in Mongolia using Partial Least Squares, Random Forest regression and Landsat 8 imagery," Int. J. Remote Sens., vol. 40, no. 8, pp. 3204-3226, Apr. 2019, https://doi.org/10.1080/01431161.2018.1541110

. F. Wang et al., "Estimation of Above-Ground Biomass of Winter Wheat Based on Consumer-Grade Multi-Spectral UAV," Remote Sens., vol. 14, no. 5, p. 1251, Mar. 2022, https://doi.org/10.3390/rs14051251

. N. Viljanen et al., "A Novel Machine Learning Method for Estimating Biomass of Grass Swards Using a Photogrammetric Canopy Height Model, Images and Vegetation Indices Captured by a Drone," Agriculture, vol. 8, no. 5, p. 70, May 2018, https://doi.org/10.3390/agriculture8050070

. L. Guo, X. Xi, W. Yang, and L. Liang, "Monitoring Land Use/Cover Change Using Remotely Sensed Data in Guangzhou of China," Sustainability, vol. 13, no. 5, p. 2944, Mar. 2021, https://doi.org/10.3390/su13052944

. S. Yang et al., "Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region," Remote Sens. Environ., vol. 204, pp. 448-455, 2018. https://doi.org/10.1016/j.rse.2017.10.011

. F. Kogan et al., "Derivation of pasture biomass in Mongolia from AVHRR-based vegetation health indices," Int. J. Remote Sens., vol. 25, no. 14, pp. 2889-2896, Jul. 2004, https://doi.org/10.1080/01431160410001697619

. B. Batbileg, A. Hirano, and O. Nyamsuren, "Mapping summer time pasture amount in north-central mongolia," in Aiming Smart Space Sensing, Pattaya, Thailand, Nov. 2012.

. Y. Xie, Z. Sha, M. Yu, Y. Bai, and L. Zhang, "A comparison of two models with Landsat data for estimating above ground grassland biomass in Inner Mongolia, China," Ecol. Model., vol. 220, no. 15, pp. 1810-1818, 2009. https://doi.org/10.1016/j.ecolmodel.2009.04.025

. M. Liu, G. Liu, L. Gong, D. Wang, and J. Sun, "Relationships of biomass with environmental factors in the grassland area of Hulunbuir, China," PLoS One, vol. 9, no. 7, p. e102344, 2014. https://doi.org/10.1371/journal.pone.0102344

. X. Wang, H. Yang, X. Liu, and Y. Su, "Effects of biomass and environmental factors on nitrogen removal performance and community structure of an anammox immobilized filler," Sci. Total Environ., vol. 710, p. 135258, 2020. https://doi.org/10.1016/j.scitotenv.2019.135258

. M. Klinge et al., "Geoecological parameters indicate discrepancies between potential and actual forest area in the forest-steppe of Central Mongolia," For. Ecosyst., vol. 8, no. 1, p. 55, Aug. 2021, https://doi.org/10.1186/s40663-021-00333-9

. M. Lumbierres, P. Méndez, J. Bustamante, R. Soriguer, and L. Santamaría, "Modeling Biomass Production in Seasonal Wetlands Using MODIS NDVI Land Surface Phenology," Remote Sens., vol. 9, no. 4, p. 392, Apr. 2017, https://doi.org/10.3390/rs9040392

. D. Zianis and M. Mencuccini, "Aboveground net primary productivity of a beech (Fagus moesiaca) forest: a case study of Naousa forest, northern Greece," Tree Physiol., vol. 25, no. 6, pp. 713-722, Jun. 2005, https://doi.org/10.1093/treephys/25.6.713

. Д. Даш. Монгол орны ландшафт экологийн асуудлууд. Улаанбаатар, Монгол, 2010. http://w.tsag-agaar.gov.mn/

. S. Amari, S.I W., "Conformal transformation of Kernel functions: A data-dependent way to improve support vector machine classifier," Neural Process. Lett., vol. 15, pp. 59-67, 2002.

. L. Breiman, "Random forests," Mach. Learn., vol. 45, pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324

. P.T. Wolter, P.A. Townsend, B.R. Sturtevant, and C.C. Kingdon, "Remote sensing of the distribution and abundance of host species for spruce budworm in Northern Minnesota and Ontario," Remote Sens. Environ., no. 112, pp. 3971-3982, 2008. https://doi.org/10.1016/j.rse.2008.07.005

. T. Javzandulam, R. Tateishi, and T. Sanjaa, "Analysis of vegetation indices for monitoring vegetation degradation in semi‐arid and arid areas of Mongolia," Int. J. Environ. Stud., vol. 62, no. 2, pp. 215-225, Apr. 2005, https://doi.org/10.1080/00207230500034123

. D. Narangarav and Ch.Lin, "Investigation of Vegetation Dynamics of Mongolia Using Time Series of NDVI in Response to Temperature and Precipitation," Mong. J. Biol. Sci., vol. 9, no. 1-2, pp. 9-17, Jan. 2017.

. T. Hilker, E. Natsagdorj, R. H. Waring, A. Lyapustin, and Y. Wang, "Satellite observed widespread decline in Mongolian grasslands largely due to overgrazing," Glob. Change Biol., vol. 20, no. 2, pp. 418-428, Feb. 2014, https://doi.org/10.1111/gcb.12365

. A. Enkhmanlai, E. Nyamjargal, D, Amarsaikhan, O. Munkhdulam and B. Batbileg, "Estimation and mapping of pasture biomass in Mongolia using machine learning methods," Geocarto Int., vol. 38, no. 1, p. 2195824, 2023. https://doi.org/10.1080/10106049.2023.2195824

. D. Amarsaikhan et al., "Estimation of Grassland Biomass in Eastern Mongolia RS-based Vegetation Indices Title," in Environmental Science and Technology, Ulaanbaatar, Mongolia, 2023.

Downloads

Published

2023-12-28

How to Cite

Damdinsuren, A., Batdorj , B., & Erdenebaatar, N. . (2023). Estimation and mapping of vegetation biomass in forest-steppe and steppe zones of Mongolia using MODIS data. Mongolian Journal of Geography and Geoecology, 60(44), 144–157. https://doi.org/10.5564/mjgg.v60i44.2939

Issue

Section

Articles