Construction of grassland drought monitoring model based on comprehensive drought database and random forest algorithm

doi:10.7523/j.ucas.2021.0066

Abstract

Abstract: Drought is one of the major natural disasters in the grassland. Therefore developing an effective drought monitoring method for grassland has important practical significance. Traditional drought monitoring model is based on single meteorological or remote sensing data, unable to fully describe complex drought event. The construction of the existing comprehensive drought monitoring models mostly relies on the standardized precipitation evapotranspiration index and other traditional meteorological indicators. However, traditional meteorological index calculation is more complicated, and has certain limitation in terms of agricultural drought monitoring. The United States Drought Monitor (USDM) combines various drought-causing factors with the help of expert's knowledge, which is a more reliable drought indicator. Therefore, in this study, USDM drought categories were used as the prior drought knowledge, and the random forest method was adopted to build a comprehensive grassland drought monitoring model based on multi-source remote sensing and meteorological data. Meanwhile, the applicability of climate and geographical conditions was considered for application verification in Inner Mongolia. Compared with USDM, the model has higher spatial resolution at 1 km scale and better monitoring capability at regional scale. The results of application in Inner Mongolia show that the model has a higher correlation with soil moisture compared with single drought index, and can monitor the spatial and temporal evolution of drought in grassy areas with a higher temporal resolution.

Key words: drought monitoring, grassland, USDM, Inner Mongolia

CLC Number:

S127
TP79

YUAN Xueqi, LI Jing, ZHU Xinran, ZHANG Zhaoxing, LIU Qinhuo. Construction of grassland drought monitoring model based on comprehensive drought database and random forest algorithm[J]. Journal of University of Chinese Academy of Sciences, 2023, 40(3): 351-361.

References

[1] 黄艳艳, 王会军. 2020年全球变暖会创新高吗?[J]. 大气科学学报, 2020, 43(4):585-591. DOI:10.13878/j.cnki.dqkxxb.20200526007.
[2] Mishra A K, Singh V P. A review of drought concepts[J]. Journal of Hydrology, 2010, 391(1-2):202-216. DOI:10.1016/j.jhydrol.2010.07.012.
[3] 赵同谦, 欧阳志云, 贾良清, 等. 中国草地生态系统服务功能间接价值评价[J]. 生态学报, 2004,24(6):1101-1110. DOI:10.3321/j.issn:1000-0933.2004.06.002.
[4] Liu X, Zhu X, Pan Y, et al. Agricultural drought monitoring:Progress, challenges, and prospects[J]. Journal of Geographical Sciences, 2016, 26(6):750-767. DOI:10.1007/s11442-016-1297-9.
[5] Brown J F, Wardlow B D, Tadesse T, et al. The vegetation drought response index (VegDRI):a new integrated approach for monitoring drought stress in vegetation[J]. GIScience & Remote Sensing, 2008, 45(1):16-46. DOI:10.2747/1548-1603.45.1.16.
[6] Wu J J, Zhou L, Liu M, et al. Establishing and assessing the Integrated Surface Drought Index (ISDI) for agricultural drought monitoring in mid-eastern China[J]. International Journal of Applied Earth Observation and Geoinformation, 2013, 23:397-410. DOI:10.1016/j.jag.2012.11.003.
[7] Feng P Y, Wang B, Liu D L, et al. Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia[J]. Agricultural Systems, 2019, 173:303-316. DOI:10.1016/j.agsy.2019.03.015.
[8] 张建, 谢田晋, 杨万能, 等. 近地遥感技术在大田作物株高测量中的研究现状与展望[J]. 智慧农业(中英文), 2021, 3(1):1-15. DOI:10.12133/j.smartag.2021.3.1.202102-SA033.
[9] Svoboda M, Lecomte D, Hayes M, et al. The drought monitor[J]. Bulletin of the American Meteorological Society, 2002, 83(8):1181-1190. DOI:10.1175/1520-0477-83.8.1181.
[10] 管晓丹, 郭铌, 黄建平, 等. 植被状态指数监测西北干旱的适用性分析[J]. 高原气象, 2008, 27(5):1046-1053.
[11] 杨波, 马苏, 王彬武, 等. 基于MODIS的湖南省农业干旱监测模型[J]. 自然资源学报, 2012, 27(10):1788-1796.DOI:10.11849/zrzyxb.2012.10.016.
[12] Rui H, Beaudoing H. README Document for NASA GLDAS Version 2 Data Products[EB/OL]. (2019-08-06)[2021-08-25]. https://data.mint.isi.edu/files/raw-data/GLDAS_NOAH025_M.2.0/doc/README_GLDAS2.pdf.
[13] 叶建刚, 申双和, 吕厚荃. 修正帕默尔干旱指数在农业干旱监测中的应用[J]. 中国农业气象, 2009, 30(2):257-261. DOI:10.3969/j.issn.1000-6362.2009.02.028.
[14] 刘高鸣, 谢传节, 何天乐, 等. 基于多源数据的农业干旱监测模型构建[J]. 地球信息科学学报, 2019, 21(11):1811-1822. DOI:10.12082/dqxxkx.2019.180666.
[15] 杜灵通, 田庆久, 王磊, 等. 基于多源遥感数据的综合干旱监测模型构建[J]. 农业工程学报, 2014, 30(9):126-132. DOI:10.3969/j.issn.1002-6819.2014.09.016.
[16] Zambrano F, Lillo-Saavedra M, Verbist K, et al. Sixteen years of agricultural drought assessment of the BioBío region in Chile using a 250 m resolution vegetation condition index (VCI)[J]. Remote Sensing, 2016, 8(6):530. DOI:10.3390/rs8060530.
[17] Anyamba A, Tucker C J, Eastman J R. NDVI anomaly patterns over Africa during the 1997/98 ENSO warm event[J]. International Journal of Remote Sensing, 2001, 22(10):1847-1859. DOI:10.1080/01431160010029156.
[18] Ji L, Peters A J. Assessing vegetation response to drought in the northern Great Plains using vegetation and drought indices[J]. Remote Sensing of Environment, 2003, 87(1):85-98. DOI:10.1016/S0034-4257(03)00174-3.
[19] Nicholson S E, Farrar T J. The influence of soil type on the relationships between NDVI, rainfall, and soil moisture in semiarid Botswana. I. NDVI response to rainfall[J]. Remote Sensing of Environment, 1994, 50(2):107-120. DOI:10.1016/0034-4257(94)90038-8.
[20] 董师师, 黄哲学. 随机森林理论浅析[J]. 集成技术, 2013, 2(1):1-7.
[21] 王玉娜, 李粉玲, 王伟东, 等. 基于无人机高光谱的冬小麦氮素营养监测[J]. 农业工程学报, 2020, 36(22):31-39.DOI:10.11975/j.issn.1002-6819.2020.22.004.
[22] 高子恒, 丁炜, 何静. 基于随机森林算法和MODIS数据的日喀则地区土地覆盖分类与动态监测[J]. 安徽农业科学, 2020, 48(16):1-12. DOI:10.3969/j.issn.0517-6611.2020.16.001.
[23] 黄芳芳, 雷鸣, 张力, 等. 基于随机森林和决策树的马尾松松材线虫病监测方法[J]. 信息通信, 2019, 32(12):32-36. DOI:10.3969/j.issn.1673-1131.2019.12.011.
[24] 姜红, 何清, 曾晓青, 等. 基于随机森林和卷积神经网络的FY-4A号卫星沙尘监测研究[J]. 高原气象, 2021, 40(3):680-689. DOI:10.7522/j.issn.1000-0534.2020.00060.
[25] Park S, Im J, Jang E, et al. Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions[J]. Agricultural and Forest Meteorology, 2016, 216:157-169. DOI:10.1016/j.agrformet.2015.10.011.
[26] 冯定原,邱新法.农业干旱的成因、指标、时空分布和防旱抗旱对策[J].中国减灾,1995(01):22-27.
[27] Hunt E R Jr, Rock B N Jr. Detection of changes in leaf water content using Near-and Middle-Infrared reflectances[J]. Remote Sensing of Environment, 1989, 30(1):43-54. DOI:10.1016/0034-4257(89)90046-1.
[28] 孙嵩松, 王喜民. 基于多源遥感数据的干旱监测研究[J]. 山东农业科学, 2019, 51(2):150-157. DOI:10.14083/j.issn.1001-4942.2019.02.029.