Modelling the dead fuel moisture content in a grassland of Ergun City, China

doi:10.1007/s40333-023-0103-7

Journal of Arid Land

2023, Vol. 15

Issue (6): 710-723 DOI: 10.1007/s40333-023-0103-7 CSTR: 32276.14.s40333-023-0103-7

Research article

Modelling the dead fuel moisture content in a grassland of Ergun City, China

CHANG Chang¹^,², CHANG Yu¹^,^*(

), GUO Meng³, HU Yuanman¹^,⁴

¹CAS Key Laboratory of Forest Ecology and Management, Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110016, China
²University of Chinese Academy of Sciences, Beijing 100049, China
³School of Geographical Sciences, Northeast Normal University, Changchun 130024, China
⁴E'erguna Wetland Ecosystem National Research Station, Hulunbuir 022250, China

Download:

HTML

PDF(4071KB)
Export: BibTeX | EndNote (RIS)

Abstract

The dead fuel moisture content (DFMC) is the key driver leading to fire occurrence. Accurately estimating the DFMC could help identify locations facing fire risks, prioritise areas for fire monitoring, and facilitate timely deployment of fire-suppression resources. In this study, the DFMC and environmental variables, including air temperature, relative humidity, wind speed, solar radiation, rainfall, atmospheric pressure, soil temperature, and soil humidity, were simultaneously measured in a grassland of Ergun City, Inner Mongolia Autonomous Region of China in 2021. We chose three regression models, i.e., random forest (RF) model, extreme gradient boosting (XGB) model, and boosted regression tree (BRT) model, to model the seasonal DFMC according to the data collected. To ensure accuracy, we added time-lag variables of 3 d to the models. The results showed that the RF model had the best fitting effect with an R² value of 0.847 and a prediction accuracy with a mean absolute error score of 4.764% among the three models. The accuracies of the models in spring and autumn were higher than those in the other two seasons. In addition, different seasons had different key influencing factors, and the degree of influence of these factors on the DFMC changed with time lags. Moreover, time-lag variables within 44 h clearly improved the fitting effect and prediction accuracy, indicating that environmental conditions within approximately 48 h greatly influence the DFMC. This study highlights the importance of considering 48 h time-lagged variables when predicting the DFMC of grassland fuels and mapping grassland fire risks based on the DFMC to help locate high-priority areas for grassland fire monitoring and prevention.

Key words： dead fuel moisture content (DFMC) random forest (RF) model extreme gradient boosting (XGB) model boosted regression tree (BRT) model grassland Ergun City

Received: 21 October 2022 Published: 30 June 2023

Corresponding Authors: * CHANG Yu (E-mail: changyu@iae.ac.cn)

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	CHANG Chang
	CHANG Yu
	GUO Meng
	HU Yuanman

Cite this article:

CHANG Chang, CHANG Yu, GUO Meng, HU Yuanman. Modelling the dead fuel moisture content in a grassland of Ergun City, China. Journal of Arid Land, 2023, 15(6): 710-723.

URL:

http://jal.xjegi.com/10.1007/s40333-023-0103-7 OR http://jal.xjegi.com/Y2023/V15/I6/710

Fig. 1 Land cover types of Ergun City (a) and an overview of fuel moisture content meters (b). The land cover type data are derived from https://www.resdc.cn/Default.aspx.

Fig. 2 Fuel moisture content meter and its components. The anemometer is placed 1 m above the ground.

Table 1 Seasonal division of this study according to the average daily temperature

Fig. 3 Box plot of the seasonal differences in the dead fuel moisture content (DFMC). The upper and lower limits of the box indicate the 75^th and 25^th percentile values, respectively; the horizontal lines and small squares in each box represent the medians and means, respectively; the upper and lower whiskers show the maximum and minimum values, respectively; and the scattered points above the maximum values are outliers.

Fig. 4 Performances of the boosted regression tree (BRT) model (a), extreme gradient boosting (XGB) model (b), and random forest (RF) model (c) in predicting the DFMC. MAE is the mean absolute error.

Fig. 5 Performance of the BRT, XGB, and RF models in spring (a1, b1, and c1), summer (a2, b2, and c2), autumn (a3, b3, and c3), and winter (a4, b4, and c4)

Fig. 6 Variable importance changes with time lags in the RF model in spring (a), summer (b), autumn (c), winter (d), and the all year (e). IncNodePurity is the degree of importance. The negative values of the x-axis represent the hours before the time of measurement.

Fig. 7 Prediction performance along with the time-lag data 72 h before the time of measuring. (a), R²; (b), MAE.


[1]	Bakšić N, Bakšić D, Jazbec A. 2017. Hourly fine fuel moisture model for Pinus halepensis (Mill.) litter. Agricultural and Forest Meteorology, 243: 93-99.

[2]	Bilgili E, Coskuner K A, Usta Y, et al. 2018. Modeling surface fuels moisture content in Pinus brutia stands. Journal of Forestry Research, 30(2): 577-587. doi: 10.1007/s11676-018-0702-x

[3]	Cai W H, Yang J, Liu Z H, et al. 2012. Controls of post-fire tree recruitment in Great Xing'an Mountains in Heilongjiang Province. Acta Ecologica Sinica, 32(11): 3303-3312. (in Chinese) doi: 10.5846/stxb

[4]	Cao M C, Zhou G S, Weng E S. 2005. Application and comparison of generalized models and classification and regression tree in simulating tree species distribution. Acta Ecologica Sinica, 25(8): 2031-2040. (in Chinese)

[5]	Capps S B, Zhuang W, Liu R, et al. 2021. Modelling chamise fuel moisture content across California: A machine learning approach. International Journal of Wildland Fire, 31(2): 136-148. doi: 10.1071/WF21061

[6]	Catchpole W R, Catchpole E A, Butler B W, et al. 1998. Rate of spread of free-burning fires in woody fuels in a wind Tunnel. Combustion Science and Technology, 131: 1-37. doi: 10.1080/00102209808935753

[7]	Chen T Q, Guestrin C. 2016. XGBoost. In:Proceedings of the 22^nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, USA.

[8]	Chen Y, Zhao L, Jiang Y D, et al. 2012. Division of Climate Season. Beijing: China Meteorological Press. (in Chinese)

[9]	Cunill Camprubí À, González-Moreno P, Resco de Dios V. 2022. Live fuel moisture content mapping in the Mediterranean Basin using random forests and combining MODIS spectral and thermal data. Remote Sensing, 14(13): 3162, doi: 10.3390/rs14133162. doi: 10.3390/rs14133162

[10]	Deak B, Valko O, Toeroek P, et al. 2014. Grassland fires in Hungary-experiences of nature conservationists on the effects of fire on biodiversity. Applied Ecology and Environmental Research, 12(1): 267-283. doi: 10.15666/aeer

[11]	De'ath G. 2007. Boosted trees for ecological modeling and prediction. Ecology, 88: 243-251. doi: 10.1890/0012-9658(2007)88[243:btfema]2.0.co;2 pmid: 17489472

[12]	Di Z L, Wu Y N, Song Y T, et al. 2019. Changes of extreme climate index in forest-steppe ecotone in Erguna. Chinese Journal of Ecology, 38(10): 3143-3152. (in Chinese)

[13]	Dragozi E, Giannaros T M, Kotroni V, et al. 2021. Dead fuel moisture content (DFMC) estimation using MODIS and meteorological data: the case of Greece. Remote Sensing, 13(21): 4224, doi: 10.3390/rs13214224. doi: 10.3390/rs13214224

[14]	Elith J, Leathwick J R, Hastie T. 2008. A working guide to boosted regression trees. Journal of Animal Ecology, 77(4): 802-813. doi: 10.1111/j.1365-2656.2008.01390.x pmid: 18397250

[15]	Fan C Q, He B B. 2021. A physics-guided deep learning model for 10-h dead fuel moisture content estimation. Forests, 12(7): 933, doi: 10.3390/rs13214224. doi: 10.3390/rs13214224

[16]	Fernandes P A M. 2001. Fire spread prediction in shrub fuels in Portugal. Forest Ecology and Management, 144(1-3): 67-74. doi: 10.1016/S0378-1127(00)00363-7

[17]	Fontenele H G V, Cruz-Lima L F S, Pacheco-Filho J L, et al. 2020. Burning grasses, poor seeds: post-fire reproduction of early-flowering Neotropical savanna grasses produces low-quality seeds. Plant Ecology, 221(12): 1265-1274. doi: 10.1007/s11258-020-01080-7

[18]	Gao C, Lin H L, Hu H Q, et al. 2020. A review of models of forest fire occurrence prediction in China. The Journal of Applied Ecology, 31(9): 3227-3240. (in Chinese)

[19]	González A D R, Hidalgo J A V, González J G Á, 2009. Construction of empirical models for predicting Pinus sp. dead fine fuel moisture in NW Spain. I: Response to changes in temperature and relative humidity. International Journal of Wildland Fire, 18(1): 71-83. doi: 10.1071/WF07101

[20]	Hiers J K, Stauhammer C L, O'Brien J J, et al. 2019. Fine dead fuel moisture shows complex lagged responses to environmental conditions in a saw palmetto (Serenoa repens) flatwoods. Agricultural and Forest Meteorology, 266-267: 20-28.

[21]	Hu H Q, Luo B Z, Luo S S, et al. 2019. Water content of surface ground fuel in Larix gmelinii-Betula platyphylla mixed forest of Nanwenhe, Daxing'an Mountains. Chinese Journal of Ecology, 38(5): 1314-1321. (in Chinese)

[22]	Jin S, Li J M. 2014. Prediction on moisture contents of typical forest dead combustible fuels of an ecotones in Qingan county of Heilongjiang province. Journal of Central South University of Forestry & Technology, 34(12): 27-34. (in Chinese)

[23]	Karlson M, Ostwald M, Reese H, et al. 2015. Mapping tree canopy cover and aboveground biomass in Sudano-Sahelian woodlands using Landsat 8 and random forest. Remote Sensing, 7(8): 10017-10041. doi: 10.3390/rs70810017

[24]	Lee H, Won M, Yoon S, et al. 2020. Estimation of 10-hour fuel moisture content using meteorological data: a model inter-comparison study. Forests, 11: 982, doi: 10.3390/f11090982. doi: 10.3390/f11090982

[25]	Lei W D, Yu Y, Li X H, et al. 2022. Estimating dead fine fuel moisture content of forest surface, based on wireless sensor network and back-propagation neural network. International Journal of Wildland Fire, 31(4): 369-378. doi: 10.1071/WF21066

[26]	Li C L, Liu M, Hu Y M, et al. 2014. Driving forces analysis of urban expansion based on boosted regression trees and Logistic regression. Acta Ecologica Sinica, 34(3): 727-737. (in Chinese)

[27]	Limb R F, Fuhlendorf S D, Engle D M, et al. 2011. Pyric-herbivory and cattle performance in grassland ecosystems. Rangeland Ecology & Management, 64(6): 659-663. doi: 10.2111/REM-D-10-00192.1

[28]	Lopes S, Viegas D X, Teixeira de Lemos L, et al. 2014. Equilibrium moisture content and timelag of dead Pinus pinaster needles. International Journal of Wildland Fire, 23(5): 721-732. doi: 10.1071/WF13084

[29]	Man Z Y, Hu H Q, Zhang Y L, et al. 2019. Dynamic change and prediction model of moisture content of surface fuel in Maoer Mountain of northeastern China. Journal of Beijing Forestry University, 41(3): 49-57. (in Chinese)

[30]	Masinda M M, Li F, Liu Q, et al. 2021. Prediction model of moisture content of dead fine fuel in forest plantations on Maoer Mountain, Northeast China. Journal of Forestry Research, 32(5): 2023-2035. doi: 10.1007/s11676-020-01280-x

[31]	Masinda M M, Li F, Qi L, et al. 2022. Forest fire risk estimation in a typical temperate forest in Northeastern China using the Canadian forest fire weather index: Case study in autumn 2019 and 2020. Natural Hazards, 111: 1085-1101. doi: 10.1007/s11069-021-05054-4

[32]	Matthews S, Gould J, McCaw L. 2010. Simple models for predicting dead fuel moisture in eucalyptus forests. International Journal of Wildland Fire, 19(4): 459-467. doi: 10.1071/WF09005

[33]	Matthews S. 2014. Dead fuel moisture research: 1991-2012. International Journal of Wildland Fire, 23(1): 78-92.

[34]	Mouillot F, Field C B. 2005. Fire history and the global carbon budget: a 1°×1° fire history reconstruction for the 20th century. Global Change Biology, 11(3): 398-420. doi: 10.1111/gcb.2005.11.issue-3

[35]	Muro J, Linstädter A, Magdon P, et al. 2022. Predicting plant biomass and species richness in temperate grasslands across regions, time, and land management with remote sensing and deep learning. Remote Sensing of Environment, 282: 113262, doi: 10.1016/j.rse.2022.113262. doi: 10.1016/j.rse.2022.113262

[36]	Nelson R M. 2000. Prediction of diurnal change in 10-h fuel stick moisture content. Canadian Journal of Forest Research-Revue Canadienne De Recherche Forestiere, 30(7): 1071-1087. doi: 10.1139/x00-032

[37]	Nieto H, Aguado I, Chuvieco E, et al. 2010. Dead fuel moisture estimation with MSG-SEVIRI data. Retrieval of meteorological data for the calculation of the equilibrium moisture content. Agricultural and Forest Meteorology, 150(7-8): 861-870. doi: 10.1016/j.agrformet.2010.02.007

[38]	Petermann J S, Buzhdygan O Y. 2021. Grassland biodiversity. Current Biology, 31(19): 1195-1201.

[39]	Podur J, Martell D L, Csillag F. 2003. Spatial patterns of lightning-caused forest fires in Ontario, 1976-1998. Ecological Modelling, 164(1): 1-20.

[40]	Qi Y, Dennison P E, Spencer J, et al. 2013. Monitoring live fuel moisture using soil moisture and remote sensing proxies. Fire Ecology, 8(3): 71-87. doi: 10.4996/fireecology.0803071

[41]	Rakhmatulina E, Stephens S, Thompson S. 2021. Soil moisture influences on Sierra Nevada dead fuel moisture content and fire risks. Forest Ecology and Management, 496: 119379, doi: 10.1016/j.foreco.2021.119379. doi: 10.1016/j.foreco.2021.119379

[42]	Resco de Dios V, Fellows A W, Nolan R H, et al. 2015. A semi-mechanistic model for predicting the moisture content of fine litter. Agricultural and Forest Meteorology, 203: 64-73. doi: 10.1016/j.agrformet.2015.01.002

[43]	Resco de Dios V, Hedo J, Cunill Camprubí À, et al. 2021. Climate change induced declines in fuel moisture may turn currently fire-free Pyrenean mountain forests into fire-prone ecosystems. Science of the Total Environment, 797: 149104, doi: 10.1016/j.scitotenv.2021.149104. doi: 10.1016/j.scitotenv.2021.149104

[44]	Schunk C, Wastl C, Leuchner M, et al. 2017. Fine fuel moisture for site- and species-specific fire danger assessment in comparison to fire danger indices. Agricultural and Forest Meteorology, 234-235: 31-47.

[45]	Sharma S, Carlson J D, Krueger E S, et al. 2021. Soil moisture as an indicator of growing-season herbaceous fuel moisture and curing rate in grasslands. International Journal of Wildland Fire, 30(1): 57-69. doi: 10.1071/WF19193

[46]	Shmuel A, Ziv Y, Heifetz E. 2022. Machine-Learning-based evaluation of the time-lagged effect of meteorological factors on 10-hour dead fuel moisture content. Forest Ecology and Management, 505: 119897, doi: 10.1016/j.foreco.2021.119897. doi: 10.1016/j.foreco.2021.119897

[47]	Slijepcevic A, Anderson W R, Matthews S, et al. 2015. Evaluating models to predict daily fine fuel moisture content in eucalypt forest. Forest Ecology and Management, 335: 261-269. doi: 10.1016/j.foreco.2014.09.040

[48]	Stocks B J, Lawson B D, Alexander M E, et al. 1989. Canadian forest fire danger rating system - an overview. Forestry Chronicle, 65(4): 258-265. doi: 10.5558/tfc65258-4

[49]	Su H Y, Shen W J, Wang J R, et al. 2020. Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests. Forest Ecosystems, 7(1): 64, doi: 10.1186/s40663-020-00276-7. doi: 10.1186/s40663-020-00276-7

[50]	Sun L, Liu Q, Hu T X. 2021. Advances in research on prediction model of moisture content of surface dead fuel in forests. Scientia Silvae Sinicae, 57(4): 142-152. (in Chinese)

[51]	Vinodkumar V, Dharssi I, Yebra M, et al. 2021. Continental-scale prediction of live fuel moisture content using soil moisture information. Agricultural and Forest Meteorology, 307: 108503, doi: 10.1016/j.agrformet.2021.108503. doi: 10.1016/j.agrformet.2021.108503

[52]	Wilson R A. 1985. Observations of extinction and marginal burning states in free burning porous fuel beds. Combustion Science and Technology, 44(3-4): 179-193. doi: 10.1080/00102208508960302

[53]	Xing J J, Qu Z L. 2017. Ground surface fuel moisture content by mixed effects models in Daxing'an Mountains. Journal of North-East Forestry University, 45(3): 58-62. (in Chinese)

[54]	Yebra M, Chuvieco E, Riano D. 2008. Estimation of live fuel moisture content from MODIS images for fire risk assessment. Agricultural and Forest Meteorology, 148(4): 523-536. doi: 10.1016/j.agrformet.2007.12.005

[55]	Yu H Z, Shu L F, Yang G, et al. 2021. Comparison of vapour-exchange methods for predicting hourly twig fuel moisture contents of larch and birch stands in the Daxinganling Region, China. International Journal of Wildland Fire, 30(6): 462-466. doi: 10.1071/WF19184

[56]	Zhang Y L, Zhang H, Jin S. 2015. Effects of season change and rainfall on forecast model accuracy of predicting fine fuels in forests in Pangu Forest Farm. Journal of Central South University of Forestry & Technology, 35(8): 5-12. (in Chinese)

[57]	Zhu L J, Webb G I, Yebra M, et al. 2021. Live fuel moisture content estimation from MODIS: A deep learning approach. ISPRS Journal of Photogrammetry and Remote Sensing, 179: 81-91. doi: 10.1016/j.isprsjprs.2021.07.010

[1]	HAN Qifei, XU Wei, LI Chaofan. Effects of nitrogen deposition on the carbon budget and water stress in Central Asia under climate change[J]. Journal of Arid Land, 2024, 16(8): 1118-1129.

[2]	SUN Hui, ZHAO Yunge, GAO Liqian, XU Mingxiang. Reasonable grazing may balance the conflict between grassland utilization and soil conservation in the semi-arid hilly areas, China[J]. Journal of Arid Land, 2024, 16(8): 1130-1146.

[3]	ZHOU Jiqiong, GONG Jinchao, WANG Pengsen, SU Yingying, LI Xuxu, LI Xiangjun, LIU Lin, BAI Yanfu, MA Congyu, WANG Wen, HUANG Ting, YAN Yanhong, ZHANG Xinquan. Historical tillage promotes grass-legume mixtures establishment and accelerates soil microbial activity and organic carbon decomposition[J]. Journal of Arid Land, 2024, 16(7): 910-924.

[4]	WU Yuechen, ZHU Haili, ZHANG Yu, ZHANG Hailong, LIU Guosong, LIU Yabin, LI Guorong, HU Xiasong. Characterization of alpine meadow surface crack and its correlation with root-soil properties[J]. Journal of Arid Land, 2024, 16(6): 834-851.

[5]	CAO Wenyu, BAI Jianjun, YU Leshan. Grassland-type ecosystem stability in China differs under the influence of drought and wet events[J]. Journal of Arid Land, 2024, 16(5): 615-631.

[6]	LI Ruishen, PEI Haifeng, ZHANG Shengwei, LI Fengming, LIN Xi, WANG Shuai, YANG Lin. Dividing the transit wind speeds into intervals as a favorable methodology for analyzing the relationship between wind speed and the aerodynamic impedance of vegetation in semiarid grasslands[J]. Journal of Arid Land, 2023, 15(8): 887-900.

[7]	ZHANG Hui, Giri R KATTEL, WANG Guojie, CHUAI Xiaowei, ZHANG Yuyang, MIAO Lijuan. Enhanced soil moisture improves vegetation growth in an arid grassland of Inner Mongolia Autonomous Region, China[J]. Journal of Arid Land, 2023, 15(7): 871-885.

[8]	YUAN Shuai, LIU Yongqiang, QIN Yan, ZHANG Kun. Spatiotemporal variation of surface albedo and its influencing factors in northern Xinjiang, China[J]. Journal of Arid Land, 2023, 15(11): 1315-1339.

[9]	XU Mengran, ZHANG Jing, LI Zhenghai, MO Yu. Attribution analysis and multi-scenario prediction of NDVI drivers in the Xilin Gol grassland, China[J]. Journal of Arid Land, 2022, 14(9): 941-961.

[10]	SU Yuan, GONG Yanming, HAN Wenxuan, LI Kaihui, LIU Xuejun. Dependency of litter decomposition on litter quality, climate change, and grassland type in the alpine grassland of Tianshan Mountains, Northwest China[J]. Journal of Arid Land, 2022, 14(6): 691-703.

[11]	LI Panpan, WANG Bing, YANG Yanfen, LIU Guobin. Effects of vegetation near-soil-surface factors on runoff and sediment reduction in typical grasslands on the Loess Plateau, China[J]. Journal of Arid Land, 2022, 14(3): 325-340.

[12]	SU Yuan, MA Xiaofei, GONG Yanming, LI Kaihui, HAN Wenxuan, LIU Xuejun. Contrasting effects of nitrogen addition on litter decomposition in forests and grasslands in China[J]. Journal of Arid Land, 2021, 13(7): 717-729.

[13]	JIN Xiaoming, YANG Xiaogang, ZHOU Zhen, ZHANG Yingqi, YU Liangbin, ZHANG Jinghua, LIANG Runfang. *Ecological stoichiometry and biomass response of Agropyron michnoi* Roshev. under simulated N deposition in a sandy grassland, China**[J]. Journal of Arid Land, 2020, 12(5): 741-751.

[14]	SONG Yongyong, XUE Dongqian, DAI Lanhai, WANG Pengtao, HUANG Xiaogang, XIA Siyou. Land cover change and eco-environmental quality response of different geomorphic units on the Chinese Loess Plateau[J]. Journal of Arid Land, 2020, 12(1): 29-43.

[15]	HU Xiaoxing, Mitsuru HIROTA, Wuyunna, Kiyokazu KAWADA, LI Hao, MENG Shikang, Kenji TAMURA, Takashi KAMIJO. *Responses in gross primary production of Stipa krylovii* and Allium polyrhizum to a temporal rainfall in a temperate grassland of Inner Mongolia, China**[J]. Journal of Arid Land, 2019, 11(6): 824-836.

Viewed

Full text

Abstract

Cited

Shared

Discussed