Estimation and digital mapping of grassland belowground biomass in the Altay region， China， based on machine learning

doi:10.11686/cyxb2021481

Abstract

Abstract:

This research investigated the spatial pattern of grassland belowground biomass （BGB） in the Altay region. Ecological indicators and BGB during the peak season （June-August） in 2015 were surveyed. Based on representative information for specific locations， terrain types， climate， and soil and plant factors， a forecasting model involving machine learning was developed to estimate BGB in the 0-30 cm soil layers in the study area. Based on this eatimation model， the spatial pattern was then obtained by the spatial interpolation method for digital mapping of BGB. It was found that： 1） The support vector machine model （SVM） had a higher estimation accuracy than an alternative partial least squares regression model and random forest model， also tested. The R² values from the SVM model for verification data were 0.77， 0.67 and 0.69， respectively in the 0-10 cm， 10-20 cm and 20-30 cm soil layers， with accompanying root mean square error （RMSE） values of 246.56， 98.81 and 63.58 g·m^-2， respectively. The outputs of three spatial interpolations indicated that an inverse distance weighting （IDW） method performed better than radial basis function and tension spline methods. 2） We further compared the output accuracy of different combinations of estimation model and spatial interpolation method. This comparison showed that SVM+IDW was a dependable combination of estimation model and spatial interpolation method for estimating the spatial pattern of BGB in the Altay region. The R² values of the digital map obtained from this combination in the 0-10 cm， 10-20 cm， and 20-30 cm soil layers were， respectively， 0.73， 0.64， and 0.60， and the RMSE values were 269.73， 108.14 and 73.01 g·m^-2. 3） The mean value of BGB in Altay region was 1265 g·m^-2， which was twice that of the average for China and comparable to the global mean value. Temperate meadow steppe had the largest BGB， with a mean value of 2908.50 g·m^-2， the temperate deserts hold the least biomass， estimated at 776.84 g·m^-2. The BGB in the whole region is 1.27×10⁸ t （≈0.13 Pg）. Our modelling identified a strong spatial variability that decreased from the north to the south and from the mountains to plains.

Key words: grassland belowground biomass, Altay region, machine learning, spatial interpolation, SVM model, IDW interpolation, digital mapping

Fang-zhen LI, Hua-ping ZHONG, Ke-hui OUYANG, Xiao-min ZHAO, Yu-zhe LI. Estimation and digital mapping of grassland belowground biomass in the Altay region， China， based on machine learning[J]. Acta Prataculturae Sinica, 2022, 31(8): 13-23.

Figures/Tables 8

References 39

1	Wang J， Sun J， Yu Z， et al. Vegetation type controls root turnover in global grasslands. Global Ecology and Biogeography， 2019， 28（4）： 442-455.
2	Sun Y， Yang Y， Zhao X， et al. Global patterns and climatic drivers of above- and belowground net primary productivity in grasslands. Science China Life Sciences， 2021， 64（5）： 739-751.
3	Pucheta E， Bonamici I， Cabido M， et al. Below-ground biomass and productivity of a grazed site and a neighbouring ungrazed exclosure in a grassland in central Argentina. Austral Ecology， 2004（29）： 201-208.
4	Zhang D D， Wang X M， Zan M. Estimation of vegetation aboveground biomass in the Wei-Ku Oasis based on Landsat 8 OLI images. Acta Prataculturae Sinica， 2021， 30（11）： 1-12.
	张殿岱，王雪梅，昝梅. 基于Landsat 8 OLI影像的渭-库绿洲植被地上生物量估算. 草业学报， 2021， 30（11）： 1-12.
5	Ghasemi N， Sahebi M R， Mohammadzadeh A. A review on biomass estimation methods using synthetic aperture radar data. International Journal of Geomatics and Geosciences， 2011， 1（4）： 776-788.
6	Sinha S， Jeganathan C， Sharma L K， et al. A review of radar remote sensing for biomass estimation. International Journal of Environmental Science and Technology， 2015， 12（5）： 1779-1792.
7	Tang Z， Deng L， An H， et al. Bayesian method predicts belowground biomass of natural grasslands. Ecoscience， 2017， 24（3）： 1-10.
8	Fierer N， Strickland M S， Liptzin D， et al. Global patterns in belowground communities. Ecology Letters， 2009， 12（11）： 1238-1249.
9	Fan J W， Wang K， Harris W， et al. Allocation of vegetation biomass across a climate-related gradient in the grasslands of Inner Mongolia. Journal of Arid Environments， 2009， 73（4/5）： 521-528.
10	Lopatin J， Kattenborn T， Galleguillos M， et al. Using aboveground vegetation attributes as proxies for mapping peatland belowground carbon stocks. Remote Sensing of Environment， 2019， 231： 111217.
11	Luo W， Jiang Y， Lv X， et al. Patterns of plant biomass allocation in temperate grasslands across a 2500-km transect in northern China. PLoS One， 2013， 8（8）： e71749.
12	Fiala K， Tůma I， Holub P. Interannual variation in root production in grasslands affected by artificially modified amount of rainfall. Scientific World Journal， 2012， 2012： 805298.
13	Gill R A， Kelly R H， Parton W J， et al. Using simple environmental variables to estimate below- ground productivity in grasslands. Global Ecology & Biogeography， 2002， 11： 79-86.
14	Qiao Y X， Zhu H Z， Zhong H P， et al. Spatial interpolation analysis of grassland below-ground biomass in the Inner Mongolia Autonomous Region， China. Acta Prataculturae Sinica， 2016， 25（6）： 1-12.
	乔宇鑫，朱华忠，钟华平，等. 内蒙古草地地下生物量空间格局分析. 草业学报， 2016， 25（6）： 1-12.
15	Li H， Jia S， Le Z. Quantitative analysis of soil total nitrogen using hyperspectral imaging technology with extreme learning machine. Sensors， 2019， 19（20）： 4355.
16	O’Connell J L， Byrd K B， Kelly M. A hybrid model for mapping relative differences in belowground biomass and root∶shoot ratios using spectral reflectance， foliar N and plant biophysical data within coastal marsh. Remote Sensing， 2015， 7（12）： 16480-16503.
17	Zhao H H， Li X D， Zhang D， et al. Aboveground biomass in grasslands in Qinghai Province estimated from MODIS data and its influencing factors. Acta Prataculturae Sinica， 2020， 29（12）： 5-16.
	赵慧芳，李晓东，张东，等. 基于MODIS数据的青海省草地地上生物量估算及影响因素研究. 草业学报， 2020， 29（12）： 5-16.
18	Bernhardt-Römermann M， Römermann C， Sperlich S， et al. Explaining grassland biomass-the contribution of climate， species and functional diversity depends on fertilization and mowing frequency. Journal of Applied Ecology， 2011， 48（5）： 1088-1097.
19	Schenk H J， Jackson R B. Rooting depths， lateral root spreads and below-ground/above-ground allometries of plants in water-limited ecosystems. Journal of Ecology， 2002， 90（3）： 480-494.
20	Ma X X， Yan Y， Lu X Y， et al. Dynamics of belowground biomass and its relationship with soil moisture in alpine grassland on the North Tibetan Plateau. Ecology and Environmental Sciences， 2016， 25（2）： 189-195.
	马星星，鄢燕，鲁旭阳，等.藏北高寒草地地下生物量特征及其与土壤水分的关系. 生态环境学报， 2016， 25（2）： 189-195.
21	Zhu B W， Zhou H K， Xu Y X， et al. Study on seasonal dynamics of biomass in meadow grassland of north shore of Qinghai Lake. Pratacultural Science， 2008， 25（12）： 62-66.
	朱宝文，周华坤，徐有绪，等. 青海湖北岸草甸草原牧草生物量季节动态研究. 草业科学， 2008， 25（12）： 62-66.
22	Peng S， Piao S， Ciais P， et al. Asymmetric effects of daytime and night-time warming on northern hemisphere vegetation. Nature， 2013， 501： 88-92.
23	Mokany K， Raison R J， Prokushkin A S. Critical analysis of root∶shoot ratios in terrestrial biomes. Global Change Biology， 2006， 12： 84-96.
24	Leonid U， Yuriy R， Vasiliy U， et al. Impact of climate and grazing on biomass components of Eastern Russia typical steppe. Journal of Integrative Agriculture， 2014， 13（6）： 1183-1192.
25	Didiano T J， Johnson M T J， Duval T P. Disentangling the effects of precipitation amount and frequency on the performance of 14 grassland species. PLoS One， 2016， 11（9）： e162310.
26	Xia J， Liu S， Liang S， et al. Spatio-temporal patterns and climate variables controlling of biomass carbon stock of global grassland ecosystems from 1982 to 2006. Remote Sensing， 2014， 6（3）： 1783-1802.
27	Wang L， Niu K， Yang Y， et al. Patterns of above- and belowground biomass allocation in China’s grasslands： Evidence from individual-level observations. Science China Life Sciences， 2010， 53（7）： 851-857.
28	Hu T， Sørensen P， Wahlström E M， et al. Root biomass in cereals， catch crops and weeds can be reliably estimated without considering aboveground biomass. Agriculture， Ecosystems & Environment， 2018， 251： 141-148.
29	Yang Y， Dou Y， An S. Environmental driving factors affecting plant biomass in natural grassland in the Loess Plateau， China. Ecological Indicators， 2017， 82： 250-259.
30	Li Y Z， Shao Q Q， Fan J W， et al. Effects of grassland cultivation on ecosystem water use efficiency in a grazed temperate grassland area. Acta Prataculturae Sinica， 2019， 28（10）： 110-121.
	李愈哲，邵全琴，樊江文，等. 开垦对放牧温性草原生态系统水分利用效率的影响. 草业学报， 2019， 28（10）： 110-121.
31	Yuen J Q， Ziegler A D， Webb E L， et al. Uncertainty in below-ground carbon biomass for major land covers in Southeast Asia. Forest Ecology and Management， 2013， 310： 915-926.
32	Lauenroth W K， Wade A A， Williamson M A， et al. Uncertainty in calculations of net primary production for grasslands. Ecosystems， 2006， 9（5）： 843-851.
33	Wilson C H， Strickland M S， Hutchings J A， et al. Grazing enhances belowground carbon allocation， microbial biomass， and soil carbon in a subtropical grassland. Global Change Biology， 2018， 24（7）： 2997-3009.
34	Ren Q， Ai Y， Hu J， et al. Effects of different yak grazing intensities on soil land plant biomass in an alpine meadow on the Qinghai-Tibetan Plateau. Acta Ecologica Sinica， 2021， 41（17）： 6862-6870.
	任强，艾鷖，胡健，等. 不同强度牦牛放牧对青藏高原高寒草地土壤和植物生物量的影响. 生态学报， 2021， 41（17）： 6862-6870.
35	Loretta C， Johnson J R M. Fire and grazing regulate belowground processes in tallgrass prairie. Ecology， 2001， 82（12）： 3377-3389.
36	Frank D A. Drought effects on above- and belowground production of a grazed temperate grassland ecosystem. Oecologia， 2007， 152（1）： 131-139.
37	Hao Y， He Z. Effects of grazing patterns on grassland biomass and soil environments in China： A meta-analysis. PLoS One， 2019， 14（4）： e215223.
38	Acosta-Gallo B， Casado M A， Montalvo J， et al. Allometric patterns of below-ground biomass in Mediterranean grasslands. Plant Biosystems， 2011， 145（3）： 584-595.
39	Harpole W S， Sullivan L L， Lind E M， et al. Addition of multiple limiting resources reduces grassland diversity. Nature， 2016， 537： 93-96.

指标 Index	训练数据Training data （n=130）			验证数据Verification data （n=55）
指标 Index	0~10 cm	10~20 cm	20~30 cm	0~10 cm	10~20 cm	20~30 cm
最小值Min （g·m^-2）	180.68	107.42	29.46	169.87	104.76	28.85
最大值Max （g·m^-2）	2485.20	862.95	459.54	2401.21	808.69	484.32
均值Mean （g·m^-2）	809.57	326.41	150.40	815.11	329.17	162.15
中位值Median （g·m^-2）	640.69	265.79	127.52	726.24	266.06	131.59
偏度Skewness	0.96	0.89	0.95	1.12	0.85	0.82

指标 Index	训练数据Training data （n=130）			验证数据Verification data （n=55）
指标 Index	0~10 cm	10~20 cm	20~30 cm	0~10 cm	10~20 cm	20~30 cm
最小值Min （g·m^-2）	180.68	107.42	29.46	169.87	104.76	28.85
最大值Max （g·m^-2）	2485.20	862.95	459.54	2401.21	808.69	484.32
均值Mean （g·m^-2）	809.57	326.41	150.40	815.11	329.17	162.15
中位值Median （g·m^-2）	640.69	265.79	127.52	726.24	266.06	131.59
偏度Skewness	0.96	0.89	0.95	1.12	0.85	0.82

草地类型Type	面积Area （km²）	地下生物量Belowground biomass （t）	比例Ratio （%）
低地草甸Lowland meadow	2370	3.26×10⁶	2.58
温性荒漠Temperate desert	70021	5.44×10⁷	42.97
温性荒漠草原Temperate desert steppe	4543	5.26×10⁶	4.16
温性草原Temperate steppe	9079	1.54×10⁷	12.19
温性草甸草原Temperate meadow steppe	7725	2.04×10⁷	16.08
山地草甸Mountain meadow	6099	1.41×10⁷	11.17
高寒草甸Alpine meadow	4725	1.37×10⁷	10.86
合计Total	-	1.27×10⁸（≈0.13 Pg）	100.00

草地类型Type	面积Area （km²）	地下生物量Belowground biomass （t）	比例Ratio （%）
低地草甸Lowland meadow	2370	3.26×10⁶	2.58
温性荒漠Temperate desert	70021	5.44×10⁷	42.97
温性荒漠草原Temperate desert steppe	4543	5.26×10⁶	4.16
温性草原Temperate steppe	9079	1.54×10⁷	12.19
温性草甸草原Temperate meadow steppe	7725	2.04×10⁷	16.08
山地草甸Mountain meadow	6099	1.41×10⁷	11.17
高寒草甸Alpine meadow	4725	1.37×10⁷	10.86
合计Total	-	1.27×10⁸（≈0.13 Pg）	100.00

[1]	Ge-xia QIN, Jing WU, Chun-bin LI, Zhen-xia JI, Zheng-chao QIU, Ying LI. Inversion of grassland aboveground biomass in Tianzhu Zangzu Autonomous County based on a machine learning algorithm [J]. Acta Prataculturae Sinica, 2022, 31(4): 177-188.
[2]	Hui-long LIN, Di FAN, Qi-sheng FENG, Tian-gang LIANG. New focus for the study of the Comprehensive Sequential Classification System for grassland： A review from 2008 to 2020 and prospects for future research [J]. Acta Prataculturae Sinica, 2021, 30(10): 201-213.
[3]	Hui-xia LIU, Yi-qiang DONG, Yu-xuan CUI, Xing-hong LIU, Pan-xing HE, Qiang SUN, Zong-jiu SUN. Environmental factors influencing soil organic carbon and its characteristics in desert grassland in Altay， Xinjiang [J]. Acta Prataculturae Sinica, 2021, 30(10): 41-52.
[4]	QIAO Yu-Xin, ZHU Hua-Zhong, SHAO Xiao-Ming, ZHONG Hua-Ping, ZHOU Li-Lei, WU Zhao-Wen. Automatic classification of grassland type in Xinjiang Ili based on spatial interpolation of remote sensing and other data [J]. Acta Prataculturae Sinica, 2017, 26(10): 30-45.