Abstract
The estimation of aboveground biomass (AGB) in agroforestry systems using remote sensing has proliferated in the last decades. Similarly, machine learning is also being used in AGB assessments. This study reviews the applications of remote sensing and machine learning for AGB estimation in agroforestry systems (AFS). A detailed review was conducted using 33 recent papers by extracting and comparing information on agroforestry type, data sources, methodology, and model accuracy. Statistical tests were performed to evaluate the differences in performances. High- and very-high-resolution imageries (less than 2 m) are widely used for AGB assessment because they helped to delineate heterogeneous features of AFS. Object-based image analysis yielded classification accuracy of up to 90 percent in some cases. Random Forest, Stochastic Gradient Boosting, and Support Vector Regression are the most common algorithms used for AGB estimation. However, there are no statistically significant differences in the performance between machine learning and other models. Similarly, scholars incorporated spectral indices with spectral bands, texture, and biophysical variables as covariate categories into AGB estimation models. The study finds no significant differences in results (R-squared) by adding more covariate categories. The accuracy of AGB estimates depends upon multiple factors, such as the spectral and spatial resolution, number and types of covariates, methods for AFS delineation and AGB estimation, and types and sizes of AFS. Despite some of the methodological challenges around measuring understory vegetation, advancements in cloud computing like Google Earth Engine and the availability of high-resolution datasets present opportunities for wider use of remote sensing for biomass estimation of AFS. Remote sensing and machine learning have the potential to estimate aboveground biomass over a large area with high accuracy and contribute to carbon monitoring.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahmad A, Gilani H, Ahmad SR (2021) Forest aboveground biomass estimation and mapping through high-resolution optical satellite imagery—a literature review. Forests 12:914. https://doi.org/10.3390/f12070914
Amani M, Ghorbanian A, Ahmadi SA et al (2020) Google earth engine cloud computing platform for remote sensing big data applications: a comprehensive review. IEEE J Sel Top Appl Earth Observations Remote Sens 13:5326–5350. https://doi.org/10.1109/JSTARS.2020.3021052
Bégué A, Arvor D, Bellon B et al (2018) Remote Sensing and cropping practices: a review. Remote Sens 10:99. https://doi.org/10.3390/rs10010099
Bolívar-Santamaría S, Reu B (2021) Detection and characterization of agroforestry systems in the Colombian Andes using sentinel-2 imagery. Agrofor Syst 95:499–514. https://doi.org/10.1007/s10457-021-00597-8
Bordoloi R, Das B, Tripathi OP et al (2022) Satellite-based integrated approaches to modeling spatial carbon stock and carbon sequestration potential of different land uses of Northeast India. Environ Sustain Indic 13:100166. https://doi.org/10.1016/j.indic.2021.100166
Chave J, Andalo C, Brown S et al (2005) Tree allometry and improved estimation of carbon stocks and balance in tropical forests. Oecologia 145:87–99. https://doi.org/10.1007/s00442-005-0100-x
Chen Q, Lu D, Keller M et al (2015) Modeling and mapping agroforestry aboveground biomass in the Brazilian amazon using airborne lidar data. Remote Sens 8:21. https://doi.org/10.3390/rs8010021
Chen L, Ren C, Zhang B et al (2018) Estimation of forest above-ground biomass by geographically weighted regression and machine learning with sentinel imagery. Forests 9:582. https://doi.org/10.3390/f9100582
Czerepowicz L, Case BS, Doscher C (2012) Using satellite image data to estimate aboveground shelterbelt carbon stocks across an agricultural landscape. Agr Ecosyst Environ 156:142–150. https://doi.org/10.1016/j.agee.2012.05.014
de Almeida CT, Galvão LS, de Aragão LE, OC e, et al (2019) Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. Remote Sens Environ 232:111323. https://doi.org/10.1016/j.rse.2019.111323
Filippi AM, Güneralp İ, Randall J (2014) Hyperspectral remote sensing of aboveground biomass on a river meander bend using multivariate adaptive regression splines and stochastic gradient boosting. Remote Sens Lett 5:432–441. https://doi.org/10.1080/2150704X.2014.915070
Forkuor G, Benewinde Zoungrana J-B, Dimobe K et al (2020) Above-ground biomass mapping in West African dryland forest using Sentinel-1 and 2 datasets - A case study. Remote Sens Environ 236:111496. https://doi.org/10.1016/j.rse.2019.111496
Gatziolis D, Andersen H-Erik (2008) A guide to LIDAR data acquisition and processing for the forests of the Pacific Northwest. In: U.S. Department of Agriculture, Forest Service, Pacific Northwest Research Station, Portland, OR
Garrett HG, Buck L (1997) Agroforestry practice and policy in the United States of America. For Ecol Manage 91:5–15. https://doi.org/10.1016/S0378-1127(96)03884-4
Gonçalves AC, Sousa AMO, Mesquita P (2019) Functions for aboveground biomass estimation derived from satellite images data in Mediterranean agroforestry systems. Agrofor Syst 93:1485–1500. https://doi.org/10.1007/s10457-018-0252-4
Graves SJ, Caughlin TT, Asner GP, Bohlman SA (2018) A tree-based approach to biomass estimation from remote sensing data in a tropical agricultural landscape. Remote Sens Environ 218:32–43. https://doi.org/10.1016/j.rse.2018.09.009
Griscom BW, Adams J, Ellis PW et al (2017) Natural climate solutions. Proc Natl Acad Sci USA 114:11645–11650. https://doi.org/10.1073/pnas.1710465114
Güneralp İ, Filippi AM, Randall J (2014) Estimation of floodplain aboveground biomass using multispectral remote sensing and nonparametric modeling. Int J Appl Earth Obs Geoinf 33:119–126. https://doi.org/10.1016/j.jag.2014.05.004
Hornero A, North PRJ, Zarco-Tejada PJ et al (2021) Assessing the contribution of understory sun-induced chlorophyll fluorescence through 3-D radiative transfer modeling and field data. Remote Sens Environ 253:112195. https://doi.org/10.1016/j.rse.2020.112195
Houghton RA, Unruh JD, Lefebvre PA (1993) Current land cover in the tropics and its potential for sequestering carbon. Global Biogeochem Cycles 7:305–320. https://doi.org/10.1029/93GB00470
Kalita RM, Das AK, Nath AJ (2016) Carbon stock and sequestration potential in biomass of tea agroforestry system in Barak Valley, Assam, North East India. Int J Ecol Environ Sci 42:107–114
Kanmegne Tamga D, Latifi H, Ullmann T et al (2022) Estimation of aboveground biomass in agroforestry systems over three climatic regions in West Africa using sentinel-1, sentinel-2, ALOS, and GEDI data. Sensors 23:349. https://doi.org/10.3390/s23010349
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 Sens 7:10017–10041. https://doi.org/10.3390/rs70810017
Karlson MO, Madelene; Reese, Heather; Bazié, HR; Tankoano, Boalidioa, (2016) Assessing the potential of multiseasonal WorldView-2 imagery for mapping West African agroforestry tree species. Int J Appl Earth Obs Geoinformation 50:80–88. https://doi.org/10.1016/j.jag.2016.03.004
Karlson M, Ostwald M, Bayala J et al (2020) The potential of sentinel-2 for crop production estimation in a smallholder agroforestry landscape burkina faso. Front Environ Sci 8:85. https://doi.org/10.3389/fenvs.2020.00085
Kearney SP, Coops NC, Chan KMA et al (2017) Predicting carbon benefits from climate-smart agriculture: Highresolution carbon mapping and uncertainty assessment in El Salvador. J Environ Manage 202:287–298. https://doi.org/10.1016/j.jenvman.2017.07.039
Ku N-W, Popescu SC (2019) A comparison of multiple methods for mapping local-scale mesquite tree aboveground biomass with remotely sensed data. Biomass Bioenergy 122:270–279. https://doi.org/10.1016/j.biombioe.2019.01.045
Kumar L, Mutunga O (2018) Google earth engine applications since inception: usage, trends, and potential. Remote sensing 10:1509. https://www.mdpi.com/2072-4292/10/10/1509
Laosuwan T, Uttaruk Y (2016) Estimating above ground carbon capture using remote sensing technology in small scale agroforestry areas. AgricultForest 62:253. https://doi.org/10.17707/AgricultForest.62.2.22
Li A, Glenn NF, Olsoy PJ et al (2015) Aboveground biomass estimates of sagebrush using terrestrial and airborne LiDAR data in a dryland ecosystem. Agric for Meteorol 213:138–147. https://doi.org/10.1016/j.agrformet.2015.06.005
Liang Y, Kou W, Lai H et al (2022) Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery. Ecol Indic 142:109286. https://doi.org/10.1016/j.ecolind.2022.109286
Liknes GC, Meneguzzo DM, Kellerman TA (2017) Shape indexes for semi-automated detection of windbreaks in thematic tree cover maps from the central United States. Int J Appl Earth Obs Geoinf 59:167–174. https://doi.org/10.1016/j.jag.2017.03.005
Liu D, Xia F (2010) Assessing object-based classification: advantages and limitations. Remote Sens Lett 1:187–194. https://doi.org/10.1080/01431161003743173
Lourenço P, Godinho S, Sousa A, Gonçalves AC (2021) Estimating tree aboveground biomass using multispectral satellite-based data in Mediterranean agroforestry system using random forest algorithm. Remote Sens Appl: Soc Environ 23:100560. https://doi.org/10.1016/j.rsase.2021.100560
Lu H (2003) Decomposition of vegetation cover into woody and herbaceous components using AVHRR NDVI time series. Remote Sens Environ 86:1–18. https://doi.org/10.1016/S0034-4257(03)00054-3
Lu D, Chen Q, Wang G et al (2016) A survey of remote sensing-based aboveground biomass estimation methods in forest ecosystems. Int J Digit Earth 9:63–105. https://doi.org/10.1080/17538947.2014.990526
Luo S, Wang C, Xi X et al (2017) Fusion of airborne LiDAR data and hyperspectral imagery for aboveground and belowground forest biomass estimation. Ecol Ind 73:378–387. https://doi.org/10.1016/j.ecolind.2016.10.001
Macedo FL, Sousa AMO, Gonçalves AC et al (2018) Above-ground biomass estimation for Quercus rotundifolia using vegetation indices derived from high spatial resolution satellite images. Eur J Remote Sens 51:932–944. https://doi.org/10.1080/22797254.2018.1521250
Mascaro J, Asner GP, Knapp DE et al (2014) A tale of two “Forests”: random forest machine learning aids tropical forest carbon mapping. PLoS ONE 9:e85993. https://doi.org/10.1371/journal.pone.0085993
Matese A, Berton A, Chiarello V et al (2021) Determination of riparian vegetation biomass from an unmanned aerial Vehicle (UAV). Forests 12:1566. https://doi.org/10.3390/f12111566
Maxwell AE, Warner TA, Fang F (2018) Implementation of machine-learning classification in remote sensing: an applied review. Int J Remote Sens 39:2784–2817. https://doi.org/10.1080/01431161.2018.1433343
Morais TG, Teixeira RFM, Figueiredo M, Domingos T (2021) The use of machine learning methods to estimate aboveground biomass of grasslands: a review. Ecol Ind 130:108081. https://doi.org/10.1016/j.ecolind.2021.108081
Naidoo L, Mathieu R, Main R et al (2016) L-band synthetic aperture radar imagery performs better than optical datasets at retrieving woody fractional cover in deciduous, dry savannahs. Int J Appl Earth Obs Geoinf 52:54–64. https://doi.org/10.1016/j.jag.2016.05.006
Nair PKR, Nair VD, Mohan Kumar B, Showalter JM (2010) Carbon sequestration in agroforestry systems. In: Advances in agronomy. Elsevier, pp 237–307
Pádua L, Vanko J, Hruška J et al (2017) UAS, sensors, and data processing in agroforestry: a review towards practical applications. Int J Remote Sens 38:2349–2391. https://doi.org/10.1080/01431161.2017.1297548
Pandey PC, Anand A, Srivastava PK (2019) Spatial distribution of mangrove forest species and biomass assessment using field inventory and earth observation hyperspectral data. Biodivers Conserv 28:2143–2162. https://doi.org/10.1007/s10531-019-01698-8
Pham TD, Yokoya N, Xia J et al (2020) Comparison of machine learning methods for estimating mangrove above-ground biomass using multiple source remote sensing data in the Red River Delta biosphere reserve. Vietnam Remote Sens 12:1334. https://doi.org/10.3390/rs12081334
Prasondita E, Nakagoshi N, Suwandana E (2019) Ecological study of aboveground biomass and plant species diversity in complex agroforestry sites, Lampung, Indonesia. The 7th Annual Meeting 27
Rizvi RH, Newaj R, Prasad R, et al (2016) Assessment of carbon storage potential and area under agroforestry systems in Gujarat Plains by Co2 fix model and remote sensing techniques. Curr Sci 110:2005. https://doi.org/10.18520/cs/v110/i10/2005-2011
Safari A, Sohrabi H, Powell S, Shataee S (2017) A comparative assessment of multi-temporal Landsat 8 and machine learning algorithms for estimating aboveground carbon stock in coppice oak forests. Int J Remote Sens 38:6407–6432. https://doi.org/10.1080/01431161.2017.1356488
Sankar S, Lewis M, Hosein P (2022) Above ground biomass estimation of a cocoa plantation using machine learning. 2022 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, Orlando, FL, USA, pp 1–8
Schneider LC, Lerner AM, McGroddy M, Rudel T (2018) Assessing carbon sequestration of silvopastoral tropical landscapes using optical remote sensing and field measurements. J Land Use Sci 13:455–472. https://doi.org/10.1080/1747423X.2018.1542463
Singh M, Malhi Y, Bhagwat S (2014) Evaluating land use and aboveground biomass dynamics in an oil palm–dominated landscape in Borneo using optical remote sensing. J Appl Remote Sens 8:083695.https://doi.org/10.1117/1.JRS.8.083695
Smith LJ, Doldirina C (2008) Remote sensing: a case for moving space data towards the public good. Space Policy 24:22–32. https://doi.org/10.1016/j.spacepol.2007.12.002
Strahler AH, Jupp DLB (1990) Modeling bidirectional reflectance of forests and woodlands using boolean models and geometric optics. Remote Sens Environ 34:153–166. https://doi.org/10.1016/0034-4257(90)90065-T
Su H, Shen W, Wang J et al (2020) Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests. Forest Ecosystems 7:64. https://doi.org/10.1186/s40663-020-00276-7
Suchenwirth L, Stümer W, Schmidt T et al (2014) Large-scale mapping of carbon stocks in riparian forests with self-organizing maps and the k-nearest-neighbor algorithm. Forests 5:1635–1652. https://doi.org/10.3390/f5071635
Tian Y, Huang H, Zhou G et al (2021) Aboveground mangrove biomass estimation in Beibu Gulf using machine learning and UAV remote sensing. Sci Total Environ 781:146816. https://doi.org/10.1016/j.scitotenv.2021.146816
Timothy D, Onisimo M, Cletah S et al (2016) Remote sensing of aboveground forest biomass: a review. Trop Ecol 57:125–132
Turner W, Rondinini C, Pettorelli N et al (2015) Free and open-access satellite data are key to biodiversity conservation. Biol Cons 182:173–176. https://doi.org/10.1016/j.biocon.2014.11.048
Udawatta RP, Jose S (2012) Agroforestry strategies to sequester carbon in temperate North America. Agrofor Syst 86:225–242. https://doi.org/10.1605/01.301-0020846221.2012
Unruh J, Houghton R, Lefebvre P (1993) Carbon storage in agroforestry: an estimate for sub-Saharan Africa. Clim Res 3:39–52. https://doi.org/10.3354/cr003039
Wang Z, Liu L, Peng D et al (2016) Estimating woody aboveground biomass in an area of agroforestry using airborne light detection and ranging and compact airborne spectrographic imager hyperspectral data: individual tree analysis incorporating tree species information. J Appl Remote Sens 10:036007. https://doi.org/10.1117/1.JRS.10.036007
Wang Y, Pyörälä J, Liang X et al (2019) In situ biomass estimation at tree and plot levels: what did data record and what did algorithms derive from terrestrial and aerial point clouds in boreal forest. Remote Sens Environ 232:111309. https://doi.org/10.1016/j.rse.2019.111309
Wilson M, Lovell S (2016) Agroforestry—the next step in sustainable and resilient agriculture. Sustainability 8:574. https://doi.org/10.3390/su8060574
Wu C, Shen H, Shen A et al (2016) Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery. J Appl Remote Sens 10:035010. https://doi.org/10.1117/1.JRS.10.035010
Xie J, Wang C, Ma D et al (2022) Generating spatiotemporally continuous grassland aboveground biomass on the tibetan plateau through PROSAIL model inversion on google earth engine. IEEE Trans Geosci Remote Sens 60:1–10. https://doi.org/10.1109/TGRS.2022.3227565
Yang Z, Li W, Chen Q et al (2019) A scalable cyberinfrastructure and cloud computing platform for forest aboveground biomass estimation based on the google earth engine. Null 12:995–1012. https://doi.org/10.1080/17538947.2018.1494761
Yasen K, Koedsin W (2015) Estimating aboveground biomass of rubber tree using remote sensing in Phuket Province, Thailand. J Med Bioeng 4:451–456
Zhang Y, Ma J, Liang S et al (2020) An evaluation of eight machine learning regression algorithms for forest aboveground biomass estimation from multiple satellite data products. Remote Sensing 12:4015. https://doi.org/10.3390/rs12244015
Zhou X, Brandle JR, Awada TN et al (2011) The use of forest-derived specific gravity for the conversion of volume to biomass for open-grown trees on agricultural land. Biomass Bioenerg 35:1721–1731. https://doi.org/10.1016/j.biombioe.2011.01.019
Acknowledgements
This material is based upon work supported by the University of Missouri Center for Agroforestry and the U.S. Department of Agriculture, Agricultural Research Service, under agreement No. 58-6020-0-007. Any opinions, findings, conclusion, or recommendations expressed in this publication are those of the authors and do not necessarily reflect the view of the U.S. Department of Agriculture.
Funding
The authors have no financial or non-financial interests that are directly or indirectly related to the work submitted for publication.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Thapa, B., Lovell, S. & Wilson, J. Remote sensing and machine learning applications for aboveground biomass estimation in agroforestry systems: a review. Agroforest Syst 97, 1097–1111 (2023). https://doi.org/10.1007/s10457-023-00850-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10457-023-00850-2