Using nonparametric modeling approaches and remote sensing imagery to estimate ecological welfare forest biomass

Abstract

The spatial distribution of forest biomass is closely related with carbon cycle, climate change, forest productivity, and biodiversity. Efficient quantification of biomass provides important information about forest quality and health. With the rising awareness of sustainable development, the ecological benefits of forest biomass attract more attention compared to traditional wood supply function. In this study, two nonparametric modeling approaches, random forest (RF) and support vector machine were adopted to estimate above ground biomass (AGB) using widely used Landsat imagery in the region, especially within the ecological forest of Fuyang District in Zhejiang Province, China. Correlation analysis was accomplished and model parameters were optimized during the modeling process. As a result, the best performance modeling method RF was implemented to produce an AGB estimation map. The predicted map of AGB in the study area showed obvious spatial variability and demonstrated that within the current ecological forest zone, as well as the protected areas, the average of AGB were higher than the ordinary forest. The quantification of AGB was proven to have a close relationship with the local forest policy and management pattern, which indicated that combining remote-sensing imagery and forest biophysical property would provide considerable guidance for making beneficial decisions.

Keywords

Above ground biomass / Ecological forest / Forest management / Landsat / Random forest

References

[1] Avitabile V, Baccini A, Friedl MA, Schmullius C. Capabilities and limitations of Landsat and land cover data for aboveground woody biomass estimation of Uganda. Remote Sens Environ, 2012, 117: 366-380.

[2] Baret F, Guyot G. Potentials and limits of vegetation indexes for lai and apar assessment. Remote Sens Environ, 1991, 35(2–3): 161-173.

[3] Berner LT, Alexander HD, Loranty MM, Ganzlin P, Mack MC, Davydov SP, Goetz SJ. Biomass allometry for alder, dwarf birch, and willow in boreal forest and tundra ecosystems of far northeastern Siberia and north-central Alaska. For Ecol Manag, 2015, 337: 110-118.

[4] Breiman L. Random forests. Mach Learn, 2001, 45(1): 5-32.

[5] Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol, 2011, 2(3): 1-27.

[6] Crist EP, Cicone RC. A physically-based transformation of thematic mapper data—the TM tasseled cap. IEEE Trans Geosci Remote Sens, 1984, 22(3): 256-263.

[7] Du HQ, Cui RR, Zhou GM, Shi YJ, Xu XJ, Fan WL, Lü YL. The responses of Moso bamboo (Phyllostachys heterocycla var. pubescens) forest aboveground biomass to Landsat TM spectral reflectance and NDVI. Acta Ecol Sin, 2010, 30(5): 257-263.

[8] Du HQ, Zhou GM, Ge HL, Fan WY, Xu XJ, Fan WL, Shi YJ. Satellite-based carbon stock estimation for bamboo forest with a non-linear partial least square regression technique. Int J Remote Sens, 2012, 33(6): 1917-1933.

[9] Du L, Zhou T, Zou ZH, Zhao X, Huang KC, Wu H. Mapping forest biomass using remote sensing and national forest inventory in China. Forests, 2014, 5(6): 1267-1283.

[10] Duane MV, Cohen WB, Campbell JL, Hudiburg T, Turner DP, Weyermann DL. Implications of alternative field-sampling designs on Landsat-based mapping of stand age and carbon stocks in Oregon forests. For Sci, 2010, 56(4): 405-416.

[11] Dube T, Mutanga O. Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa. ISPRS J Photogramm Remote Sens, 2015, 101: 36-46.

[12] Eckert S. Improved forest biomass and carbon estimations using texture measures from worldview-2 satellite data. Remote Sens, 2012, 4(12): 810-829.

[13] Foody GM, Boyd DS, Cutler MEJ. Predictive relations of tropical forest biomass from Landsat TM data and their transferability between regions. Remote Sens Environ, 2003, 85(4): 463-474.

[14] Gao BC. NDWI—a normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens Environ, 1996, 58(3): 257-266.

[15] Gao J, Liu YS. Deforestation in Heilongjiang Province of China, 1896–2000: severity, spatiotemporal patterns and causes. Appl Geogr, 2012, 35(1–2): 345-352.

[16] Guo Y, Li ZY, Zhang X, Chen EX, Bai LN, Tian X, He QS, Feng Q, Li WM (2012) Optimal support vector machines for forest above-ground biomass estimation from multisource remote sensing data. In: Geoscience and remote sensing symposium (IGARSS), 2012 IEEE International, pp 6388–6391

[17] Hame T, Salli A, Andersson K, Lohi A. A new methodology for the estimation of biomass of coniferdominated boreal forest using NOAA AVHRR data. Int J Remote Sens, 1997, 18(15): 3211-3243.

[18] Han N, Du HQ, Zhou GM, Xu XJ, Cui RR, Gu CY. Spatiotemporal heterogeneity of Moso bamboo aboveground carbon storage with Landsat Thematic Mapper images: a case study from Anji County, China. Int J Remote Sens, 2013, 34(14): 4917-4932.

[19] Hirata Y, Tabuchi R, Patanaponpaiboon P, Poungparn S, Yoneda R, Fujioka Y. Estimation of aboveground biomass in mangrove forests using high-resolution satellite data. J For Res, 2014, 19(1): 34-41.

[20] Ji L, Wylie BK, Nossov DR, Peterson B, Waldrop MP, Mcfarland JW, Rover J, Hollingsworth TN. Estimating aboveground biomass in interior Alaska with Landsat data and field measurements. Int J Appl Earth Obs Geoinf, 2012, 18: 451-461.

[21] Kelsey K, Neff J. Estimates of aboveground biomass from texture analysis of Landsat imagery. Remote Sens, 2014, 6(7): 6407-6422.

[22] Koch B. Status and future of laser scanning, synthetic aperture radar and hyperspectral remote sensing data for forest biomass assessment. ISPRS J Photogramm Remote Sens, 2010, 65(6): 581-590.

[23] Labrecque S, Fournier RA, Luther JE, Piercey D. A comparison of four methods to map biomass from Landsat-TM and inventory data in western Newfoundland. For Ecol Manag, 2006, 226(1–3): 129-144.

[24] Latifi H, Fassnacht FE, Hartig F, Berger C, Hernández J, Corvalán P, Koch B. Stratified aboveground forest biomass estimation by remote sensing data. Int J Appl Earth Obs Geoinf, 2015, 38: 229-241.

[25] Lek S, Guégan JF. Artificial neural networks as a tool in ecological modelling, an introduction. Ecol Model, 1999, 120(2–3): 65-73.

[26] Li WH. Degradation and restoration of forest ecosystems in China. For Ecol Manag, 2004, 201(1): 33-41.

[27] Liao YH, Chen HY, Zheng W, Chen CG, Liu LW. Study on community of Fengshui woods and the value of application in the construction of ecological public welfare forest. J Subtrop Resour Environ, 2008, 3(2): 42-48.

[28] Lim K, Treitz P, Wulder M, St-Onge B, Flood M. LiDAR remote sensing of forest structure. Prog Phys Geogr, 2003, 27(1): 88-106.

[29] Liu QX, Chang J, Jiang B, Yuan WG, Qi L, Zhu JZ, Ge Y. The biomass of the evergreen broad-leaved ecological public-welfare forests in Zhejiang, East China. Acta Ecol Sin, 2005, 25(9): 2139-2144.

[30] Lu DS. Aboveground biomass estimation using Landsat TM data in the Brazilian Amazon. Int J Remote Sens, 2005, 26(12): 2509-2525.

[31] Lu DS. The potential and challenge of remote sensing-based biomass estimation. Int J Remote Sens, 2006, 27(7): 1297-1328.

[32] Lu DS, Chen Q, Wang GX, Liu LJ, Li GY, Moran E. A survey of remote sensing-based aboveground biomass estimation methods in forest ecosystems. Int J Digit Earth, 2014, 9(1): 63-105.

[33] Main-Knorn M, Moisen GG, Healey SP, Keeton WS, Freeman EA, Hostert P. Evaluating the remote sensing and inventory-based estimation of biomass in the western Carpathians. Remote Sens, 2011, 3(12): 1427-1446.

[34] Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens, 2011, 66(3): 247-259.

[35] Mutanga O, Adam E, Cho MA. High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. Int J Appl Earth Obs Geoinf, 2012, 18: 399-406.

[36] Návar J. Allometric equations for tree species and carbon stocks for forests of northwestern Mexico. For Ecol Manag, 2009, 257(2): 427-434.

[37] Ohmann JL, Gregory MJ, Roberts HM. Scale considerations for integrating forest inventory plot data and satellite image data for regional forest mapping. Remote Sens Environ, 2014, 151: 3-15.

[38] Pflugmacher D, Cohen WB, Kennedy RE. Using Landsat-derived disturbance history (1972–2010) to predict current forest structure. Remote Sens Environ, 2012, 122: 146-165.

[39] Powell SL, Cohen WB, Healey SP, Kennedy RE, Moisen GG, Pierce KB, Ohmann JL. Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: a comparison of empirical modeling approaches. Remote Sens Environ, 2010, 114(5): 1053-1068.

[40] Qi XK, Wang KL, Zhang CH. Effectiveness of ecological restoration projects in a karst region of southwest China assessed using vegetation succession mapping. Ecol Eng, 2013, 54: 245-253.

[41] Roy PS, Ravan SA. Biomass estimation using satellite remote sensing data—an investigation on possible approaches for natural forest. J Biosci, 1996, 21(4): 535-561.

[42] Roy DP, Wulder MA, Loveland TR, Allen RG, Anderson MC, Helder D, Irons JR, Johnson DM, Kennedy R, Scambos TA. Landsat-8: science and product vision for terrestrial global change research. Remote Sens Environ, 2014, 145: 154-172.

[43] Stow D, Niphadkar M, Kaiser J. MODIS-derived visible atmospherically resistant index for monitoring chaparral moisture content. Int J Remote Sens, 2005, 26(17): 3867-3873.

[44] Tang LN, Shao GF, Dai LM. Roles of digital technology in China’s sustainable forestry development. Int J Sust Dev World Ecol, 2009, 16(2): 94-101.

[45] Teillet PM, Guindon B, Goodenough DG. On the slope-aspect correction of multispectral scanner data. Can J Remote Sens, 1982, 8(2): 84-106.

[46] Tian X, Li ZY, Su ZB, Chen EX, van der Tol C, Li X, Guo Y, Li LH, Ling FL. Estimating montane forest above-ground biomass in the upper reaches of the Heihe River Basin using Landsat-TM data. Int J Remote Sens, 2014, 35(21): 7339-7362.

[47] Vaglio Laurin G, Chen Q, Lindsell JA, Coomes DA, Frate FD, Guerriero L, Pirotti F, Valentini R. Above ground biomass estimation in an African tropical forest with lidar and hyperspectral data. ISPRS J Photogramm Remote Sens, 2014, 89(26): 49-58.

[48] Wang XK, Feng ZW, Ouyang ZY. The impact of human disturbance on vegetative carbon storage in forest ecosystems in China. For Ecol Manag, 2001, 148(1–3): 117-123.

[49] Wang XC, Shao GF, Chen H, Lewis BJ, Qi G, Yu DP, Zhou L, Dai LM. An Application of remote sensing data in mapping landscape-level forest biomass for monitoring the effectiveness of forest policies in Northeastern China. Environ Manag, 2013, 52(3): 612-620.

[50] Xie YC, Sha ZY, Yu M, Bai YF, Zhang L. A comparison of two models with Landsat data for estimating above ground grassland biomass in Inner Mongolia, China. Ecol Model, 2009, 220(15): 1810-1818.

[51] Yang J, Yuan WG, Jiang B, Zhu JR, Wen LN. Effect of environment on biomass of major ecological forest in Zhejiang. J Zhejiang For Sci Technol, 2007, 27(02): 20-23.

[52] Yin RS, Yin GP. China’s primary programs of terrestrial ecosystem restoration: initiation, implementation, and challenges. Environ Manag, 2010, 45(3): 429-441.

[53] Yu DY, Shi PJ, Han GY, Zhu WQ, Du SQ, Xun B. Forest ecosystem restoration due to a national conservation plan in China. Ecol Eng, 2011, 37(9): 1387-1397.

[54] Yuan WG, Jiang B, Ge YJ, Zhu JR, Shen AH. Study on biomass model of key ecological forest in Zhejiang Province. J Zhejiang For Sci Technol, 2009, 29(2): 1-5.

[55] Yuan JG, Niu Z (2008) Evaluation of atmospheric correction using FLAASH. In: 2008 International workshop on earth observation and remote sensing applications, EORSA, pp 1–6

[56] Zhang F, Du Q, Ge HL, Liu AX, Fu WJ, Ji BY. Spatial distribution of forest carbon in Zhejiang Province with geostatistics based on CFI sample plots. Acta Ecol Sin, 2012, 32(16): 5275-5286.

[57] Zhang J, Ge Y, Chang J, Jiang B, Jiang H, Peng CH, Zhu JR, Yuan WG, Qi LZ, Yu SQ. Carbon storage by ecological service forests in Zhejiang Province, subtropical China. For Ecol Manag, 2007, 245(1–3): 64-75.

[58] Zhang J, Huang S, Hogg EH, Lieffers V, Qin Y, He F. Estimating spatial variation in Alberta forest biomass from a combination of forest inventory and remote sensing data. Biogeosciences, 2014, 11(9): 2793-2808.

[59] Zhang XY, Kondragunta S. Estimating forest biomass in the USA using generalized allometric models and MODIS land products. Geophys Res Lett, 2006, 33(9): 370-386.

[60] Zheng DL, Rademacher J, Chen JQ, Crow T, Bresee M, Le Moine J, Ryu SR. Estimating aboveground biomass using Landsat 7 ETM + data across a managed landscape in northern Wisconsin, USA. Remote Sens Environ, 2004, 93(3): 402-411.

[61] Zhu XL, Liu DS. Improving forest aboveground biomass estimation using seasonal Landsat NDVI time-series. ISPRS J Photogramm Remote Sens, 2015, 102: 222-231.