Comparison of Three Spectral Vegetation Indices in Classifying Land Use/Cover Using Decision Tree

Document Type : Research Paper

Author

Department of Biosystems Engineering/Faculty of Agricultural Sciences/ University of Guilan, /Rasht /Iran

10.22034/saps.2024.61012.3200

Abstract

Background and Objective: The drastic changes of land use in northern provinces of Iran have been one of main issues of the policy-making during the last two decades, and so it is always important to find an appropriate method. The present research aims to evaluate the performance and compare three plant spectral indices for land use/cover classification in Lahijan and improve the obtained results.
Materials and Methods: OLI images of Landsat 8 were used to produce maps of NDVI, LAI and EVI. The classification was done using decision tree and thresholding according to six land uses/covers of the region, and land use/cover maps were developed. To improve the classification performance, a new decision tree was proposed by combining NDVI and DEM.
 
Results: The validation results using the confusion matrix showed that the performance of NDVI with overall accuracy of 87.7% and kappa coefficient of 0.83 was more than the others. The overall accuracy of LAI and EVI was 71.4 and 71.6%, respectively. The kappa coefficients were 0.828, 0.609 and 0.614 respectively. The proposed method increased the overall accuracy by 4.94% and reached 92.60%. It also increased the percentage of true classification in the tea class from 50.75 to 86.87% and in the forest from 95.08 to 98.18%.
 
Conclusions: In areas with dense vegetation, it is possible to improve the results of land use/cover classification by combining NDVI and DEM in a decision tree. The results can be used for quick mapping and detecting of land use/cover of the region.
 

Keywords

Main Subjects

References

Abir FA and Saha R. 2021. Assessment of land surface temperature and land cover variability during winter: a spatio-temporal analysis of pabna municipality in bangladesh. Environmental Challenges, 4: 100167.
Abkar AA, Safdarinezhad A, Zamani M, Sufbaf SR, Gholami Bidkhani N and Ghafari O. 2015. Analyzing and modeling of correlation between LAI and vegetation indices using spectroradiometric observations. Iranian Journal of Remote Sensing & GIS, 7(2): 69-88. (In Persian)
Adjorlolo C, Mutanga O, Cho M and Ismail R. 2012. Challenges and opportunities in the use of remote sensing for c3 and c4 grass species discrimination and mapping. African Journal of Range & Forage Science, 29(2): 47-61.
Alavipanah SK. 2003. Application of remote sensing in earth science. Tehran, University of Tehran. (In Persian)
Alipour F, Aghkhani MH, Abbaspour-Fard MH and Sepehr A. 2014. Demarcation and estimation of agricultural lands using ETM+ imagery data (case study: astan ghods razavi great farm). Journal of Agricultural Machinery, 4(2): 244-254. (In Persian) DOI: 10.22067/jam.v4i2.34827
Andalibi L, Ghorbani A, Moameri M, Hazbavi Z, Nothdurft A, Jafari R and Dadjou F. 2021. Leaf Area Index Variations in Ecoregions of Ardabil Province, Iran. Remote Sensing, 13: 2879.
Arora MK and Mathur S. 2001. Multi-source classification using artificial neural network in a rugged terrain. Geocarto International. 16(3): 37-44.
Attarchi S, Poorrahimi M and Isazade V. 2020. Comparison of spectral indices and object-based classification for built-up area extraction in different urban areas. Geographical Urban planning Research, 8(1): 23-43. (In Persian)
Bernstein LS, Adler-Golden SM, Jin X, Gregor B and Sundberg RL. 2012. Quick atmospheric correction (Quac) code for VNIR-SWIR spectral imagery. algorithm details. 4th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Shanghai, China.
Boegh E, Soegaard H, Broge N, Hasager C, Jensen N Schelde, K and Thomsen A. 2002. Airborne multi-spectral data for quantifying leaf area index, nitrogen concentration and photosynthetic efficiency in agriculture. Remote Sensing of Environment, 81(2-3): 179-193.
Bovolo F, Bruzzone L and Marconcini M. 2008. A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure. IEEE Transactions on Geoscience and Remote Sensing, 46(7): 2070-2082.
Cañete-Salinas P, Zamudio F, Yáñezd M, Gajardo J, Valdés H, Espinosa C, Venegas J, Retamal L, Ortega-Farias S and Acevedo-Opazo C. 2020. Evaluation of models to determine LAI on poplar stands using spectral indices from sentinel-2 satellite images. Ecological Modelling, 428: 109058.
Coffey R. 2013, The difference between “land use” and “land cover”, Michigan State University Extension.
Comber AJ. 2008. Land use or land cover. Journal of Land Use Science. 3(4): 199-201, DOI: 10.1080/17474230802465140
Dihkan M, Guneroglu N, Karsli F and Guneroglu A. 2013. Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique. International Journal of Remote Sensing. 34: 8549–8565.
Fisher P, Comber AJ and Wadsworth R. 2005. Land use and land cover: contradiction or complement. Re-presenting GIS. 85: 98.‏
Friedl MA, Brodley CE and Strahler A. H. 1999. Maximizing land cover classification accuracies produced by decision trees at continental to global scales. IEEE Transactions on Geoscience and Remote Sensing, 37(2): 969-977.
Hou T, Sun W, Chen C, Yang G, Meng X, and Peng J. 2022. Marine floating raft aquaculture extraction of hyperspectral remote sensing images based decision tree algorithm. International Journal of Applied Earth Observation and Geoinformation, 111: 102846.
Houborg R, Soegaard H and Boegh E. 2007. Combining vegetation index and model inversion methods for the extraction of key vegetation biophysical parameters using Terra and Aqua MODIS reflectance data. Remote Sensing of Environment, 106(1): 39-58.
Huang X, Liu J, Zhu W, Atzberger C and Liu Q. 2019. The optimal threshold and vegetation index time series for retrieving crop phenology based on a modified dynamic threshold method. Remote Sensing, 11(23): 2725.
Huete A. 2002. Remote Sensing for Natural Resources Management and Enviromental Monitoring: Manual of remote sensing 3ed, Vol 4, Univercity of Arizona.
Kandrika S and Roy PS. 2008. Land use land cover classification of orissa using multi-temporal IRS-P6 awifs data: a decision tree approach. International Journal of Applied Earth Observation and Geoinformation, 10(2): 186-193.
Kato S and Yamaguchi Y. 2005. Analysis of urban heat-island effect using ASTER and ETM+ data: separation of anthropogenic heat discharge and natural heat radiation from sensible heat flux. Remote Sensing of Environment, 99(1-2): 44-54.
Kheir RB, Abdallah C, Runnstrom M and Martensson U. 2008. Designing erosion management plans in lebanon using remote sensing, GIS and decision-tree modeling. Landscape and Urban Planning, 88(2-4): 54-63.
Komaki CB, Asadikia R and Niknahad Gharmakhar H. 2019. Estimation of vegetation cover percentage and biomass using remote sensing indices (case study: protected areas of southern Alborz, Karaj). RS & GIS for Natural Resources, 10(1): 1-16. (In Persian)
Kumar BP, Babu KR, Anusha BN, Rajasekhar M. 2022. Geo-environmental monitoring and assessment of land degradation and desertification in the semi-arid regions using Landsat 8 OLI / TIRS, LST, and NDVI approach. Environmental Challenges. 8:  100578.
Li H, Wang C, Zhong C, Zhang Z and Liu Q. 2017. Mapping typical urban LULC from landsat imagery without training samples or self-defined parameters. Remote sensing, 9(7): 700.
Liu L and Zhang Y. 2011. Urban heat island analysis using the Landsat TM data and ASTER data: a case study in Hong Kong. Remote sensing, 3(7): 1535-1552.
Lotfian R. 2015. Change detection and predication of urban development in kashan region using CA-Markov and GEOMOD method. Faculty of Natural Resources. Isfahan University of Technology, Isfahan, Iran. (In Persian)
Matsushita B, Yang W, Chen J, Onda Y and Qiu G. 2007. Sensitivity of the enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) to topographic effects: a case study in high-density cypress forest. Sensors, 7(11): 2636-2651.
Mesri A, Rahimi-Ajdadi F and Bagheri I. 2022. Monitoring rice land changes using GIS and RS. Journal of Agricultural Machinery. 12(4): 515-527. (In Persian)
Nguyen TTH and Pham TTT. 2016. Incorporating ancillary data into Landsat 8 image classification process: a case study in Hoa Binh, Vietnam. Environmental Earth Sciences. 75: 430.
Nikpour N, Negaresh H, Fotoohi S, Hosseini SZ and Bahrami S. 2019. Monitoring the trend of vegetation changes one of the most important indicators of land degradation (in Ilam province). Journal of Spatial Analysis Environmental Hazards. 5(4): 21-48. (In Persian)
Pan F, Xi X and Wang C. 2020. A comparative study of water indices and image classification algorithms for mapping inland surface. Remote Sensing, 12: 1611.
Polydoros A and Cartalis C. 2015. Use of earth observation based indices for the monitoring of built-up area features and dynamics in support of urban energy studies. Energy and Buildings, 98: 92-99.
Potapov P, Hansen MC, Kommareddy I, Kommareddy A, Turubanova S, Pickens A, Adusei B, Tyukavina A and Ying Q. 2020. Landsat analysis ready data for global land cover and land cover change mapping. Remote sensing, 12(3): 426.
Rahimi-Ajdadi F and Khani M. 2021. Remote sensing-based detection of tea land losses: the case of Lahijan, Iran. Remote Sensing Applications: Society and Environment, 23: 100568.
Ramos JF, Renza D and Ballesteros LDM. 2018. Evaluation of spectral similarity indices in unsupervised change detection approaches. Dyna, 85(204): 117-126.
Rouse JW, Haas RH, Schell JA and Deerin DW. 1973. Monitoring vegetation systems in the great plains with ERTS. N. SP-351. Ed Third ERTS Symposium. 1: 309- 317. Whastington. NASA
Shammi SA and Meng Q. 2021. Use time series NDVI and EVI to develop dynamic crop growth metrics foryield modeling. Ecological Indicators, 121: 107124.
Thakkar A, Desai V, Patel A and Potdar M. 2014. Land use/land cover classification of remote sensing data and their derived products in a heterogeneous landscape of a Khan-Kali Watershed, Gujarat. Asian Journal of Geoinformatics. 14(4): 1-12.
Xi Y, Thinh NX and Li C. 2019. Preliminary comparative assessment of various spectral indices for built-up land derived from Landsat-8 OLI and Sentinel-2A MSI imageries. European Journal of Remote Sensing, 52(1): 240-252.
Xu H. 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14): 3025-3033.
Xu H. 2010. Analysis of impervious surface and its impact on urban heat environment using the normalized difference impervious surface index (NDISI). Photogrammetric Engineering & Remote Sensing, 76(5): 557-565.
Xu D, Chen B, Shen B, Wang X, Yan Y, Xu L and Xin X. 2019. The classification of grassland types based on object-based image analysis with multisource data. Rangeland Ecology & Management. 72: 318–326.
Yang C, Odvody GN, Fernandez CJ, Landivar JA, Minzenmayer RR and Nichols RL. 2015. Evaluating unsupervised and supervised image classification methods for mapping cotton root rot. Precision Agriculture, 16(2): 201-215.
Zeaiean Firoozabadi P. 2020. Utilization of NDVI, VTCI and WDI indices in analyzing the effects of drought severity and duration on vegetation density in Siminehrood catchment. Applied Researches in Geographical Sciences. 20(59): 371-392.
Zha Y, Gao J and Ni S. 2003. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing, 24(3): 583-594.
Zhang Y, Odeh IO and Han C. 2009. Bi-temporal characterization of land surface temperature in relation to impervious surface area, NDVI and NDBI, using a sub-pixel image analysis. International Journal of Applied Earth Observation and Geoinformation, 11(4): 256-264.
Zhong L, Hawkins T, Biging G and Gong P. 2011. A phenology-based approach to map crop types in the San Joaquin Valley, California. International Journal of Remote Sensing. 32(22): 7777-7804.
Zhu J, Pan Z, Wang H, Huang P, Sun J, Qin F and Liu Z. 2019. An improved multi-temporal and multi-feature tea plantation identification method using Sentinel-2 imagery. Sensors. 19: 2087. doi: 10.3390/s19092087
Journal of Agricultural Science and Sustainable Production
Volume 35, Issue 4
2026
Pages 253-269

Files

Share

How to cite

Statistics