Maple Species Identification Based On Hyperspectral Imaging Time Series

Year 2025, Volume: 11 Issue: 2, 81 - 94

Pavel Dmitriev , Boris Kozlovsky , Anastasiya Dmitrieva

Abstract

The aim of the study was to identify Acer campestre L., A. negundo L., and A. saccharinum L. from time-series hyperspectral data. Maple leaves were subjected to Hyperspectral Imaging (HSI) in laboratory conditions every 7-10 days for two years. Random forest (RF), correlation analysis, principal component analysis (PCA), PCA-RF and Gini index were used to determine significant spectral bands for species classification. This paper demonstrates that maple species can be accurately classified during specific periods of the growing season with a success rate exceeding 90%. These periods can vary from year to year. Research has demonstrated that using seven spectral bands is adequate for classifying maple species, while using twenty spectral bands can maximize accuracy. The repeatability of the obtained results confirms their representativeness over time and when using different methods of data processing.

Keywords

Spectral bands , Acer , photosynthetic pigments , remote sensing , random forest

Ethical Statement

All authors have read, understood, and have complied as applicable with the statement on "Ethical responsibilities of Authors" as found in the Instructions for Authors.

Supporting Institution

Southern Federal University

Project Number

The project was supported by the Russian Science Foundation under grant No. 24-24-00405, https://rscf.ru/project/24-24-00405/, and performed in Southern Federal University (Rostov-on-Don, Russian Federation)

References

• Al-Dahoud, A., Fezari, M., Alkhatib, A.A., Soltani, M. N., Al- Dahoud, A. 2023. Forest fire detection system based on low-cost wireless sensor network and internet of things. WSEAS Transactions on Environment and Development, 19:506-513.
• Aasen, H., Burkart, А., Bolten, A., Bareth, G. 2015. Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: From camera calibration to quality assurance. JPRS, 108:245-259. https://doi.org/ 10.1016/j.isprsjprs.2015.08.002
• Ahmed, S., Nicholson, C.E., Muto, P., Perry, J.J., Dean, J.R. 2021. Applied aerial spectroscopy: A case study on remote sensing of an ancient and semi-natural woodland. PLoS ONE, 16(11):e0260056. https://doi.org/10.1371/journal.pone.0260056
• Bareth, G., Aasen, H., Bendig, J., et al. 2015. Low-weight and UAV-based hyperspectral full-frame cameras for monitoring crops: Spectral comparison with portable spectroradiometer measurements. Photogramm Fernerkundung Geoinf, 69-79. https://doi.org/ 10.1127/PFG/2015/0256
• Berra, E.F., Gaulton, R., Barr, S. 2019. Assessing spring phenology of a temperate woodland: A multiscale comparison of ground, unmanned aerial vehicle and Landsat satellite observations. Remote Sensing of Environment, 223:229-242. https://doi.org/10.1016/ j.rse.2019.01.010
• Blackburn, G.A. 1998. Quantifying chlorophylls and caroteniods at leaf and canopy scales: An evaluation of some hyperspectral approaches. Remote Sens of Environ, 66(3):273–285. https://doi.org/10.1016/ S0034- 4257(98)00059-5
• Bozo, M., Aptoula, E., Çataltepe, Z. 2020. A Discriminative Long Short Term Memory Network with Metric Learning Applied to Multispectral Time Series Classification. J Imaging, 6:68. https://doi.org/ 10.3390/jimaging6070068
• Carter, G.A. 1994. Ratios of leaf reflectances in narrow wavebands as indicators of plant stress. Int J of Remote Sens, 15(3):697–703. https://doi.org/10. 1080/01431169408954109
• Cattell, R.B. 1966. The Scree test for the number of factors. Multivariate Behavioral Research, 1:245–276. http://dx.doi.org/10.1207/s15327906mbr0102 _10
• Chianucci, F., Disperati, L., Guzzi, D., et al. 2016. Estimation of canopy attributes in beech forests using true colour digital images from a small fixed-wing UAV. International Journal of Applied Earth Observation and Geoinformation, 47:60-68. https://doi.org/10.1016/j.jag.2015.12.005
• Collin, F.D., Durif, G., Raynal, L., et al. 2020. Extending Approximate Bayesian Computation with Supervised Machine Learning to infer demographic history from genetic polymorphisms using DIYABC Random Forest. Molecular Ecology Resources, 21(8): 2598-2613. https://doi.org/10.1111/1755-0998.13413
• Colomina, I., Molina, P. 2014. Unmanned aerial systems for photogrammetry and remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 92:79-97. https://doi.org/10.1016/j.isprsjprs. 2014.02.013
• Dadon, A., Mandelmilch, M., Ben-Dor, E., Sheffer, E. 2019. Sequential PCA-based Classification of Mediterranean Forest Plants using Airborne Hyperspectral Remote Sensing. Remote Sens, 11:2800. https://doi.org/10.3390/rs11232800
• Dainelli, R., Toscano, P., Di Gennaro, S.F., Matese, A. 2021 Recent Advances in Unmanned Aerial Vehicle Forest Remote Sensing—A Systematic Review. Part I: A General Framework. Forests, 12:327. https://doi.org/10.3390/f12030327
• Dash, J.P., Pearse, G.D., Watt, M.S. 2018. UAV Multispectral Imagery Can Complement Satellite Data for Monitoring Forest Health. Remote Sens, 10:1216. https://doi.org/10.3390/rs10081216
• Dmitriev, P.A., Kozlovsky, B.L., Dmitrieva, A.A., Varduni, T.V. 2023. Maple species identification based on leaf hyperspectral imaging data. Remote Sensing Applications: Society and Environment, 30:2352-9385. https://doi.org/10.1016/j.rsase.2023. 100964
• Dmitriev, P., Kozlovsky, B., Dmitrieva, A., Varduni, T. 2024. Identification of the Leaves of Ulmus pumila L., Tilia cordata Mill. and Acer campestre L. Using Vegetation Indices. European Journal of Forest Engineering, 10(1), 54-66. https://doi.org/10.33904/ ejfe.1430606
• Fang, F., McNeil, B.E., Warner, T.A., Maxwell, A.E. 2018. Combining high spatial resolution multi-temporal satellite data with leaf-on LiDAR to enhance tree species discrimination at the crown level. International Journal of Remote Sensing, 39:23. https://doi.org/10.1080/01431161.2018. 1504343
• Fassnacht, F.E., Latifi, H., Stereńczak, K., Lefsky, M. 2016. Review of studies on tree species classification from remotely sensed data. Remote Sens Environ, 186:64–87.
• Franklin, S.E., Ahmed, O.S. 2018. Deciduous tree species classification using object‐based analysis and machine learning with unmanned aerial vehicle multispectral data. Int J Remote Sens, 39:5236–5245. https://doi.org/10.1080/01431161.2017.1363442
• Fricker, G.A., Ventura, J.D., Wolf, J.A., North, M.P., Davis, F.W., Franklin, J. 2019. A Convolutional Neural Network Classifier Iden‐ tifies Tree Species in Mixed‐Conifer Forest from Hyperspectral Imagery. Remote Sens, 11(19):2326. https://doi.org/ 10.3390/rs11192326
• Gamon, J.A., Peñuelas, J., Field, C.B. 1992. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sens of Environ, 41(1):35–44. https://doi.org/10.1016/0034-4257(92) 90059-S
• Georganos, S., Grippa, T., Gadiaga, A.N., et al. 2019. Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling. Geocarto International, 36:2. https://doi.org/10.1080/10106049.2019.1595177
• Gimenez, R., Lassalle, G., Hédacq, R., et al 2021. Exploitation of spectral and temporal information for mapping plant species in a former industrial site. Int Arch Photogramm Remote Sens Spatial Inf Sci, 559–566. https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-559-2021
• Guo, Q., Zhang, J., Guo, S., Ye, Z., Deng, H., Hou, X., Zhang, H. 2022. Urban Tree Classification Based on Object-Oriented Approach and Random Forest Algorithm Using Unmanned Aerial Vehicle (UAV) Multispectral Imagery. Remote Sens, 14:3885. https://doi.org/10.3390/rs14163885
• Heupel, K., Spengler, D., Itzerott, S. 2018. A Progressive Crop-Type Classification Using Multitemporal Remote Sensing Data and Phenological Information. PFG, 86:53–69. https://doi.org/10.1007/s41064-018-0050-7
• Huete, A. 1988. A soil-adjusted vegetation index (SAVI). Remote Sens of Environ, 25:295–309. https://doi.org/ 10.1016/0034-4257(88)90106-X
• Huete, A.R., Liu, H.Q., Batchily, K., van Leeuwen, W. 1997. A comparison of vegetation indices over a global set of TM images for EOS–MODIS. Remote Sens of Environ, 59:440–451. https://doi.org/10.1016/ S0034-4257(96)00112-5 Hunt, E.R., Doraiswamy, P.C., McMurtrey, J.E., et al. 2013. A visible band index for remote sensing leaf chlorophyll content at the canopy scale. Int J of Appl Earth Observation and Geoinformation, 21:103–112. https://doi.org/10.1016/j.jag.2012.07.020
• Hycza, T., Stereńczak, K., Bałazy, R. 2018. Potential use of hyperspectral data to classify forest tree species. N Z j of For Sci, 48:18. https://doi.org/10.1186/s40490-018-0123-9
• Iglhaut, J., Cabo, C., Puliti, S., et al. 2019. Structure from Motion Photogrammetry in Forestry: a Review. Curr Forestry Rep, 5:155–168. https://doi.org/10.1007/ s40725-019-00094-3
• Ignatova, M.A., Kozlovsky, B.L., Dmitrieva, A.A., Varduni, T.V., Dmitriev, P.A. 2024. Assessment of seasonal dynamics of photosynthetic pigments in maple leaves using vegetation indices calculated from hyperspectral imaging data. AgroEcoInfo: Electronic scientific and production journal, https://doi.org/10.51419/202142206
• Jones, T.G., Coops, N.C., Sharma, T. 2010. Assessing the utility of airborne hyperspectral and LiDAR data for species distribution mapping in the coastal Pacific Northwest, Canada. Remote Sensing of Environment, 114:2841-2852. https://doi.org/10.1016/J.RSE.2010. 07.002
• Jordan, C.F. 1969. Derivation of leaf-area index from quality of light on forest floor. Ecol, 50(4):663–678. https://doi.org/10.2307/1936256
• Kavzoglu, T., Tonbul, H., Yildiz Erdemir, M., et al. 2018. Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis. J Indian Soc Remote Sens, 46:1297–1306. https://doi.org/10.1007/s12524-018-0803-1
• Lassalle, G., Ferreira, M.P., Cué La Rosa L.E., et al. 2023 Advances in multi- and hyperspectral remote sensing of mangrove species: A synthesis and study case on airborne and multisource spaceborne imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 195:298-312. https://doi.org/10.1016/j.isprsjprs. 2022.12.003
• Li, Y., Chai, G., Wang, Y., Lei, L., Zhang, X. 2022. ACE R-CNN: An Attention Complementary and Edge Detection-Based Instance Segmentation Algorithm for Individual Tree Species Identification Using UAV RGB Images and LiDAR Data. Remote Sens, 14:3035. https://doi.org/10.3390/rs14133035
• Liu, H. 2022. Classification of urban tree species using multi-features derived from four-season RedEdge-MX data. Computers and Electronics in Agriculture, 194:106794. https://doi.org/10.1016/j.compag.2022. 106794
• Liu, L., Coops, N.C., Aven, N.W., Pang, Y. 2017. Mapping urban tree species using integrated airborne hyperspectral and LiDAR remote sensing data. Remote Sensing of Environment, 200:170-182. https://doi.org/10.1016/j.rse.2017.08.010
• Merzlyak, M.N., Gitelson, A.A., Chivkunova, O.B., Rakitin, V.Y.U. 1999. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiol Plant, 106(1):135–141. https://doi.org/10.1034/J.1399-3054.1999.106119.X
• Miyoshi, G.T., Arruda, Md.S., Osco, L.P., et al. 2020. A novel deep learning method to identify single tree species in UAV-based hyperspectral images. Remote Sensing, 12(8):1294. https://doi.org/10.3390/ rs12081294
• Miyoshi, G.T., Imai, N.N., Tommaselli, A.M.G., Honkavaara, E. 2020a. Spectral differences of tree species belonging to atlantic forest obtained from UAV hyperspectral images. Int Arch Photogramm Remote Sens Spatial Inf Sci, 49–54. https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-49-2020
• Miyoshi, T.G., Imai, N.N., Garcia Tommaselli, A.M., Antunes de Moraes, M.V., Honkavaara, E. 2020b. Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest. Remote Sens, 12(2):244. https://doi.org/10.3390/rs12020244
• Myint, S.W., Gober, P., Brazel, A., Grossman-Clarke, S., Weng, Q. 2011. Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sensing of Environment, 115:1145-1161. https://doi.org/10. 1016/j.rse.2010.12.017
• Norton, C.L., Hartfield, K., Collins, C.D.H., van Leeuwen, W.J.D., Metz, L.J. 2022. Multi-Temporal LiDAR and Hyperspectral Data Fusion for Classification of Semi-Arid Woody Cover Species. Remote Sens, 14:2896. https://doi.org/10.3390/ rs14122896
• Quemada, C., Pérez-Escudero, J.M., Gonzalo, R., Ederra, I., Santesteban, L.G., Torres, N., Iriarte, J.C. 2021. Remote Sensing for Plant Water Content Monitoring: A Review. Remote Sens. 13, 2088. https://doi.org/10.3390/rs13112088
• Rehman, T.H., Lundy, M.E., Linquist, B.A. 2022. Comparative Sensitivity of Vegetation Indices Measured via Proximal and Aerial Sensors for Assessing N Status and Predicting Grain Yield in Rice Cropping Systems. Remote Sens, 14:2770. https://doi.org/10.3390/rs14122770
• Saeed, S., Latif, M.A., Rajput, M.A. 2021. Fuzzy-Based Multi-Crop Classification Using High Resolution UAV Imagery. Quaid-E-Awam University Research Journal of Engineering, Science & Technology, Nawabshah, 19(1):1-8. https://doi.org/10.52584/ QRJ.1901.01
• Sivanandam, P., Lucieer, A., 2022. Tree Detection and Species Classification in a Mixed Species Forest Using Unoccupied Aircraft System (UAS) RGB and Multispectral Imagery. Remote Sens, 14:4963. https://doi.org/10.3390/rs14194963
• Sothe, C., De Almeida, C.M., Schimalski, M.B., et al. 2020. Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data. GIScience & Remote Sensing, 57:369–394. https://doi.org/10.1080/15481603.2020.1712102
• Su, T-H., Wu, C-H., Kao, J-H. 2021. Artificial intelligence in precision medicine in hepatology. J Gastroenterol Hepatol, 36:569–580. https://doi.org/ 10.1111/jgh.15415
• Tang, J., Liang, J., Yang, Y., Zhang, S., Hou, H, Zhu, X. 2022. Revealing the Structure and Composition of the Restored Vegetation Cover in Semi-Arid Mine Dumps Based on LiDAR and Hyperspectral Images. Remote Sens, 14:978. https://doi.org/10.3390/ rs14040978
• Tucker, C.J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens of Environ, 8(2):127–150. https://doi.org/10.1016/ 0034-4257(79)90013-0
• van Geffen, F., Heim, B., Brieger, F., et al. 2022. SiDroForest: a comprehensive forest inventory of Siberian boreal forest investigations including drone-based point clouds, individually labeled trees, synthetically generated tree crowns, and Sentinel-2 labeled image patches. Earth Syst Sci Data, 14:4967–4994. https://doi.org/10.5194/essd-14-4967-2022
• Veras, H.F.P., Ferreira, M.P., da Cunha Neto, E.M., et al. 2022. Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. Ecological Informatics, 71:101815. https://doi.org/10.1016/j.ecoinf.2022. 101815
• Xu, K., Tian, Q., Zhang, Z., Yue, J., Chang, C-T. 2020. Tree Species (Genera) Identification with GF-1 Time-Series in A Forested Landscape, Northeast China. Remote Sens, 12:1554. https://doi.org/10.3390/ rs12101554
• Xu, Z., Shi, W., Lin, L., et al. 2021. PCA-RF model for Dendrolimus punctatus Walker damage detection. Nat Hazards, 106:991–1009. https://doi.org/10.1007/ s11069-021-04503-4
• Yang, G., Zhao, Y., Li, B., et al. 2019. Tree Species Classification by Employing Multiple Features Acquired from Integrated Sensors. Journal of Sensors, 2019:12. https://doi.org/10.1155/2019/ 3247946
• Shi, Y., Skidmore, A.K., Wang, T., et al. 2018. Tree species classification using plant functional traits from LiDAR and hyperspectral data. International Journal of Applied Earth Observation and Geoinformation, 73:207-219. https://doi.org/10.10 16/j.jag.2018.06.018
• Zhong, H., Lin, W., Liu, H., et al. 2022. Identification of tree species based on the fusion of UAV hyperspectral image and LiDAR data in a coniferous and broad-leaved mixed forest in Northeast China. Front Plant Sci, 13:964769. https://doi.org/10.3389/fpls.2022. 964769
• Zhou, G., Ni Z., Zhao, Y., Luan, J. 2022. Identification of Bamboo Species Based on Extreme Gradient Boosting (XGBoost) Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery. Sensors, 22:5434. https://doi.org/10.3390/s22145434
• Zhou, X.X., Li, Y.Y., Luo, Y.K., et al. 2022. Research on remote sensing classification of fruit trees based on Sentinel-2 multi-temporal imageries. Sci Rep, 12:11549. https://doi.org/10.1038/s41598-02215 414-0