Estimation of Picea Schrenkiana Canopy Density at Sub-Compartment Scale by Integration of Optical and Radar Satellite Images
Abstract
:1. Introduction
- A quantitative comparison is given between linear and nonlinear regression models for Picea Schrenkiana canopy density estimation.
- Multiple data sources are integrated, including active and passive satellite imagery and DEM data, to improve model accuracy.
- A discussion is provided of the estimation potential using different models and different features on canopy density estimation at the sub-component scale.
2. Materials and Methods
2.1. Study Region
2.2. Dataset
2.2.1. Image Data
2.2.2. Forest Resource Data
2.3. Methods
2.3.1. Feature Factor Extraction
- Optical Image Processing
- (1)
- Vegetation Index
- (2)
- Texture Characteristics
- Radar Image Characteristics
- (1)
- Backscattering Coefficient
- (2)
- Texture Characteristics
- Topographic Characteristics
2.3.2. Modeling Fundamentals
Multiple Stepwise Regression
Back Propagation Neural Network
Cubist Model
- Rule 1:
- If conditions such as “Altitude ≤ x” and “NDVI ≥ y” are met,
- Then, the prediction is given by the equation “FCC = + × Altitude…”, where ‘’, ‘’, etc., are coefficients of the linear regression model.
- Rule m:
- If conditions like “Altitude ≥ x” and “NDVI ≤ y” are met,
- Then, the prediction is given by “FCC = + × NDVI…”, with ‘’, ‘’, etc., being linear regression coefficients.
- (i)
- The node sample count falls below a predetermined threshold;
- (ii)
- The ratio of the node’s sample target attribute standard deviation to the overall sample target attribute standard deviation is below a certain limit.
2.3.3. Model Accuracy Evaluation
3. Results
3.1. Correlation Analysis of Image Characteristic and Canopy Density
3.2. Models Construction and Parameter Optimization
3.2.1. Multiple Stepwise Regression Model
3.2.2. BP Neural Network Model
3.2.3. Cubist Model
3.3. Comparison of Modeling Results
3.3.1. Analysis of Overall Accuracy Evaluation
3.3.2. Accuracy Evaluation and Analysis of Different Canopy Density Grades
3.3.3. Remote Sensing Inversion Mapping of Canopy Density
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Gschwantner, T.; Schadauer, K.; Vidal, C.; Lanz, A.; Tomppo, E.; di Cosmo, L.; Robert, N.; Duursma, D.E.; Lawrence, M. Common tree definitions for national forest inventories in Europe. Silva Fenn. 2009, 43, 303–321. [Google Scholar] [CrossRef]
- Jennings, S.B.; Brown, N.D.; Sheil, D. Assessing forest canopies and understorey illumination: Canopy density, canopy cover and other measures. Forestry 1999, 72, 59–74. [Google Scholar] [CrossRef]
- IPCC. Good Practice Guidance for Land Use, Land-Use Change and Forestry; Institute for Global Environmental Strategies (IGES): Hayama, Japan, 2003. [Google Scholar]
- Xu, B.; Gong, P.; Pu, R. Crown closure estimation of oak savannah in a dry season with Landsat TM imagery: Comparison of various indices through Correlation Analysis. Int. J. Remote Sens. 2003, 24, 1811–1822. [Google Scholar] [CrossRef]
- Chen, G.; Lou, T.; Jing, W.; Wang, Z. Sparkpr: An Efficient Parallel Inversion of Canopy density of the forest. IEEE Access 2019, 7, 135949–135956. [Google Scholar] [CrossRef]
- Smith, A.M.; Ramsay, P.M. A comparison of ground-based methods for estimating canopy density for use in phenology study. Agric. For. Meteorol. 2018, 252, 18–26. [Google Scholar] [CrossRef]
- Yang, C.; Ni, J.; Zhou, Q.; Cheng, W.; Han, S. Correlation between canopy density of different stands and remote sensing data. J. Ecol. 2015, 35, 2119–2125. [Google Scholar]
- Gu, C. Study on Estimation of Mountain Forest Parameters Using Geometric Optical Model Coupled with Multi-Source Remote Sensing Data. Ph.D. Thesis, China Academy of Forestry Sciences, Beijing, China, 2018. [Google Scholar]
- Chopping, M.; Moisen, G.G.; Su, L.; Laliberte, A.; Rango, A.; Martonchik, J.V.; Peters, D.P.C. Large area mapping of southwestern forest crown cover, canopy height, and biomass using the NASA Multiangle Imaging Spectro-Radiometer. Remote Sens. Environ. 2008, 112, 2051–2063. [Google Scholar] [CrossRef]
- Smith, A.M.S.; Falkowski, M.J.; Hudak, A.T.; Evans, J.S.; Robinson, A.P.; Steele, C.M. A cross-comparison of field, spectral, and lidar estimates of forest canopy cover. Can. J. Remote Sens. 2009, 35, 447–459. [Google Scholar] [CrossRef]
- Hill, M.J.; Román, M.O.; Schaaf, C.B.; Hutley, L.; Brannstrom, C.; Etter, A.; Hanan, N.P. Characterizing vegetation cover in global savannas with an annual foliage clumping index derived from the MODIS BRDF product. Remote Sens. Environ. 2011, 115, 2008–2024. [Google Scholar]
- Chopping, M.; North, M.; Chen, J.; Schaaf, C.B.; Blair, J.B.; Martonchik, J.V.; Bull, M.A. Forest Canopy Cover and Height from MISR in Topographically Complex Southwestern US Landscapes Assessed with High Quality Reference Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2012, 5, 44–58. [Google Scholar] [CrossRef]
- Ripple, W.J. Determining coniferous forest cover and forest fragmentation with NOAA-9 advanced very High-resolution radiometer data. Photogramm. Eng. Remote Sens. 1994, 60, 533–540. [Google Scholar]
- Boyd, D.S.; Foody, G.M.; Ripple, W.J. Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing. Appl. Geogr. 2002, 22, 375–392. [Google Scholar] [CrossRef]
- Wang, C.; Du, H.; Xu, X.; Han, N.; Zhou, G.; Sun, S.; Gao, G. Multi-scale crown closure retrieval for moso bamboo forest using multi-source remotely sensed imagery based on geometric-optical and Erf-BP Neural Network Models. Int. J. Remote Sens. 2015, 36, 5384–5402. [Google Scholar] [CrossRef]
- Morales, R.M.; Miura, T.; Idol, T. An assessment of Hawaiian dry forest condition with fine resolution remote sensing. For. Ecol. Manag. 2008, 255, 2524–2532. [Google Scholar] [CrossRef]
- Tan, B.; Li, Z.; Chen, E.; Pang, Y.; Lei, Y. Quantitative estimation of canopy density of the forest using Hyperion hyperspectral data. J. Beijing For. Univ. 2006, 3, 95–101. [Google Scholar]
- Dan, Y.; Shi, J.; Li, X.; Luo, S.; Li, M. Estimation of canopy closure based on improved dimidiate pixel model. J. Beijing For. Univ. 2019, 41, 35–43. [Google Scholar]
- Sun, S.; Tian, X.; Gu, C.; Han, Z.; Wang, C.; Zhang, Z. Remote sensing estimation of canopy density of the forest of Genhe River in Inner Mongolia based on KNN-FIFS. Remote Sens. Technol. Appl. 2019, 34, 959. [Google Scholar] [CrossRef]
- Ning, K. Study on the Method of Retrieving Canopy Density of the Forest in Mountain Area Based on SAR Image. Master’s Thesis, Southwest Jiaotong University, Chengdu, China, 2014. [Google Scholar]
- Chen, J.M.; Pavlic, G.; Brown, L.; Cihlar, J.; Leblanc, S.G.; White, H.P.; Hall, R.J.; Peddle, D.R.; King, D.J.; Trofymow, J.A.; et al. Derivation and validation of Canada-wide coarse-Resolution leaf area index maps using high-resolution satellite imagery and ground measurements. Remote Sens. Environ. 2002, 80, 165–184. [Google Scholar] [CrossRef]
- Li, C.; Tan, B. Study on the method of forest resources remote sensing survey based on GIS. For. Sci. 2004, 40, 40–45. [Google Scholar]
- Diemer, C.; Lucaschewski, I.; Spelsberg, G.; Tomppo, E.; Pekkarinen, A. Integration of terrestrial forest sample plot data, map information and Satellite data: An operational multisource-inventory concept. In Proceedings of the Third Conference “Fusion of Earth Data: Merging Point Measurements, Raster Maps and Remotely Sensed Images”, Sophia Antipolis, France, 26–28 January 2000. [Google Scholar]
- Montesano, P.M.; Neigh, C.S.R.; Sexton, J.; Feng, M.; Channan, S.; Ranson, K.J.; Townshend, J.R. Calibration and Validation of Landsat Tree Cover in the Taiga−Tundra Ecotone. Remote Sens. 2016, 8, 551. [Google Scholar] [CrossRef]
- Hadi; Korhonen, L.; Hovi, A.; Rönnholm, P.; Rautiainen, M. The accuracy of large-area forest canopy cover estimation using Landsat in boreal region. Int. J. Appl. Earth Obs. Geoinf. 2016, 53, 118–127. [Google Scholar] [CrossRef]
- Gong, P.; Pu, R. Hyperspectral Remote Sensing and Its Application; Higher Education Press: Beijing, China, 2000. [Google Scholar]
- Tong, S.; Zhang, J.; Ha, S.; Lai, Q.; Ma, Q. Dynamics of Fractional Vegetation Coverage and Its Relationship with Climate and Human Activities in Inner Mongolia, China. Remote Sens. 2016, 8, 776. [Google Scholar] [CrossRef]
- Xiao, Q.; Tao, J.; Xiao, Y.; Qian, F. Monitoring vegetation cover in Chongqing between 2001 and 2010 using remote sensing data. Environ. Monit. Assess. 2017, 189, 493. [Google Scholar] [CrossRef] [PubMed]
- Ding, Y.; Zheng, X.; Zhao, K.; Xin, X.; Liu, H. Quantifying the Impact of NDVIsoil Determination Methods and NDVIsoil Variability on the Estimation of Fractional Vegetation Cover in Northeast China. Remote Sens. 2016, 8, 29. [Google Scholar] [CrossRef]
- Yang, X.; He, P.; Yu, Y.; Fan, W. Stand Estimation of canopy density in Planted Forests Using a Geometric-Optical Model Based on Remote Sensing. Remote Sens. 2022, 14, 1983. [Google Scholar] [CrossRef]
- Wu, Y.; Zhang, D.; Zhang, H.; Wu, H. Remote sensing estimation of canopy density of the forest combined with image texture characteristic. For. Sci. 2012, 48, 48–53. [Google Scholar]
- Zheng, D.; Zeng, W.; Zhi, C.; Shi, P. Quantitative estimation of canopy density of the forest by remote sensing in the Three Gorges Reservoir Area. J. Cent. South For. Univ. 2013, 33, 1–4. [Google Scholar]
- Wang, R.; Xing, Y.; Wang, L.; You, H.; Qiu, S.; Wang, A. Estimation of canopy density of the forest by combining spaceborne ICESat-GLAS waveform and multispectral Landsat TM image. J. Appl. Ecol. 2015, 26, 1657–1664. [Google Scholar]
- Li, Q.; Wang, Z.; Wang, Y.; Liu, M.; Yang, Y. Study on estimating canopy density of Picea Schrenkiana. var. Tianschanica Forest based on GF-2 remote sensing image. J. Cent. South For. Univ. 2019, 39, 48–54. [Google Scholar]
- Gao, L.; Wang, X.; Johnson, B.A.; Tian, Q.; Wang, Y.; Verrelst, J.; Mu, X.; Gu, X. Remote Sensing Algorithms for Estimation of Fractional Vegetation Cover Using Pure Vegetation Index Values: A Review. ISPRS J. Photogramm. Remote Sens. 2020, 159, 364–377. [Google Scholar] [CrossRef]
- Bannari, A.; Morin, D.; Bonn, F.; Huete, A.R. A Review of Vegetation Indices. Remote Sens. Rev. 1995, 13, 95–120. [Google Scholar] [CrossRef]
- Haralick, R.M.; Shanmugam, K.; Dinstein, I. Textural Characteristic for Image Classification. IEEE Trans. Syst. Man Cybern. 1973, smc-3, 610–621. [Google Scholar] [CrossRef]
- Patel, D.; Stonham, T.J. Texture Image Classification and Segmentation Using RANK-Order Clustering. In Proceedings of the 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis, The Hague, Netherlands, 30 August 1992; IEEE Computer Society: Piscataway, NJ, USA, 1992; Volume 1, pp. 92–95. [Google Scholar]
- Warner, T. Kernel-based Texture in Remote Sensing Image Classification. Geogr. Compass 2011, 5, 781–798. [Google Scholar] [CrossRef]
- Xu, H.; Pan, P.; Yang, W.; Ou, Y.; Ning, J.; Shao, J.; Li, Q. Classification and precision evaluation of forest resources based on multi-source remote sensing images. J. Jiangxi Agric. Univ. 2019, 5, 1–12. [Google Scholar]
- Hao, N. Forest Classification and Landscape Pattern Analysis Based on GF-1 Image—Taking Liangshui Nature Reserve as an Example. Master’s Thesis, Xi’an University of Science and Technology, Xi’an, China, 2016. [Google Scholar]
- Li, M.; Tan, Y.; Pan, J.; Peng, S. Study on forest biomass Modeling combining spectral, texture and topographic characteristic. Remote Sens. Inf. 2006, 6, 6–9+66. [Google Scholar]
- Moreira, A.; Prats-Iraola, P.; Younis, M.; Krieger, G.; Hajnsek, I.; Papathanassiou, K.P. A Tutorial on Synthetic Aperture Radar. IEEE Geosci. Remote Sens. Mag. 2013, 1, 6–43. [Google Scholar] [CrossRef]
- Yang, L.; Shi, L.; Sun, W.; Yang, J.; Li, P.; Li, D.; Liu, S.; Zhao, L. Radiometric and Polarimetric Quality Validation of Gaofen-3 over a Five-Year Operation Period. Remote Sens. 2023, 15, 1605. [Google Scholar] [CrossRef]
- Wu, Y.; Zhang, W.; Zhang, L.; Wu, J. Correlation Analysis of terrain and vegetation distribution based on DEM. Northeast For. Univ. News 2012, 40, 96–98. [Google Scholar]
- Abdollahnejad, A.; Panagiotidis, D.; Shataee Joybari, S.; Surový, P. Prediction of Dominant Forest Tree Species Using QuickBird and Environmental Data. Forests 2017, 8, 42. [Google Scholar] [CrossRef]
- Richardson, H.J.; Hill, D.J.; Denesiuk, D.R.; Fraser, L.H. A comparison of geographic datasets and field meas urements to model soil carbon using random forests and stepwise regressions (British Columbia, Canada). GIScience Remote Sens. 2017, 54, 573–591. [Google Scholar] [CrossRef]
- Liu, Z.; Chang, Y.; Chen, H. Estimation of forest volume in Huzhong forest region based on remote sensing, geographic information system and Artificial Neural Network. J. Appl. Ecol. 2008, 9, 1891–1896. [Google Scholar]
- Li, C.; Zhao, X.; Li, C. Theory and Implementation of Forest Volume Estimation by Remote Sensing; Science Press: Beijing, China, 2006. [Google Scholar]
- Witten, I.H.; Frank, E.; Hall, M.A. Data mining: Practical Machine Learning Tools and Techniques, 2nd ed.; Morgan Kaufmann: San Francisco, CA, USA, 2005. [Google Scholar]
- Kuhn, M.; Johnson, K. Applied Predictive Modeling; Springer: New York, NY, USA, 2013. [Google Scholar]
- Kuhn, M.; Weston, S.; Keefer, C.; Coulter, N. Cubist Models for Regression. R Package Vignette R Package Version 0.0 2012, 18, 480. [Google Scholar]
- Quinlan, J.R. Combining Instance-Based and Model-Based Learning. In Proceedings of the Tenth International Conference on Machine Learning, Amherst, MA, USA, 27–29 June 1993; Morgan Kaufmann: San Fracisco, CA, USA, 1993; pp. 236–243. [Google Scholar]
- Quinlan, J.R. Learning with Continuous Classes. In Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, 16–18 November 1992; World Scientific: Singapore, 1992; Volume 92, pp. 343–348. [Google Scholar]
- Xie, B.; Cao, C.; Xu, M.; Yang, X.; Duerler, R.S.; Bashir, B.; Huang, Z.; Wang, K.; Chen, Y.; Guo, H. Improved Forest Canopy Closure Estimation Using Multispectral Satellite Imagery within Google Earth Engine. Remote Sens. 2022, 14, 2051. [Google Scholar] [CrossRef]
- Wachid, M.N.; Hapsara, R.P.; Cahyo, R.D.; Wahyu, G.N.; Syarif, A.M.; Umarhadi, D.A.; Fitriani, A.N.; Ramadhanningrum, D.P.; Widyatmanti, W. Mangrove canopy density analysis using Sentinel-2A imagery satellite data. In Proceedings of the 3rd International Conference of Planning in the Era of Uncertainty (ICPEU), Malang, Indonesia, 3–7 March 2017. [Google Scholar]
- Humagain, K.; Portillo-Quintero, C.; Cox, R.D.; Cain, J.W. Mapping Tree Density in Forests of the Southwestern USA Using Landsat 8 Data. Forests 2017, 8, 287. [Google Scholar] [CrossRef]
- Cilek, A.; Berberoglu, S.; Donmez, C.; Sahingoz, M. The use of regression tree method for Sentinel-2 satellite data to mapping percent tree cover in different forest types. Environ. Sci. Pollut. Res. 2021, 29, 23665–23676. [Google Scholar] [CrossRef] [PubMed]
- Hua, Y.Y.; Zhao, X.S. Multi-Model Estimation of Forest Canopy Closure by Using Red Edge Bands Based on Sentinel-2 Images. Forests 2021, 12, 1768. [Google Scholar] [CrossRef]
- Xu, E.; Guo, Y.; Chen, E.; Li, Z.; Zhao, L.; Liu, Q. An Estimation Model for Regional Forest Canopy Closure Combined with UAV LiDAR and High Spatial Resolution Satellite Remote Sensing Data. Geomat. Inf. Sci. Wuhan Univ. 2022, 47, 1298–1308. [Google Scholar]
- Wang, X.; Lu, Y. Modern Forest Measurement Method; China Forestry Publishing House: Beijing, China, 2013. [Google Scholar]
- Sankey, T.; Donager, J.; McVay, J.; Sankey, J.B. UA V lidar and hyperspectral fusion for forest monitoring in the southwestern USA. Remote Sens. Environ. 2017, 195, 30–43. [Google Scholar] [CrossRef]
- Xavier, A.C.; Vettorazzi, C.A. Monitoring leaf area index at watershed level through NDVI from Landsat-7/ETM+ data. Sci. Agric. 2004, 61, 243–252. [Google Scholar] [CrossRef]
- Xu, L.; Shi, Y.J.; Fang, H.Y.; Zhou, G.M.; Xu, X.J.; Zhou, Y.F.; Tao, J.X.; Ji, B.Y.; Xu, J.; Li, C.; et al. Vegetation carbon stocks driven by canopy density and forest age in subtropical forest ecosystems. Sci. Total Environ. 2018, 631–632, 619–626. [Google Scholar] [CrossRef]
- Fiala, A.C.S.; Garman, S.L.; Gray, A.N. Comparison of five canopy cover estimation techniques in the western Oregon Cascades. For. Ecol. Manag. 2006, 232, 188–197. [Google Scholar] [CrossRef]
- Korhonen, L.T.; Korhonen, K.; Rautiainen, M.; Stenberg, P. Estimation of forest canopy cover: A comparison of field measurement techniques. Silva Fenn. 2006, 40, 577–588. [Google Scholar] [CrossRef]
- Paletto, A.; Tosi, V. Forest canopy cover and canopy density: Comparison of assessment techniques. Eur. J. For. Res. 2009, 128, 265–272. [Google Scholar] [CrossRef]
- Brown, L.A.; Ogutu, B.O.; Dash, J. Tracking forest biophysical properties with automated digital repeat photography: A fisheye perspective using digital hemispherical photography from below the canopy. Agric. For. Meteorol. 2020, 287, 107944. [Google Scholar] [CrossRef]
- Li, J.; Mao, X. Comparison of Estimation of canopy density of Plantations Using Parametric, Semi-Parametric, and Non-Parametric Models Based on GF-1 Remote Sensing Images. Forests 2020, 11, 597. [Google Scholar] [CrossRef]
- Yang, C.J.; Huang, H.; Han, S.; Ni, J. Estimating forest canopy density using LANDSAT TM data based on sub-compartment objects. In Proceedings of the International Geoscience and Remote Sensing Symposium, Melbourne, Australia, 21–26 July 2013; Volume 10, pp. 999–1002. [Google Scholar]
- Franklin, S.E. Discrimination is crimination of subalpine forest species and canopy density using digital CASI, SPOT PLA, and Landsat TM data. Photogramm. Eng. Remote Sens. 1994, 60, 1233–1241. [Google Scholar]
- Su Mon, M.; Mizoue, N.; Htun, N.Z.; Kajisa, T.; Yoshida, S. Estimating canopy density of the forest of tropical mixed deciduous vegetation using Landsat data: A comparison of three classification approaches. Int. J. Remote Sens. 2012, 33, 1042–1057. [Google Scholar] [CrossRef]
- Pu, R.; Gong, P. Wavelet transform applied to EO-1 hyperspectral data for forest LAI and crown closure mapping. Remote Sens. Environ. 2004, 91, 212–224. [Google Scholar] [CrossRef]
- Pu, R.; Xu, B.; Gong, P. Oakwood crown closure estimation by unmixing Landsat TM data. Int. J. Remote Sens. 2003, 24, 4433–4445. [Google Scholar] [CrossRef]
- Joshi, C.; De Leeuw, J.; Skidmore, A.K.; Van Duren, I.C.; Van Oosten, H. Remotely sensed estimation of canopy density of the forest: A comparison of the performance of four methods. Int. J. Appl. Earth Obs. Geoinf. 2006, 8, 84–95. [Google Scholar] [CrossRef]
Vegetation Indexes (VI) | Calculation Formulas |
---|---|
Normalized Differential Vegetation Index (NDVI) | |
Renormalized Difference Vegetation Index (RDVI) | |
Perpendicular Vegetation Index (PVI) | 5 |
Soil-Adjusted Vegetation Index (SAVI) | |
Modified Soil-Adjusted Vegetation Index (MSAVI) | |
Difference Vegetation Index (DVI) | |
Simple Ratio Vegetation Index (SRVI) | |
Ratio Vegetation Index RVI |
GLCM Characteristic Value | Calculation Formula | Description |
---|---|---|
Mean (ME) | In the GLCM, the ME represents the average value of gray levels in a specific direction. This means that by statistically analyzing the gray-level pairs in a particular direction and calculating their average, one can obtain the overall brightness level of the image texture in that direction. | |
Variance (VAR) | VAR reflects the degree of dispersion or variation in the distribution of gray levels in the image texture. It measures the difference between gray levels, indicating the degree of diversity in the image texture. | |
Homogeneity (HOM) | HOM measures the consistency of gray-level pairs in the image texture. In the GLCM, higher homogeneity indicates less difference between gray-level pairs, resulting in a more uniform and consistent texture. | |
Contrast (CON) | CON describes the difference between different gray levels in the image texture. It quantifies the relative difference between pairs of gray levels, indicating the degree of contrast between different parts of the image texture. | |
Dissimilarity (DIS) | DIS reflects the degree of difference between different gray levels in the image texture. It measures the dissimilarity between pairs of gray levels, indicating the degree of difference between different parts of the image texture. | |
Entropy (ENT) | ENT describes the randomness or uncertainty of the image texture. It measures the disorder in the distribution of gray levels, indicating the irregularity of the texture. | |
Second Moment (ASM) | ASM reflects the uniformity of the image texture. It measures the frequency of occurrence of gray-level pairs in the image texture, indicating the uniformity of the texture. | |
Correlation (COR) | COR reflects the linear relationship between pixels in the image texture. It measures the degree of correlation between pairs of gray levels, indicating the strength of the linear relationship between pixels in the texture. |
Factor | Correlation Coefficient | Significance Level | Factor | Correlation Coefficient | Significance Level |
---|---|---|---|---|---|
NDVI | 0.332 ** | 0.000 | HV3_0ASM | 0.418 ** | 0.000 |
PCA3_0VAR | 0.388 ** | 0.000 | HV3_0ENT | −0.419 ** | 0.000 |
PCA3_0ASM | −0.611 ** | 0.000 | HV3_90COR | −0.335 ** | 0.000 |
PCA5_0ENT | 0.626 ** | 0.000 | HV3_135HOM | 0.368 ** | 0.000 |
PCA5_90COR | 0.426 ** | 0.000 | HV3_135DIS | −0.342 ** | 0.000 |
PCA9_0HOM | −0.617 ** | 0.000 | HV3_135CON | −0.314 ** | 0.000 |
PCA13_0CON | 0.441 ** | 0.000 | HV5_0VAR | −0.314 ** | 0.000 |
PCA13_0DIS | 0.550 ** | 0.000 | Altitude | 0.563 ** | 0.000 |
- | - | - | Slope | −0.312 ** | 0.000 |
Step Parameters | Correlation Coefficient | R2 | Standard Error | Significance | Durbin–Watson |
---|---|---|---|---|---|
1 | 0.663 | 0.435 | 0.1139 | 0.000 | |
2 | 0.742 | 0.543 | 0.1024 | 0.000 | |
3 | 0.763 | 0.572 | 0.0991 | 0.000 | |
4 | 0.776 | 0.590 | 0.0970 | 0.000 | 1.932 |
The Transfer Function | The Number of Nodes in Layer (Ι) | The Number of Nodes in Layer (ΙΙ) | R2train | R2test | RMSEtrain | RMSEtest |
---|---|---|---|---|---|---|
Logsig and tansig | 5 | 9 | 0.6816 | 0.5889 | 0.0879 | 0.1064 |
Tansig and logsig | 2 | 4 | 0.7278 | 0.5739 | 0.0792 | 0.1043 |
Tansig and purelin | 5 | 4 | 0.7936 | 0.5694 | 0.0711 | 0.1201 |
Purelin and tansig | 2 | 6 | 0.6900 | 0.6194 | 0.0859 | 0.1070 |
Logsig and purelin | 6 | 5 | 0.6921 | 0.5962 | 0.0853 | 0.1048 |
Purelin and logsig | 12 | 1 | 0.6082 | 0.5786 | 0.0946 | 0.1058 |
Variables | Conds | Model |
---|---|---|
PCA3_0ASM | 15% | 74% |
Altitude | 12% | 85% |
HV3_135CON | 12% | 2% |
PCA13_0DIS | 74% | |
PCA9_0HOM | 62% | |
PCA13_0CON | 61% | |
PCA5_0ENT | 60% | |
HV3_0ENT | 36% | |
HV3_135DIS | 35% | |
HV3_0ASM | 24% | |
NDVI | 24% | |
PCA3_0VAR | 12% | |
HV3_90COR | 11% | |
HV3_135HOM | 11% |
Data Source | Model | RMSE | AAPP (%) |
---|---|---|---|
Optical image characteristics | Multiple stepwise regression | 0.1194 | 75.54% |
BP neural network | 0.1066 | 80.51% | |
Cubist | 0.0997 | 79.45% | |
Average accuracy | 0.1086 | 78.50% | |
Radar image characteristics | Multiple stepwise regression | 0.1229 | 76.70% |
BP neural network | 0.1166 | 77.39% | |
Cubist | 0.1249 | 76.62% | |
Average accuracy | 0.1214 | 76.90% | |
Combining optical and radar image characteristics | Multiple stepwise regression | 0.1115 | 77.86% |
BP neural network | 0.1043 | 79.66% | |
Cubist | 0.1019 | 78.46% | |
Average accuracy | 0.1059 | 78.66% |
Canopy Density Grade | Low Canopy Density | Middle Canopy Density | High Canopy Density | ||||
---|---|---|---|---|---|---|---|
Data Source | Model | RMSE | AAPP (%) | RMSE | AAPP (%) | RMSE | AAPP (%) |
Optical image characteristic | Multiple stepwise regression | 0.1247 | 53.19% | 0.1044 | 82.19% | 0.1854 | 78.54% |
BP neural network | 0.0847 | 75.37% | 0.1092 | 81.12% | 0.1289 | 87.47% | |
Cubist | 0.0937 | 64.36% | 0.1003 | 83.06% | 0.1076 | 87.48% | |
Radar image characteristic | Multiple stepwise regression | 0.1538 | 50.39% | 0.0814 | 85.44% | 0.2335 | 73.95% |
BP neural network | 0.1530 | 45.59% | 0.0710 | 87.41% | 0.2255 | 77.74% | |
Cubist | 0.1688 | 44.23% | 0.0738 | 87.46% | 0.2386 | 72.67% | |
Characteristic of joint optical image and radar image | Multiple stepwise regression | 0.1294 | 53.39% | 0.0955 | 83.19% | 0.1740 | 80.99% |
BP neural network | 0.1211 | 57.92% | 0.0966 | 85.21% | 0.1152 | 88.77% | |
Cubist | 0.1235 | 54.87% | 0.0943 | 83.93% | 0.1009 | 89.17% |
Order | Data | Object | Model | Accuracy | Document |
---|---|---|---|---|---|
1 | Landsat 8, Sentinel-2 | Pinus tabulaeformis, Quercus Mongolia, Betula spp., Populus spp., Larix spp., and Armeniaca sibirica | A novel bounding envelope methodology | 80.00% (Landsat 8) 86.00% (Sentinel-2) | [55] |
2 | Sentinel-2, DEM | Larix gmelinii, Pinus tabuliformis, Betula platyphylla, Populus davidiana, and Quercus mongolica | MSR | 79.24% | [59] |
BP | 83.03% | ||||
Li–Strahler geometric optical mode | 75.17% | ||||
3 | UAV images, LiDAR, GF-2 | Pinus tabuliformis, Larix gmelinii, Betula platyphylla, Populus davidiana | UnetR | 75.60% | [60] |
FCN | 73.70% | ||||
RF | 70.20% | ||||
SVR | 68.90% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, Y.; Li, X.; Yang, X.; Qi, W.; Zhang, D.; Wang, J. Estimation of Picea Schrenkiana Canopy Density at Sub-Compartment Scale by Integration of Optical and Radar Satellite Images. Forests 2024, 15, 1145. https://doi.org/10.3390/f15071145
Wang Y, Li X, Yang X, Qi W, Zhang D, Wang J. Estimation of Picea Schrenkiana Canopy Density at Sub-Compartment Scale by Integration of Optical and Radar Satellite Images. Forests. 2024; 15(7):1145. https://doi.org/10.3390/f15071145
Chicago/Turabian StyleWang, Yibo, Xusheng Li, Xiankun Yang, Wenchao Qi, Donghui Zhang, and Jinnian Wang. 2024. "Estimation of Picea Schrenkiana Canopy Density at Sub-Compartment Scale by Integration of Optical and Radar Satellite Images" Forests 15, no. 7: 1145. https://doi.org/10.3390/f15071145