Using canopy height model derived from UAV imagery as an auxiliary for spectral data to estimate the canopy cover of mixed broadleaf forests

In northern Argentina, the assessment of degraded forests is a big challenge for both science and practice, due to their heterogeneous structure. However, new technologies could contribute to mapping post-disturbance canopy cover and basal area in detail. Therefore, this research assesses whether or not the inclusion of partial cover unmanned aerial vehicle imagery could reduce the classification error of a SPOT6 image used in an area-based inventory. BA was calculated from 77 ground inventory plots over 3944 ha of a forest affected by mixed-severity fires in the Argentinian Yungas. In total, 74% of the area was covered with UAV flights, and canopy height models were calculated to estimate partial canopy cover at three tree height classes. Basal area and partial canopy cover were used to formulate the adjusted canopy cover index, and it was calculated for 70 ground plots and an additional 20 image plots. Four classes of fire severity were created based on basal area and adjusted canopy cover index, and were used to run two supervised classifications over a segmented (algorithm multiresolution) wall-to-wall SPOT6 image. The comparison of the Cohan’s Kappa coefficient of both classifications shows that they are not significantly different (p-value: 0.43). However, the approach based on the adjusted canopy cover index achieved more homogeneous strata (Welch t-test with 95% of confidence). Additionally, UAV-derived canopy height model estimates of tree height were compared with field measurements of 71 alive trees. The canopy height models underestimated tree height with an RMSE ranging from 2.8 to 8.3 m. The best accuracy of the canopy height model was achieved using a larger pixel size (10 m), and for lower stocked plots due to high fire severity.

Download Full-text

Comparison and Evaluation of Different Pit-Filling Methods for Generating High Resolution Canopy Height Model Using UAV Laser Scanning Data

Remote Sensing ◽

10.3390/rs13122239 ◽

2021 ◽

Vol 13 (12) ◽

pp. 2239

Author(s):

Ying Quan ◽

Mingze Li ◽

Yuanshuo Hao ◽

Bin Wang

Keyword(s):

High Resolution ◽

Laser Scanning ◽

Evaluation Framework ◽

Canopy Height ◽

Filter Method ◽

Individual Tree ◽

Significant Difference ◽

Point Interpolation ◽

Canopy Height Model ◽

Height Model

As a common form of light detection and ranging (LiDAR) in forestry applications, the canopy height model (CHM) provides the elevation distribution of aboveground vegetation. A CHM is traditionally generated by interpolating all the first LiDAR echoes. However, the first echo cannot accurately represent the canopy surface, and the resulting large amount of noise (data pits) also reduce the CHM quality. Although previous studies concentrate on many pit-filling methods, the applicability of these methods in high-resolution unmanned aerial vehicle laser scanning (UAVLS)-derived CHMs has not been revealed. This study selected eight widely used, recently developed, representative pit-filling methods, namely first-echo interpolation, smooth filtering (mean, medium and Gaussian), highest point interpolation, pit-free algorithm, spike-free algorithm and graph-based progressive morphological filtering (GPMF). A comprehensive evaluation framework was implemented, including a quantitative evaluation using simulation data and an additional application evaluation using UAVLS data. The results indicated that the spike-free algorithm and GPMF had excellent visual performances and were closest to the real canopy surface (root mean square error (RMSE) of simulated data were 0.1578 m and 0.1093 m, respectively; RMSE of UAVLS data were 0.3179 m and 0.4379 m, respectively). Compared with the first-echo method, the accuracies of the spike-free algorithm and GPMF improved by approximately 23% and 22%, respectively. The pit-free algorithm and highest point interpolation method also have advantages in high-resolution CHM generation. The global smooth filter method based on the first-echo CHM reduced the average canopy height by approximately 7.73%. Coniferous forests require more pit-filling than broad-leaved forests and mixed forests. Although the results of individual tree applications indicated that there was no significant difference between these methods except the median filter method, pit-filling is still of great significance for generating high-resolution CHMs. This study provides guidance for using high-resolution UAVLS in forestry applications.

Download Full-text

A Novel Machine Learning Method for Estimating Biomass of Grass Swards Using a Photogrammetric Canopy Height Model, Images and Vegetation Indices Captured by a Drone

Agriculture ◽

10.3390/agriculture8050070 ◽

2018 ◽

Vol 8 (5) ◽

pp. 70 ◽

Cited By ~ 39

Author(s):

Niko Viljanen ◽

Eija Honkavaara ◽

Roope Näsi ◽

Teemu Hakala ◽

Oiva Niemeläinen ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Vegetation Indices ◽

Canopy Height ◽

Meat Production ◽

Machine Learning Technique ◽

Learning Technique ◽

Canopy Height Model ◽

Mean Square Errors ◽

Height Model

Silage is the main feed in milk and ruminant meat production in Northern Europe. Novel drone-based remote sensing technology could be utilized in many phases of silage production, but advanced methods of utilizing these data are still developing. Grass swards are harvested three times in season, and fertilizer is applied similarly three times—once for each harvest when aiming at maximum yields. Timely information of the yield is thus necessary several times in a season for making decisions on harvesting time and rate of fertilizer application. Our objective was to develop and assess a novel machine learning technique for the estimation of canopy height and biomass of grass swards utilizing multispectral photogrammetric camera data. Variation in the studied crop stand was generated using six different nitrogen fertilizer levels and four harvesting dates. The sward was a timothy-meadow fescue mixture dominated by timothy. We extracted various features from the remote sensing data by combining an ultra-high resolution photogrammetric canopy height model (CHM) with a pixel size of 1.0 cm and red, green, blue (RGB) and near-infrared range intensity values and different vegetation indices (VI) extracted from orthophoto mosaics. We compared the performance of multiple linear regression (MLR) and a Random Forest estimator (RF) with different combinations of the CHM, RGB and VI features. The best estimation results with both methods were obtained by combining CHM and VI features and all three feature classes (CHM, RGB and VI features). Both estimators provided equally accurate results. The Pearson correlation coefficients (PCC) and Root Mean Square Errors (RMSEs) of the estimations were at best 0.98 and 0.34 t/ha (12.70%), respectively, for the dry matter yield (DMY) and 0.98 and 1.22 t/ha (11.05%), respectively, for the fresh yield (FY) estimations. Our assessment of the sensitivity of the method with respect to different development stages and different amounts of biomass showed that the use of the machine learning technique that integrated multiple features improved the results in comparison to the simple linear regressions. These results were extremely promising, showing that the proposed multispectral photogrammetric approach can provide accurate biomass estimates of grass swards, and could be developed as a low-cost tool for practical farming applications.

Download Full-text