Estimating plot volume using lidar height and intensity distributional parameters

This study explored the feasibility of height distributional metrics and intensity values extracted from low-density airborne light detection and ranging (lidar) data to estimate plot volumes in dense Korean pine (Pinus koraiensis) plots. Multiple linear regression analyses were performed using lidar height and intensity distributional metrics. The candidate variables for predicting plot volume were evaluated using three data sets: total, canopy, and integrated lidar height and intensity metrics. All intensities of lidar returns used were corrected by the reference distance. Regression models were developed using each data set, and the first criterion used to select the best models was the corrected Akaike Information Criterion (AIC_c). The use of three data sets was statistically significant at R² = 0.75 (RMSE = 52.17 m³ ha^?1), R² = 0.84 (RMSE = 45.24 m³ ha^?1), and R² = 0.91 (RMSE = 31.48 m³ ha^?1) for total, canopy, and integrated lidar distributional metrics, respectively. Among the three data sets, the integrated lidar metrics-derived model showed the best performance for estimating plot volumes, improving errors up to 42% when compared to the other two data sets. This is attributed to supplementing variables weighted and biased to upper limits in dense plots with more statistical variables that explain the lower limits. In all data sets, intensity metrics such as skewness, kurtosis, standard deviation, minimum, and standard error were employed as explanatory variables. The use of intensity variables improved the accuracy of volume estimation in dense forests compared to prior research. Correction of the intensity values contributed up to a maximum of 58% improvement in volume estimation when compared to the use of uncorrected intensity values (R² = 0.78, R² = 0.53, and R² = 0.63 for total, canopy, and integrated lidar distributional metrics, respectively). It is clear that the correction of intensity values is an essential step for the estimation of forest volume.     

Forest inventory stand height estimates from very high spatial resolution satellite imagery calibrated with lidar plots

Many areas of forest across northern Canada are challenging to monitor on a regular basis as a result of their large extent and remoteness. Although no forest inventory data typically exist for these northern areas, detailed and timely forest information for these areas is required to support national and international reporting obligations. We developed and tested a sample-based approach that could be used to estimate forest stand height in these remote forests using panchromatic Very High Spatial Resolution (VHSR, < 1 m) optical imagery and light detection and ranging (lidar) data. Using a study area in central British Columbia, Canada, to test our approach, we compared four different methods for estimating stand height using stand-level and crown-level metrics generated from the VHSR imagery. ‘Lidar plots’ (voxel-based samples of lidar data) are used for calibration and validation of the VHSR-based stand height estimates, similar to the way that field plots are used to calibrate photogrammetric estimates of stand height in a conventional forest inventory or to make empirical attribute estimates from multispectral digital remotely sensed data. A k-nearest neighbours (k-NN) method provided the best estimate of mean stand height (R ² = 0.69; RMSE = 2.3 m, RMSE normalized by the mean value of the estimates (RMSE-%) = 21) compared with linear regression, random forests, and regression tree methods. The approach presented herein demonstrates the potential of VHSR panchromatic imagery and lidar to provide robust and representative estimates of stand height in remote forest areas where conventional forest inventory approaches are either too costly or are not logistically feasible. While further evaluation of the methods is required to generalize these results over Canada to provide robust and representative estimation, VHSR and lidar data provide an opportunity for monitoring in areas for which there is no detailed forest inventory information available.     

Canopy level estimations of chlorophyll and LAI for two tropical species (teak and bamboo) from Hyperion (EO1) data

Current economic development in tropical regions (especially in India, China, and Brazil) is putting tremendous pressure on tropical forest cover. Some of the dominant and economically important species are planted at large scale in these countries. Teak and bamboo are two important species of tropical regions because of their commercial and conservation values. Accurate estimates of foliar chemistry can help in evaluating the health status of vegetation in these regions. An attempt has been made to derive canopy level estimation of chlorophyll and leaf area index (LAI) for these species utilizing Hyperion data. Partial least square (PLS) regression analysis was carried out to identify the correlation between measured parameters (chlorophyll and LAI) and Hyperion reflectance spectra. PLS regression identified 600–750 nm as a sensitive spectral region for chlorophyll and 1000–1507 nm for LAI. The PLS regression model tested in this study worked well for the estimation of chlorophyll (R ² = 0.90, root mean square error (RMSE) = 0.182 for teak and R ² = 0.84, RMSE = 0.113 for bamboo) and for the estimation of LAI (R ² = 0.87, RMSE = 0.425). The lower predictive error obtained indicates the robustness of the data set and also of the applicability of the PLS regression analysis. Wavelengths recognized by the PLS regression model were utilized for the development of vegetation indices for estimating chlorophyll and LAI. Predictive performances of the developed simple ratios (SRs) were evaluated using the cross-validation method. SR 743/692 gave the best results for the prediction of chlorophyll with the leave-one-out cross-validation (LOO-CV) method (R ² = 0.73, RMSE = 0.28 for teak and R ² = 0.71, RMSE = 0.15 for bamboo). The normalized difference ratio (ND 1457/1084) gave the best results for the prediction of LAI with LOO-CV (R ² = 0.66, RMSE = 0.57). Ratios developed here can be tested for teak and bamboo cover spread in tropical regions with similar environmental conditions.     

Estimating the leaf area index in Indian tropical forests using Landsat-8 OLI data

Leaf area index (LAI) is a key vegetation biophysical parameter and is extensively used in modelling of phenology, primary production, light interception, evapotranspiration, carbon, and nitrogen dynamics. In the present study, we attempt to spatially characterize LAI for natural forests of Western Ghats India, using ground based and Landsat-8 Operational Land Imager (OLI) sensor satellite data. For this, 41 ground-based LAI measurements were carried out across a gradient of tropical forest types, viz. dry, moist, and evergreen forests using LAI-2200 plant canopy analyser, during the month of March 2015. Initially, measured LAI values were regressed with 15 spectral variables, including nine spectral vegetation indices (SVIs) and six Landsat-8 surface reflectance (ρ) variables using univariate correlation analysis. Results showed that the red (ρ_red), near-infrared (ρ_NIR), shortwave infrared (ρ_SWIR1, ρ_SWIR2) reflectance bands (R² > 0.6), and all SVIs (R² > 0.7) except simple ratio (SR) have the highest and second highest coefficient of determination with ground-measured LAI. In the second step, to select significant (high R², low root mean square error (RMSE), and p-level < 0.05) SVIs to determine the best representative model, stepwise multiple linear regression (SMLR) was implemented. The results indicate that the SMLR model predicted LAI with better coefficient of determination (R² = 0.83, RMSE = 0.78) using normalized difference vegetation index, enhanced vegetation index, and soil-adjusted vegetation index variables compared to the univariate approach. The predicted SMLR model was used to estimate a spatial map of LAI. It is desirable to evaluate the stability and potentiality of regional LAI models in natural forest ecosystems against the operationally accepted Moderate Resolution Imaging Spectroradiometer (MODIS) global LAI product. To do this, the Landsat-8 pixel-based LAI map was resampled to 1 km resolution and compared with the MODIS derived LAI map. Results suggested that Landsat-8 OLI-based VIs provide significant LAI maps at moderate resolution (30 m) as well as coarse resolution (1 km) for regional climate models.     

A new three-band spectral index for mitigating the saturation in the estimation of leaf area index in wheat

The normalized difference vegetation index (NDVI) is a commonly used index for monitoring crop growth status. Previous studies have shown that the leaf area index (LAI) estimation based on NDVI is limited by saturation that occurs under conditions of relatively dense canopies (LAI > 2 m² m^–2). To reduce the saturation effect, we suggested new spectral indices through the spectral indices approach. The results suggested that the two-band normalized difference spectral index (NDSI = ((ρ_{940 –} ρ₇₃₀) /(ρ₉₄₀ + ρ₇₃₀))) resulted from the two-band spectral indices approach and the three-band modified normalized difference spectral index (mNDSI = ((ρ_{940 –} 0.8 × ρ₉₅₀) – ρ₇₃₀) /((ρ_{940 –} 0.8 × ρ₉₅₀) + ρ₇₃₀)) resulted from the three-band spectral indices approach, and they were able to mitigate saturation and improve the LAI prediction with a determination coefficient (R²) of 0.77 and 0.78, respectively. In the validation based on data from independent experiments, these new indices exhibited an accuracy with relative root mean square error (RRMSE) lower than 23.38% and bias higher than –0.40. These accuracies were significantly higher than those obtained with some existing indices with good performance in LAI estimation, such as the enhanced vegetation index (EVI) (RRMSE = 30.19%, bias = –0.34) and the modified triangular vegetation index 2 (MTVI2) (RRMSE = 29.30%, bias = –0.28), and the indices with the ability to mitigate the saturation, such as the wide dynamic range vegetation index (WDRVI) (RRMSE = 31.37%, bias = –0.54), the red-edge wide dynamic range vegetation index (red-edge WDRVI) (RRMSE = 26.34%, bias = –0.54), and the normalized difference red-edge index (NDRE) (RRMSE = 28.41%, bias = –0.56). Additionally, these new indices were more sensitive under moderate to high LAI conditions (between 2 and 8 m² m^–2). Between these two new developed spectral indices, there was no significant difference in the accuracy and sensitivity assessments. Considering the index structure and convenience in application, we demonstrated that the two-band spectral index NDSI((ρ_{940 –} ρ₇₃₀) /(ρ₉₄₀ + ρ₇₃₀)) is efficient in mitigating saturation and has considerable potential for estimating the LAI of canopies throughout the entire growing season of wheat (Triticum aestivum L.), whereas the three-band spectral index contributes lesser in the saturation mitigation provided the red-edge band has been contained.     

Comparison of Landsat 8 OLI and Landsat 7 ETM+ for estimating grassland LAI using model inversion and spectral indices: case study of Mpumalanga,South Africa

The leaf area index (LAI) is the key biophysical indicator used to assess the condition of rangeland. In this study, we investigated the implications of narrow spectral response, high radiometric resolution (12 bits), and higher signal-to-noise ratio of the Landsat 8 Operational Land Imager (OLI) sensor for the estimation of LAI. The Landsat 8 LAI estimates were compared to that of its predecessors, namely Landsat 7 Enhanced Thematic Mapper Plus (ETM+) (8 bits). Furthermore, we compared the radiative transfer model (RTM) and spectral indices approaches for estimating LAI on rangeland systems in South Africa. The RTM was inverted using artificial neural network (ANN) and lookup table (LUT) algorithms. The accuracy of the models was higher for Landsat 8 OLI, where ANN (root mean squared error, RMSE = 0. 13; R² = 0. 89), LUT (RMSE = 0. 25; R² = 0. 50), compared to Landsat 7 ETM+, where ANN (RMSE = 0. 35; R² = 0. 60), LUT (RMSE = 0. 38; R² = 0. 50). Compared to an empirical approach, the RTM provided higher accuracy. In conclusion, Landsat 8 OLI provides an improvement for the estimation of LAI over Landsat 7 ETM+. This is useful for rangeland monitoring.     

Chlorophyll content estimation in arid grasslands from Landsat-8 OLI data

In this study, an arid grassland was selected, and the chlorophyll content of the leaf and canopy level was estimated based on Landsat-8 Operational Land Imager (OLI) data using the PROSAIL radiative transfer (RT) model. Two vegetation indices (green chlorophyll index, CI_green, and greenness index, G) were selected to estimate the leaf and canopy chlorophyll content (LCC and CCC). By analysing the effect of soil background on the two indices, the LCC was divided into low and moderate-to-high levels. A different combination of the two indices was adopted at each level to improve the chlorophyll content estimation accuracy. The results suggested that the chlorophyll content estimated using the proposed method yielded a higher accuracy with coefficient of determination, R² = 0.84, root-mean-square error, RMSE = 9.67 μg cm^?2 for LCC and R² = 0.85, RMSE = 0.43 g m^?2 for CCC than that using CI_green alone with R² = 0.62, RMSE = 20.04 μg cm^?2 for LCC and R² = 0.85, RMSE = 0.71 g m^?2 for CCC. The results also confirmed the validity of this approach to estimate the chlorophyll content in arid areas.     

Validation of MERIS LAI and FAPAR products for winter wheat-sown test fields in North-East Bulgaria

Progress in deriving land surface biophysical parameters in a spatially explicit manner using remotely sensed data has greatly enhanced our ability to model ecosystem processes and monitor crop development. A multitude of satellite sensors and algorithms have been used to generate ready-to-use maps of various biophysical parameters. Validation of these products for different vegetation types is needed to assess their reliability and consistency. While most of the current satellite biophysical products have spatial resolution of one kilometre, a recent effort utilizing data from the Medium Resolution Imaging Spectrometer (MERIS) provided leaf area index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), and other canopy parameters in a resolution as fine as 300 m over the European continent. This resolution would be more appropriate for application at the regional scale, particularly for crop monitoring. This higher-resolution MERIS product has been evaluated in a limited number of studies to date. This article aims to validate LAI and FAPAR from the MERIS 10-day composite BioPar BP-10 product over winter wheat fields in northeast Bulgaria. The ground measurements of LAI and FAPAR were up-scaled and 30 m resolution reference raster layers were created using empirical relationships with Landsat TM (RMSE = 0.06 and RMSE = 0.22 for FAPAR and LAI, respectively). MERIS FAPAR and LAI were found to have significant correlation with FAPAR and LAI from the reference raster layers (R² = 0.84 and R² = 0.78, respectively). When MERIS Green LAI was calculated (incorporating the fraction of vegetation and brown vegetation cover from the BioPar BP-10 product), better correspondence with LAI values from the reference raster layer was achieved, with RMSE and bias reduced by 30–35%. The results from this study confirm the findings of previous validations showing that MERIS Green LAI tends to overestimate LAI values lower than 1. As a conclusion of the study, the BioPar BP-10 product was found to provide reliable estimates of FAPAR and acceptably accurate estimates of LAI for winter wheat crops in North-East Bulgaria.     

Monitoring boreal forest leaf area index across a Siberian burn chronosequence: a MODIS validation study

Landscapes containing differing amounts of ecological disturbance provide an excellent opportunity to validate and better understand the emerging Moderate Resolution Imaging Spectrometer (MODIS) vegetation products. Four sites, including 1‐year post‐fire coniferous, 13‐year post‐fire deciduous, 24‐year post‐fire deciduous, and >100 year old post‐fire coniferous forests, were selected to serve as a post‐fire chronosequence in the central Siberian region of Krasnoyarsk (57.3°N, 91.6°E) with which to study the MODIS leaf area index (LAI) and vegetation index (VI) products. The collection 4 MODIS LAI product correctly represented the summer site phenologies, but significantly underestimated the LAI value of the >100 year old coniferous forest during the November to April time period. Landsat 7‐derived enhanced vegetation index (EVI) performed better than normalized difference vegetation index (NDVI) to separate the deciduous and conifer forests, and both indices contained significant correlation with field‐derived LAI values at coniferous forest sites (r ² = 0.61 and r ² = 0.69, respectively). The reduced simple ratio (RSR) markedly improved LAI prediction from satellite measurements (r ² = 0.89) relative to NDVI and EVI. LAI estimates derived from ETM+ images were scaled up to evaluate the 1 km resolution MODIS LAI product; from this analysis MODIS LAI overestimated values in the low LAI deciduous forests (where LAI<5) and underestimated values in the high LAI conifer forests (where LAI>6). Our results indicate that further research on the MODIS LAI product is warranted to better understand and improve remote LAI quantification in disturbed forest landscapes over the course of the year.     

A new approach for forest decline assessments: maximizing detail and accuracy with multispectral imagery

Remote sensing of forest condition is typically based on broadband vegetation indices to quantify coarse categories of canopy condition. More detailed and accurate assessments have been demonstrated using narrowband sensors, although with more limited image availability. While differences in sensor capabilities are obvious, I hypothesized that multispectral imagery may be able to detect more subtle canopy stress symptoms if a new calibration approach was considered. This involves three major changes to traditional decline assessments: (1) calibration with more detailed field measurements, (2) consideration of narrowband derived indices adapted for broadband calculation, and (3) a multivariate calibration model. Testing this approach on Landsat-5 (TM) imagery in the Catskills, NY, USA, a five-term linear regression model (r² = 0.621, RMSE 0.403) based on a unique combination of vegetation indices sensitive to canopy chlorophyll, carotenoids, green leaf area, and water content was able to quantify a broad range of forest condition across species. When rounded to a class-based system for comparison to more traditional methods, this equation predicted decline across 42 mixed-species plots with 65% accuracy (10-classes), and 100% accuracy (5-classes). This approach was a significant improvement over commonly used vegetation indices such as NDVI (r² = 0.351, RMSE = 0.500, 10-class accuracy = 60%, and 5-class accuracy = 74%). These results suggest that relying solely on a single common vegetation index to assess forest condition may artificially limit the accuracy and detail possible with multispectral imagery. I recommend that future efforts to monitor forest decline consider this three-pronged approach to decline predictions in order to maximize the information and accuracy obtainable with broadband sensors so widely available at this time.     

Predicting Eucalyptus spp. stand volume in Zululand,South Africa: an analysis using a stochastic gradient boosting regression ensemble with multi-source data sets

Accurate, reliable, and up-to-date forest stand volume information is a prerequisite for a detailed evaluation of commercial forest resources and their sustainable management. Commercial forest responses to global climate change remain uncertain, and hence the mapping of stand volume as carbon sinks is fundamentally important in understanding the role of forests in stabilizing climate change effects. The aim of this study was to examine the utility of stochastic gradient boosting (SGB) and multi-source data to predict stand volume of a Eucalyptus plantation in South Africa. The SGB ensemble, random forest (RF), and stepwise multiple-linear regression (SMLR) were used to predict Eucalyptus stand volume and other related tree-structural attributes such as mean tree height and mean diameter at breast height (DBH). Multi-source data consisted of SPOT-5 raw spectral features (four bands), 14 spectral vegetation indices, rainfall data, and stand age. When all variables were used, the SGB algorithm showed that stand volume can be accurately estimated (R² = 0.78 and RMSE = 33.16 m³ ha^?1 (23.01% of the mean)). The competing RF ensemble produced an R² value of 0.76 and a RMSE value of 37.28 m³ ha^?1 (38.28% of the mean). SMLR on the other hand, produced an R² value of 0.65 and an RMSE value of 42.50 m³ ha^?1 (42.50% of the mean). Our study further showed that Eucalyptus mean tree height (R² = 0.83 and RMSE = 1.63 m (9.08% of the mean)) and mean diameter at breast height (R² = 0.74 and RMSE = 1.06 (7.89% of the mean)) can also be reasonably predicted using SGB and multi-source data. Furthermore, when the most important SGB model-selected variables were used for prediction, the predictive accuracies improved significantly for mean DBH (R² = 0.81 and RMSE = 1.21 cm (6.12% of the mean)), mean tree height (R² = 0.86 and RMSE = 1.39 m (7.02% of the mean)), and stand volume (R² = 0.83 and RMSE = 29.58 m³ ha^?1 (17.63% of the mean)). These results underscore the importance of integrating multi-source data with remotely sensed data for predicting Eucalyptus stand volume and related tree-structural attributes.     

Leaf area and clumping indices for a boreal mixed-wood forest: lidar,hyperspectral, and Landsat models

The leaf area index (LAI) and the clumping index (CI) provide valuable insight into the spatial patterns of forest canopies, the canopy light regime and forest productivity. This study examines the spatial patterns of LAI and CI in a boreal mixed-wood forest, using extensive field measurements and remote sensing analysis. The objectives of this study are to: (1) examine the utility of airborne lidar (light detection and ranging) and hyperspectral data to model LAI and clumping indices; (2) compare these results to those found from commonly used Landsat vegetation indices (i.e. the normalized difference vegetation index (NDVI) and the simple ratio (SR)); (3) determine whether the fusion of lidar data with Landsat and/or hyperspectral data will improve the ability to model clumping and LAI; and (4) assess the relationships between clumping, LAI and canopy biochemistry.

Regression models to predict CI were much stronger than those for LAI at the site. Lidar was the single best predictor of CI (r ² > 0.8). Landsat NDVI and SR also had a moderately strong predictive performance for CI (r ² > 0.68 with simple linear and non-linear regression forms), suggesting that canopy clumping can be predicted operationally from satellite platforms, at least in boreal mixed-wood environments. Foliar biochemistry, specifically canopy chlorophyll, carotenoids, magnesium, phosphorus and nitrogen, was strongly related to the clumping index. Combined, these results suggest that Landsat models of clumping could provide insight into the spatial distribution of foliar biochemistry, and thereby photosynthetic capacity, for boreal mixed-wood canopies. LAI models were weak (r ² < 0.4) unless separate models were used for deciduous and coniferous plots. Coniferous LAI was easier to model than deciduous LAI (r ² > 0.8 for several indices). Deciduous models of LAI were weaker for all remote sensing indices (r ² < 0.67). There was a strong, linear relationship between foliar biochemistry and LAI for the deciduous plots. Overall, our results suggest that broadband satellite indices have strong predictive performance for clumping, but that airborne hyperspectral or lidar data are required to develop strong models of LAI at this boreal mixed-wood site.     

Comparison of different regression models and validation techniques for the assessment of wheat leaf area index from hyperspectral data

Leaf area index (LAI) is one of the most important plant parameters when observing agricultural crops and a decisive factor for yield estimates. Remote-sensing data provide spectral information on large areas and allow for a detailed quantitative assessment of LAI and other plant parameters. The present study compared support vector regression (SVR), random forest regression (RFR), and partial least-squares regression (PLSR) and their achieved model qualities for the assessment of LAI from wheat reflectance spectra. In this context, the validation technique used for verifying the accuracy of an empirical–statistical regression model was very important in order to allow the spatial transferability of models to unknown data. Thus, two different validation methods, leave-one-out cross-validation (cv) and independent validation (iv), were performed to determine model accuracy. The LAI and field reflectance spectra of 124 plots were collected from four fields during two stages of plant development in 2011 and 2012. In the case of cross-validation for the separate years, as well as the entire data set, SVR provided the best results (2011: R²_cv = 0.739, 2012: R²_cv = 0.85, 2011 and 2012: R²_cv = 0.944). Independent validation of the data set from both years led to completely different results. The accuracy of PLSR (R²_iv = 0.912) and RFR (R²_iv = 0.770) remained almost at the same level as that of cross-validation, while SVR showed a clear decline in model performance (R²_iv = 0.769). The results indicate that regression model robustness largely depends on the applied validation approach and the data range of the LAI used for model building.     

Polar grid fraction as an estimator of montane tropical forest canopy structure using airborne lidar

The structure of a forest canopy is the key determinant of light transmission, use and understory availability. Airborne light detection and ranging (LiDAR) has been used successfully to measure multiple canopy structural properties, thereby greatly reducing the fieldwork required to map spatial variation in structure. However, lidar metrics to date do not reflect the full extent of the three-dimensional information available from the data. To this end, we developed a new metric, the polar grid fraction (GRID), based on gridding lidar returns in polar coordinates, in order to more closely match measurements provided by field instruments on leaf area index (LAI), gap fraction (GF) and percentage photosynthetically active radiation transmittance (tPAR). The metric summarizes the arrangement of lidar point returns for a single ground location rather than to an area surrounding the location.

Compared with more traditional proportion-based and height percentile-based estimators, the GRID estimator increased validation R² by 14.5% for GF and 6.0% for tPAR over the next best estimator. LAI was still best estimated with the more traditional statistic based on the proportion of ground returns in 14 m × 14 m moving kernels. By applying the models to a 2 × 2 m grid across the lidar coverage area, extreme values occurred in the estimations of all three response variables when using proportion-based and height percentile-based estimators. However, no extreme values were estimated by models using the GRID estimator, indicating that models based on GRID may be less influenced by spurious data. These results suggest that the GRID estimator is a strong candidate for any project requiring estimates of canopy metrics for large areas.     

Mapping tree distribution and LAI in peatlands using field methods and imaging spectroscopy: a case study for the Haaksbergerveen,the Netherlands

Leaf area index (LAI) is among the vegetation parameters that play an important role in climate, hydrological and ecological studies, and is used for assessing growth and expansion of vegetation. The main objective of this study was to develop a methodology to map the LAI distribution of birch trees (Betula pendula) in peatland ecosystems using field-based instruments and airborne-based remote-sensing techniques. The developed mapping method was validated using field-based LAI measurements using the LAI-2000 instrument. First vegetation indices, including simple ratio (SR), normalized difference vegetation index (NDVI), and reduced simple ratio (RSR), were derived from HyMap data and related to ground-based measurements of LAI. LAI related better with RSR (R² = 0.68), followed by NDVI (R² = 0.63) and SR (R² = 0.58), respectively. Areas with birch were identified using Spectral Angle Mapper (SAM) to classify the image into 11 end members of dominant species including bare soil and open water. Next, the relationship between LAI and RSR was applied to areas with birch, yielding a birch LAI map. Comparison of the map of the birch trees and field-based LAI data was done using linear regression, yielding an R² = 0.38 and an RMSE = 0.25, which is fairly accurate for a structurally highly diverse field situation. The method may prove an invaluable tool to monitor tree encroachment and assess tree LAI in these remote and poorly accessible areas.     

Estimating aboveground biomass of a mangrove plantation on the Northern coast of Vietnam using machine learning techniques with an integration of ALOS-2 PALSAR-2 and Sentinel-2A data

ABSTRACT

Aboveground biomass (AGB) of mangrove forest plays a crucial role in global carbon cycle by reducing greenhouse gas emissions and mitigating climate change impacts. Monitoring mangrove forests biomass accurately still remains challenging compared to other forest ecosystems. We investigated the usability of machine learning techniques for the estimation of AGB of mangrove plantation at a coastal area of Hai Phong city (Vietnam). The study employed a GIS database and support vector regression (SVR) to build and verify a model of AGB, drawing upon data from a survey in 25 sampling plots and an integration of Advanced Land Observing Satellite-2 Phased Array Type L-band Synthetic Aperture Radar-2 (ALOS-2 PALSAR-2) dual-polarization horizontal transmitting and horizontal receiving (HH) and horizontal transmitting and vertical receiving (HV) and Sentinel-2A multispectral data. The performance of the model was assessed using root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R²), and leave-one-out cross-validation. Usability of the SVR model was assessed by comparing with four state-of-the-art machine learning techniques, i.e. radial basis function neural networks, multi-layer perceptron neural networks, Gaussian process, and random forest. The SVR model shows a satisfactory result (R² = 0.596, RMSE = 0.187, MAE = 0.123) and outperforms the four machine learning models. The SVR model-estimated AGB ranged between 36.22 and 230.14 Mg ha^?1 (average = 87.67 Mg ha^?1). We conclude that an integration of ALOS-2 PALSAR-2 and Sentinel-2A data used with SVR model can improve the AGB accuracy estimation of mangrove plantations in tropical areas.     

Species stratification and upscaling of forest carbon estimates to landscape scale using GeoEye-1 image and lidar data in sub-tropical forests of Nepal

Aboveground forest biomass and carbon estimation at landscape scale is crucial for implementation of REDD+ programmes. This study aims to upscale the forest carbon estimates using GeoEye-1 image and small footprint lidar data from small areas to a landscape level using RapidEye image. Species stratification was carried out based on the spectral separability curve of GeoEye-1 image, and comparison of mean intensity and mean plot height of the trees from lidar data. GeoEye-1 image and lidar data were segmented using region growing approach to delineate individual tree crowns; and the segmented crowns (CPA) of tree were further used to establish a relationship with field measured carbon and total trees’ height. Carbon stock measured from field, individual tree crown (ITC) segmentation approach and area-based approach (ABA) was compared at plot level using one-way ANOVA and post hoc Tukey comparison test. ITC-based carbon estimates was used to establish a relationship with spectral reflectance of RapidEye image variables (NDVI, RedEdge NDVI, PC1, single band of RedEdge, and NIR) to upscale the carbon at landscape level. One-way ANOVA resulted in a highly significant difference (p-value < 0.005) between the mean plot height and lidar intensity to stratify Shorea robusta and Other species successfully. ITC carbon stock estimation models of two major tree species explained about 88% and 79% of the variances, respectively, at 95% confidence level. The ABA estimated carbon was highly correlated (R² = 0.83, RMSE = 20.04) to field measured carbon with higher accuracy than the ITC estimated carbon. A weak relationship was observed between the carbon stock and the RapidEye image variables. However, upscaling of carbon estimates from ABA is likely to improve the relationship of the RapidEye variables rather than upscaling the carbon estimates from ITC approach.     

Retrieval of leaf chlorophyll content in field crops using narrow-band indices: effects of leaf area index and leaf mean tilt angle

Reliable estimation of leaf chlorophyll-a and -b content (chl-a + b) at canopy scales is essential for monitoring vegetation productivity, physiological stress, and nutrient availability. To achieve this, narrow-band vegetation indices (VIs) derived from imaging spectroscopy data are commonly used. However, VIs are affected by canopy structures other than chl-a + b, such as leaf area index (LAI) and leaf mean tilt angle (MTA). In this study, we evaluated the performance of 58 VIs reported in the literature to be chl-a + b-sensitive against a unique measured set of species-specific leaf angles for six crop species in southern Finland. We created a large simulated canopy reflectance database (100,000 canopy configurations) using the physically based PROSAIL (coupling of PROSPECT and SAIL (Scattering by Arbitrarily Inclined Leaves) radiative transfer models) model. The performance of model-simulated indices was compared against airborne AISA Eagle II imaging spectroradiometer data and field-measured chl-a + b, LAI, and MTA values. In general, LAI had a positive effect on the strength of the correlation between chl-a + b and VIs while MTA had a negative effect in both measured and simulated data. Three indices (REIP (red edge inflection point), TCARI (transformed chlorophyll absorption ratio index)/OSAVI (optimized soil-adjusted vegetation index), and CTR6 (Carter indices)) showed strong correlations with chl-a + b and similar performance in model-simulated and measured data set. However, only two (TCARI/OSAVI and CTR6) were independent from LAI and MTA. We consider these two indices robust proxies of crop leaf chl-a + b.     

Discrete return lidar-based prediction of leaf area index in two conifer forests

Leaf area index (LAI) is a key forest structural characteristic that serves as a primary control for exchanges of mass and energy within a vegetated ecosystem. Most previous attempts to estimate LAI from remotely sensed data have relied on empirical relationships between field-measured observations and various spectral vegetation indices (SVIs) derived from optical imagery or the inversion of canopy radiative transfer models. However, as biomass within an ecosystem increases, accurate LAI estimates are difficult to quantify. Here we use lidar data in conjunction with SPOT5-derived spectral vegetation indices (SVIs) to examine the extent to which integration of both lidar and spectral datasets can estimate specific LAI quantities over a broad range of conifer forest stands in the northern Rocky Mountains. Our results show that SPOT5-derived SVIs performed poorly across our study areas, explaining less than 50% of variation in observed LAI, while lidar-only models account for a significant amount of variation across the two study areas located in northern Idaho; the St. Joe Woodlands (R² = 0.86; RMSE = 0.76) and the Nez Perce Reservation (R² = 0.69; RMSE = 0.61). Further, we found that LAI models derived from lidar metrics were only incrementally improved with the inclusion of SPOT 5-derived SVIs; increases in R² ranged from 0.02–0.04, though model RMSE values decreased for most models (0–11.76% decrease). Significant lidar-only models tended to utilize a common set of predictor variables such as canopy percentile heights and percentile height differences, percent canopy cover metrics, and covariates that described lidar height distributional parameters. All integrated lidar-SPOT 5 models included textural measures of the visible wavelengths (e.g. green and red reflectance). Due to the limited amount of LAI model improvement when adding SPOT 5 metrics to lidar data, we conclude that lidar data alone can provide superior estimates of LAI for our study areas.     

TanDEM-X elevation model data for canopy height and aboveground biomass retrieval in a tropical peat swamp forest

It was demonstrated in the past that radar data is useful to estimate aboveground biomass due to their interferometric capability. Therefore, the potential of a globally available TanDEM-X digital elevation model (DEM) was investigated for aboveground biomass estimation via canopy height models (CHMs) in a tropical peat swamp forest. However, CHMs based on X-band interferometers usually require external terrain models. High accurate terrain models are not available on global scale. Therefore, an approach exclusively based on TanDEM-X and the decrease of accuracy compared to an approach utilizing a high accurate terrain model is assessed. In addition, the potential of X-band interferometric heights in tropical forests needs to be evaluated. Therefore, two CHMs were derived from an intermediate TanDEM-X DEM (iDEM; as a precursor for WorldDEM^TM) alone and in combination with lidar measurements used as terrain model. The analysis showed high accuracies (root mean square error [RMSE] = 5 m) for CHMs based on iDEM and reliable estimation of aboveground biomass. The iDEM CHM, exclusively based on TanDEM-X, achieved a poor R² of 0.2, nonetheless resulted in a cross-validated RMSE of 54 t ha^?1 (16%). The low R² suggested that the X-band height alone was not sufficient to estimate an accurate CHM, and thus the need for external terrain models was confirmed. A CHM retrieved from the difference of iDEM and an accurate lidar terrain model achieved a considerably higher correlation with aboveground biomass (R² = 0.68) and low cross-validated RMSE of 24.5 t ha^?1 (7.5%). This was higher or comparable to other aboveground biomass estimations in tropical peat swamp forests. The potential of X-band interferometric heights for CHM and biomass estimation was thus confirmed in tropical forest in addition to existing knowledge in boreal forests.