Dataset Information

Estimation of forage biomass and vegetation cover in grasslands using UAV imagery.

ABSTRACT: Grasslands are among the most widespread ecosystems on Earth and among the most degraded. Their characterization and monitoring are generally based on field measurements, which are incomplete spatially and temporally. The recent advent of unmanned aerial vehicles (UAV) provides data at unprecedented spatial and temporal resolutions. This study aims to test and compare three approaches based on multispectral imagery acquired by UAV to estimate forage biomass or vegetation cover in grasslands. The study site is composed of 30 pasture plots (25 × 50 m), 5 bare soil plots (25 x 50), and 6 control plots (5 × 5 m) on a 14-ha field maintained at various biomass levels by grazing rotations and clipping over a complete growing season. A total of 14 flights were performed. A first approach based on structure from motion was used to generate a volumetric-based biomass estimation model (R2 of 0.93 and 0.94 for fresh biomass [FM] and dry biomass [DM], respectively). This approach is not very sensitive to low vegetation levels but is accurate for FM estimation greater than 0.5 kg/m2 (0.1 kg DM/m2). The Green Normalized Difference Vegetation Index (GNDVI) was selected to develop two additional approaches. One is based on a regression biomass prediction model (R2 of 0.80 and 0.66 for FM and DM, respectively) and leads to an accurate estimation at levels of FM lower than 3 kg/m2 (0.6 kg DM/m2). The other approach is based on a classification of vegetation cover from clustering of GNDVI values in four classes. This approach is more qualitative than the other ones but more robust and generalizable. These three approaches are relatively simple to use and applicable in an operational context. They are also complementary and can be adapted to specific applications in grassland characterization.

SUBMITTER: Theau J

PROVIDER: S-EPMC7833225 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimation of forage biomass and vegetation cover in grasslands using UAV imagery.

Théau Jérôme J Lauzier-Hudon Étienne É Aubé Lydiane L Devillers Nicolas N

PloS one 20210125 1

Grasslands are among the most widespread ecosystems on Earth and among the most degraded. Their characterization and monitoring are generally based on field measurements, which are incomplete spatially and temporally. The recent advent of unmanned aerial vehicles (UAV) provides data at unprecedented spatial and temporal resolutions. This study aims to test and compare three approaches based on multispectral imagery acquired by UAV to estimate forage biomass or vegetation cover in grasslands. The ...[more]

PMID: 33493223

Similar Datasets

Project description:BackgroundKarst vegetation is of great significance for ecological restoration in karst areas. Vegetation Indices (VIs) are mainly related to plant yield which is helpful to understand the status of ecological restoration in karst areas. Recently, karst vegetation surveys have gradually shifted from field surveys to remote sensing-based methods. Coupled with the machine learning methods, the Unmanned Aerial Vehicle (UAV) multispectral remote sensing data can effectively improve the detection accuracy of vegetation and extract the important spectrum features.ResultsIn this study, UAV multispectral image data at flight altitudes of 100 m, 200 m, and 400 m were collected to be applied for vegetation detection in a karst area. The resulting ground resolutions of the 100 m, 200 m, and 400 m data are 5.29, 10.58, and 21.16 cm/pixel, respectively. Four machine learning models, including Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Deep Learning (DL), were compared to test the performance of vegetation coverage detection. 5 spectral values (Red, Green, Blue, NIR, Red edge) and 16 VIs were selected to perform variable importance analysis on the best detection models. The results show that the best model for each flight altitude has the highest accuracy in detecting its training data (over 90%), and the GBM model constructed based on all data at all flight altitudes yields the best detection performance covering all data, with an overall accuracy of 95.66%. The variables that were significantly correlated and not correlated with the best model were the Modified Soil Adjusted Vegetation Index (MSAVI) and the Modified Anthocyanin Content Index (MACI), respectively. Finally, the best model was used to invert the complete UAV images at different flight altitudes.ConclusionsIn general, the GBM_all model constructed based on UAV imaging with all flight altitudes was feasible to accurately detect karst vegetation coverage. The prediction models constructed based on data from different flight altitudes had a certain similarity in the distribution of vegetation index importance. Combined with the method of visual interpretation, the karst green vegetation predicted by the best model was in good agreement with the ground truth, and other land types including hay, rock, and soil were well predicted. This study provided a methodological reference for the detection of karst vegetation coverage in eastern China.

Project description:Woody biomass dynamics are an expression of ecosystem function, yet biomass estimates do not provide information on the spatial distribution of woody vegetation within the vertical vegetation subcanopy. We demonstrate the ability of airborne light detection and ranging (LiDAR) to measure aboveground biomass and subcanopy structure, as an explanatory tool to unravel vegetation dynamics in structurally heterogeneous landscapes. We sampled three communal rangelands in Bushbuckridge, South Africa, utilised by rural communities for fuelwood harvesting. Woody biomass estimates ranged between 9 Mg ha(-1) on gabbro geology sites to 27 Mg ha(-1) on granitic geology sites. Despite predictions of woodland depletion due to unsustainable fuelwood extraction in previous studies, biomass in all the communal rangelands increased between 2008 and 2012. Annual biomass productivity estimates (10-14% p.a.) were higher than previous estimates of 4% and likely a significant contributor to the previous underestimations of modelled biomass supply. We show that biomass increases are attributable to growth of vegetation <5 m in height, and that, in the high wood extraction rangeland, 79% of the changes in the vertical vegetation subcanopy are gains in the 1-3 m height class. The higher the wood extraction pressure on the rangelands, the greater the biomass increases in the low height classes within the subcanopy, likely a strong resprouting response to intensive harvesting. Yet, fuelwood shortages are still occurring, as evidenced by the losses in the tall tree height class in the high extraction rangeland. Loss of large trees and gain in subcanopy shrubs could result in a structurally simple landscape with reduced functional capacity. This research demonstrates that intensive harvesting can, paradoxically, increase biomass and this has implications for the sustainability of ecosystem service provision. The structural implications of biomass increases in communal rangelands could be misinterpreted as woodland recovery in the absence of three-dimensional, subcanopy information.

Project description:Plant lodging is one of the most essential phenotypes for soybean breeding programs. Soybean lodging is conventionally evaluated visually by breeders, which is time-consuming and subject to human errors. This study aimed to investigate the potential of unmanned aerial vehicle (UAV)-based imagery and machine learning in assessing the lodging conditions of soybean breeding lines. A UAV imaging system equipped with an RGB (red-green-blue) camera was used to collect the imagery data of 1266 four-row plots in a soybean breeding field at the reproductive stage. Soybean lodging scores were visually assessed by experienced breeders, and the scores were grouped into four classes, i.e., non-lodging, moderate lodging, high lodging, and severe lodging. UAV images were stitched to build orthomosaics, and soybean plots were segmented using a grid method. Twelve image features were extracted from the collected images to assess the lodging scores of each breeding line. Four models, i.e., extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), were evaluated to classify soybean lodging classes. Five data preprocessing methods were used to treat the imbalanced dataset to improve classification accuracy. Results indicate that the preprocessing method SMOTE-ENN consistently performs well for all four (XGBoost, RF, KNN, and ANN) classifiers, achieving the highest overall accuracy (OA), lowest misclassification, higher F1-score, and higher Kappa coefficient. This suggests that Synthetic Minority Oversampling-Edited Nearest Neighbor (SMOTE-ENN) may be a good preprocessing method for using unbalanced datasets and the classification task. Furthermore, an overall accuracy of 96% was obtained using the SMOTE-ENN dataset and ANN classifier. The study indicated that an imagery-based classification model could be implemented in a breeding program to differentiate soybean lodging phenotype and classify lodging scores effectively.

Project description:Forest understory vegetation is an important characteristic of the forest. Predicting and mapping understory is a critical need for forest management and conservation planning, but it has proved difficult with available methods to date. LiDAR has the potential to generate remotely sensed forest understory structure data, but this potential has yet to be fully validated. Our objective was to examine the capacity of LiDAR point cloud data to predict forest understory cover. We modeled ground-based observations of understory structure in three vertical strata (0.5 m to < 1.5 m, 1.5 m to < 2.5 m, 2.5 m to < 3.5 m) as a function of a variety of LiDAR metrics using both mixed-effects and Random Forest models. We compared four understory LiDAR metrics designed to control for the spatial heterogeneity of sampling density. The four metrics were highly correlated and they all produced high values of variance explained in mixed-effects models. The top-ranked model used a voxel-based understory metric along with vertical stratum (Akaike weight = 1, explained variance = 87%, cross-validation error = 15.6%). We found evidence of occlusion of LiDAR pulses in the lowest stratum but no evidence that the occlusion influenced the predictability of understory structure. The Random Forest model results were consistent with those of the mixed-effects models, in that all four understory LiDAR metrics were identified as important, along with vertical stratum. The Random Forest model explained 74.4% of the variance, but had a lower cross-validation error of 12.9%. We conclude that the best approach to predict understory structure is using the mixed-effects model with the voxel-based understory LiDAR metric along with vertical stratum, because it yielded the highest explained variance with the fewest number of variables. However, results show that other understory LiDAR metrics (fractional cover, normalized cover and leaf area density) would still be effective in mixed-effects and Random Forest modelling approaches.

Project description:BackgroundBiomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained.ResultsMore precise results with a lower mean absolute error (MAE) were obtained with RF (MAE = 0.17 kg/m2) compared to the PLSR (MAE = 0.20 kg/m2). High accuracy in the prediction of soybean FB was achieved using only four predictors (CC, PH and two VIs). The selected model was additionally tested in a two-year trial on an independent set of soybean genotypes in drought simulation environments. The results showed that soybean grown under drought conditions accumulated less biomass than the control, which was expected due to the limited resources.ConclusionThe research proved that soybean FB could be successfully predicted using UAV photos and MLM. The filtration of highly correlated variables reduced the final number of predictors, improving the efficiency of remote biomass estimation. The additional testing conducted in the independent environment proved that model is capable to distinguish different values of soybean FB as a consequence of drought. Assessed variability in FB indicates the robustness and effectiveness of the proposed model, as a novel tool for the non-destructive estimation of soybean FB.

Dataset Information

Estimation of forage biomass and vegetation cover in grasslands using UAV imagery.

Publications

Estimation of forage biomass and vegetation cover in grasslands using UAV imagery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets