Above-Ground Biomass Estimation in Oats Using UAV Remote Sensing and Machine Learning

Current strategies for phenotyping above-ground biomass in field breeding nurseries demand significant investment in both time and labor. Unmanned aerial vehicles (UAV) can be used to derive vegetation indices (VIs) with high throughput and could provide an efficient way to predict forage yield with high accuracy. The main objective of the study is to investigate the potential of UAV-based multispectral data and machine learning approaches in the estimation of oat biomass. UAV equipped with a multispectral sensor was flown over three experimental oat fields in Volga, South Shore, and Beresford, South Dakota, USA, throughout the pre- and post-heading growth phases of oats in 2019. A variety of vegetation indices (VIs) derived from UAV-based multispectral imagery were employed to build oat biomass estimation models using four machine-learning algorithms: partial least squares (PLS), support vector machine (SVM), Artificial neural network (ANN), and random forest (RF). The results showed that several VIs derived from the UAV collected images were significantly positively correlated with dry biomass for Volga and Beresford (r = 0.2–0.65), however, in South Shore, VIs were either not significantly or weakly correlated with biomass. For Beresford, approximately 70% of the variance was explained by PLS, RF, and SVM validation models using data collected during the post-heading phase. Likewise for Volga, validation models had lower coefficient of determination (R2 = 0.20–0.25) and higher error (RMSE = 700–800 kg/ha) than training models (R2 = 0.50–0.60; RMSE = 500–690 kg/ha). In South Shore, validation models were only able to explain approx. 15–20% of the variation in biomass, which is possibly due to the insignificant correlation values between VIs and biomass. Overall, this study indicates that airborne remote sensing with machine learning has potential for above-ground biomass estimation in oat breeding nurseries. The main limitation was inconsistent accuracy in model prediction across locations. Multiple-year spectral data, along with the inclusion of textural features like crop surface model (CSM) derived height and volumetric indicators, should be considered in future studies while estimating biophysical parameters like biomass.

Mangrove Above-Ground Biomass and Carbon Stock in the Karimunjawa-Kemujan Islands Estimated from Unmanned Aerial Vehicle-Imagery

Blue carbon ecosystems in the Karimunjawa Islands may play a vital role in absorbing and storing the releasing carbon from the Java Sea. The present study investigated mangrove above-ground biomass (AGB) and carbon stock in the Karimunjawa-Kemujan Islands, the largest mangrove area in the Karimunjawa Islands. Taking the aerial photos from an Unmanned Aerial Vehicle combined with Global Navigation Satellite System (GNSS) measurements, we generated Digital Surface Model (DSM) and Digital Terrain Model (DTM) with high accuracy. We calculated mangrove canopy height by subtracting DSM from DTM and then converted it into Lorey’s height. The highest mangrove canopy is located along the coastline facing the sea, ranging from 8 m to 15 m. Stunted mangroves 1 m to 8 m in height are detected mainly in the inner areas. AGBs were calculated using an allometric equation destined for the Southeast and East Asia region. Above-ground carbon biomass is half of AGB. The AGB and carbon biomass of mangroves in the Karimunjawa-Kemujan Islands range from 8 Mg/ha to 328 Mg/ha, and from 4 MgC/ha to 164 MgC/ha, respectively. With a total area of 238.98 ha, the potential above-ground carbon stored in the study area is estimated as 16,555.46 Mg.

Importance Of Small Diameter Woody Plants And Treelet Species In Tropical Wet Evergreen Forest Of Southern Western Ghats, India

Tropical forests have long been accepted for their productivity and ecosystem services on account of their high diversity and stand structural attributes. In spite of their significance, tropical forests, and especially those of Asia, remain understudied. Until recently, most forest inventories in Asia have concentrated on trees 10 cm in diameter. Floristic composition, plant species diversity, above-ground biomass, basal area, and diversity were investigated across different life forms and two-diameter classes in a large-scale 10-ha plot, in the undisturbed tropical seasonal rain forest of Southern Western Ghats, Kerala, India. The regeneration pattern of the study area was examined by evaluating fisher's alpha and IVI (Important Value Index) across three layers of vegetation (seedling, sapling, and tree). Within the plot, we recorded 25,390 woody plant species ≥1 cm dbh from 45 families, 91 genera, and 106 species. Plant density was 2539 woody individuals per hectare, with a basal area of 47.72 m2/ha and above-ground biomass of 421.77 Mg/ha. By basal area, density, and frequency, the Rubiaceae, Sapotaceae, and Malvaceae families were the most important. Small-diameter trees (1 cm ≤ dbh ≤10 cm) were found to be 78 percent of the total tree population, 20.2 percent of the basal area, and 1.4 percent of the aboveground biomass. They also possessed 6 percent more diversity at the family level, 10% more diversity at the genus level, and 12% more diversity at the species level than woody individuals under 10 cm dbh. Woody individuals of treelets life form and small-diameter classes were much more diverse and dense than the other groups, indicating that results based only on larger canopy trees and larger diameter class maybe not be an appropriate representation of the diversity status of a particular tropical forest type. The lower density of individuals in the initial girth class indicates the vulnerability of the forest system to anthropogenic, natural disturbance and a changing climate. Reduce the minimum diameter limit down to 1 cm, in contrast to 10 cm limit used in most of the evergreen forest inventories, revealed a high density and diversity in the lower stories.

An Allometric Model Based Approach For Estimating Biomass In Seven Indian Bamboo Species In Western Himalayan Foothills, India

The rapid growth rate, high biomass production, and annual harvesting, makes bamboo as suitable species for commercial production. Allometric equations for many broadleaf and conifer tree species are available. However, knowledge on biomass production and allometric equations of bamboos are limited. This study aims at developing species specific allometric models for predicting biomass and synthetic height values as a proxy variable for seven bamboo species in Himalayan foothills. Two power form based allometric models were used to predict above ground and culm biomass using Diameter at breast height (D) alone and D in combination with culm height (H) as independent variable. This study also extended to establishing H-D allometric model that can be used to generate synthetic H values as proxy to missing H. In the seven bamboo species studied, among three major biomass component (culm, branch and foliage), culm is the most important component with highest share (69.56 to 78.71%).Distribution of percentage (%) share of culm, branch and foliage to above ground fresh weight varies significantly between different bamboo species. D. hamiltonii has highest productivity for above ground biomass components. Ratio of dry to fresh weight of seven bamboo species was estimated for culm, branch, foliage and above ground biomass to convert fresh weight to dry weight.

Performance Evaluation of the WOFOST Model for Estimating Evapotranspiration, Soil Water Content, Grain Yield and Total Above-Ground Biomass of Winter Wheat in Tensift Al Haouz (Morocco): Application to Yield Gap Estimation

The main goal of this investigation was to evaluate the potential of the WOFOST model for estimating leaf area index (LAI), actual evapotranspiration (ETa), soil moisture content (SM), above-ground biomass levels (TAGP) and grain yield (TWSO) of winter wheat in the semi-arid region of Tensift Al Haouz, Marrakech (central Morocco). An application for the estimation of the Yield Gap is also provided. The model was firstly calibrated based on three fields data during the 2002–2003 and 2003–2004 growing seasons, by using the WOFOST implementation in the Python Crop simulation Environment (PCSE) to optimize the different parameters that provide the minimum difference between the measured and simulated LAI, TAGP, TWSO, SM and ETa. Then, the model validation was performed based on the data from five other wheat fields. The results obtained showed a good performance of the WOFOST model for the estimation of LAI during both growing seasons on all validation fields. The average R2, RSME and NRMSE were 91.4%, 0.57 m2/m2, and 41.4%, respectively. The simulated ETa dynamics also showed a good agreement with the observations by eddy covariance systems. Values of 60% and 72% for R2, 0.8 mm and 0.7 mm for RMSE, 54% and 31% for NRMSE are found for the two validation fields, respectively. The model’s ability to predict soil moisture content was also found to be satisfactory; the two validation fields gave R2 values equal to 48% and 49%, RMSE values equal to 0.03 cm3/cm3 and 0.05 cm3/cm3, NRMSE values equal to 11% and 19%. The calibrated model had a medium performance with respect to the simulation of TWSO (R2 = 42%, RSME = 512 kg/ha, NRMSE = 19%) and TAGP (R2 = 34% and RSME = 936 kg/ha, NRMSE = 16%). After accurate calibration and validation of the WOFOST model, it was used for analyzing the gap yield since this model is able to estimate the potential yield. The WOFOST model allowed a good simulation of the potential yield (7.75 t/ha) which is close to the optimum value of 6.270 t/ha in the region. Yield gap analysis reveals a difference of 5.35 t/ha on average between the observed yields and the potential yields calculated by WOFOST. Such difference is ascribable to many factors such as the crop cycle management, agricultural practices such as water and fertilization supply levels, etc. The various simulations (irrigation scenarios) showed that early sowing is more adequate than late sowing in saving water and obtaining adequate grain yield. Based on various simulations, it has been shown that the early sowing (mid to late December) is more adequate than late sowing with a total amount of water supply of about 430 mm and 322 kg (140 kg of N, 80 kg of P and 102 kg of K) of fertilization to achieve the potential yield. Consequently, the WOFOST model can be considered as a suitable tool for quantitative monitoring of winter wheat growth in the arid and semi-arid regions.

Above-Ground Biomass Estimation of Plantation with Complex Forest Stand Structure Using Multiple Features from Airborne Laser Scanning Point Cloud Data

Accurate forest above-ground biomass (AGB) estimation is important for dynamic monitoring of forest resources and evaluation of forest carbon sequestration capacity. However, it is difficult to depict the forest’s vertical structure and its heterogeneity using optical remote sensing when estimating forest AGB, for the reason that electromagnetic waves cannot penetrate the canopy’s surface to obtain low vegetation information, especially in subtropical and tropical forests with complex layer structure and tree species composition. As an active remote sensing technology, an airborne laser scanner (ALS) can penetrate the canopy surface to obtain three-dimensional structure information related to AGB. This paper takes the Jiepai sub-forest farm and the Gaofeng state-owned forest farm in southern China as the experimental area and explores the optimal features from the ALS point cloud data and AGB inversion model in the subtropical forest with complex tree species composition and structure. Firstly, considering tree canopy structure, terrain features, point cloud structure and density features, 63 point cloud features were extracted. In view of the biomass distribution differences of different tree species, the random forest (RF) method was used to select the optimal features of each tree species. Secondly, four modeling methods were used to establish the AGB estimation models of each tree species and verify their accuracy. The results showed that the features related to tree height had a great impact on forest AGB. The top features of Cunninghamia Lanceolata (Chinese fir) and Eucalyptus are all related to height, Pinus (pine tree) is also related to terrain features and other broadleaved trees are also related to point cloud density features. The accuracy of the stepwise regression model is best with the AGB estimation accuracy of 0.19, 0.76, 0.71 and 0.40, respectively, for the Chinese fir, pine tree, eucalyptus and other broadleaved trees. In conclusion, the proposed linear regression AGB estimation model of each tree species combining different features derived from ALS point cloud data has high applicability, which can provide effective support for more accurate forest AGB and carbon stock inventory and monitoring.

Estimation of carbon stock in seagrass communities in Central Tapanuli

This study aims to determine the carbon stock in seagrass communities in Central Tapanuli, North Sumatera, Indonesia. The research was conducted from July to August 2020 in the coastal areas of Hajoran and Jago Jago. The parameters measured in this study were density, coverage, biomass, carbon content, and carbon stock in seagrass. Biomass analysis and carbon measurement are divided into the top (above-ground biomass) and the bottom substrate (below-ground biomass). Carbon measurements are conducted using the loss on ignition (LOI) approach. The results showed that the seagrass ecosystem on the coast of Central Tapanuli Regency, which was covered by monospecies Enhalus acoroides, was in a less healthy condition with a cover percentage of 30.3-33.3% and a density of 59-67 shoots/m2. Above-ground and below-ground seagrass biomass reached 140.19-188.72 g/m2 and 368.13-423.69 g/m2 respectively, while carbon stock reached 70.57-94.86 g Corg/m2 and 18731-19603 g Corg/m2 and total standing stock range 257.87-290.90 g Corg/m2. The data obtained from this research can be used as a database to see the potential of seagrass beds as storage of CO2 and as an effort to mitigate and adapt to climate change.

Richesse Floristique Et Stockage De Carbone De La Zone Agricole De La Forêt De Kissila Dans Le Mayombe Congolais

Sustainable forest management remains a major challenge for the international and local community in addressing deforestation and forest degradation. These forests are now experiencing a very marked degradation, mainly caused by agricultural practices. This study assessed the floristic richness and the stock of aerial carbon in order to contribute to a better knowledge of the natural resources of this forest. Five plots of 50m each have been installed with a total area of 12,500m² or 1,25ha. All trees of Diameter to Chest Height (DHP) ≥ 10cm were surveyed at 1.30m from the soil in each plot. Species richness, ecological spectrum, floristic diversity indices, and structural parameters were studied. Above-ground biomass was calculated using Djomo's allometric equation and carbon estimation by above-ground biomass x 0.47. The floristic inventory helped to identify 309 trees that were inventoried, comprising 79 species, 63 genera, and 32 families. The family of Annonaceae (11.39 %) is the most qualitatively represented while that of Olacaceae (11.65%) is the most quantitatively represented. Diversity indices tend to be 5, while density per hectare and average basal area are 247 trees and 10.71 m²/ha. The average calculated aboveground biomass is 311.76tC/ha and the average carbon stock is 89.5tC/ha. This study shows that the forest in this area can be classified as a highly disturbed secondary forest. La gestion durable des forêts reste un problème majeur que doit faire face la communauté internationale et locale dans la lutte contre la déforestation et la dégradation des forêts. Ces forêts connaissent de nos jours une dégradation très accentuée principalement causée par les pratiques agricoles. Cette étude a pour objectif d’évaluer la richesse floristique et d’estimer le stock de carbone aérien afin de contribuer à une meilleure connaissance des ressources naturelles de cette forêt du Mayombe en général et celle du village Kissila en particulier. Cinq parcelles de 50 m de côté chacune ont été installées avec une superficie totale de 12.500 m² soit 1,25 ha. Tous les arbres de Diamètre à Hauteur de la Poitrine (DHP) ≥10 cm ont été inventoriés à 1,30 m du sol dans chaque parcelle. La richesse spécifique, le spectre écologique, les indices de diversité floristique, ainsi que les paramètres structuraux ont été étudiés. La biomasse aérienne a été calculée à partir de l’équation allométrique de Djomo et l’estimation du carbone par la biomasse aérienne x 0,47. L’inventaire floristique a permis d’identifier 309 arbres répartis en 79 espèces, 63 genres et 32 familles. La famille des Annonaceae (11,39 %°) est la plus représentée qualitativement et celle des Olacaceae quantitativement (11,65%). Les indices de diversité de Shannon tendent vers 5, la densité à l’hectare et la surface terrière moyenne sont de 247 arbres et 10,71 m²/ha. La biomasse aérienne moyenne calculée est de 311,76tC/ha et le stock de carbone aérien moyen est de 89,5 tC/ha. Cette étude montre que la forêt de cette zone peut être classée comme une forêt secondaire fortement perturbée.