Integration of UAV, Sentinel-1, and Sentinel-2 Data for Mangrove Plantation Aboveground Biomass Monitoring in Senegal

Navarro, José Antonio Suárez; Algeet, Nur; Fernández-Landa, Alfredo; Esteban, Jéssica; Rodríguez-Noriega, Pablo; Guillén-Climent, María Luz

doi:10.3390/rs11010077

Cited by 127 publications

(96 citation statements)

References 88 publications

(136 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image transformations for optical and SAR data have commonly been applied in mangrove AGB retrievals in previous studies [7,11,19]. In this study, we employed an SAR image transformation for the ALOS-2 PALSAR-2 imagery consisting of a combination of multi-polarizations [21] and used eight vegetation indices (VIs) of the S-2 MSI data, as shown in Table 3, because each index is sensitive to the mangrove structure and biomass [29,46,47].…”

Section: Image Transformation Of the S-2 Multispectral And Alos-2 Palmentioning

confidence: 99%

“…The performance of the SVR model is highly influenced by the choice of the various kernel functions. To minimize the bias, the radial basis function (RBF) kernel was used in the current study because it has been applied to forest biophysical parameter retrievals in prior studies [11,47].…”

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

“…influenced by the choice of the various kernel functions. To minimize the bias, the radial basis function (RBF) kernel was used in the current study because it has been applied to forest biophysical parameter retrievals in prior studies [11,47]. The quality of the mangrove AGB retrieval can be evaluated by the ε insensitive loss function developed by Vapnik [73].…”

Section: Hyperparametermentioning

confidence: 99%

“…These indices are often employed to evaluate the differences between the measured AGB and the predicted AGB data [47] because RMSE (Equation (3)) and R 2 (Equation (4)) are standard criteria used to measure statistical errors in regression models. Higher R 2 and lower RMSE values indicate better performance for an ML model [11,16]. We employed Scikit-learn in Python 3.7 to evaluate the performances of all the ML models in the current study [78].…”

Section: Model Evaluationmentioning

confidence: 99%

“…In recent years, remote sensing-based approaches have been widely used to retrieve mangrove AGB and map carbon stocks using various sensors ranging from optical and synthetic aperture radar (SAR) to light detection and ranging (LiDAR) data [10][11][12] because such sensors provide a large number of benefits compared to traditional field-based methods such as lower cost, faster speed, easier repeatability, and the coverage of wider areas [13,14]. However, to date, there have been no attempts to investigate an integration of optical and SAR sensors, such as L-band, X-band, and C-band data, to retrieve the mangrove AGB using novel machine-learning (ML) techniques in tropical regions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

et al. 2020

View full text Add to dashboard Cite

This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2 data to estimate the mangrove above-ground biomass (AGB), including small and shrub mangrove patches in the Red River Delta biosphere reserve across the northern coast of Vietnam. We used the novel extreme gradient boosting decision tree (XGBR) technique together with genetic algorithm (GA) optimization for feature selection to construct and verify a mangrove AGB model using data from a field survey of 105 sampling plots conducted in November and December of 2018 and incorporated the dual polarimetric (HH and HV) data of the ALOS-2 PALSAR-2 L-band and the Sentinel-2 multispectral data combined with Sentinel-1 (C-band VV and VH) data. We employed the root-mean-square error (RMSE) and coefficient of determination (R 2 ) to evaluate the performance of the proposed model. The capability of the XGBR-GA model was assessed via a comparison with other machine-learning (ML) techniques, i.e., the CatBoost regression (CBR), gradient boosted regression tree (GBRT), support vector regression (SVR), and random forest regression (RFR) models. The XGBR-GA model yielded a promising result (R 2 = 0.683, RMSE = 25.08 Mg·ha −1 ) and outperformed the four other ML models. The XGBR-GA model retrieved a mangrove AGB ranging from 17 Mg·ha −1 to 142 Mg·ha −1 (with an average of 72.47 Mg·ha −1 ). Therefore, multisource optical and synthetic aperture radar (SAR) combined with the XGBR-GA model can be used to estimate the mangrove AGB in North Vietnam. The effectiveness of the proposed method needs to be further tested and compared to other mangrove ecosystems in the tropics.

show abstract

Section: Image Transformation Of the S-2 Multispectral And Alos-2 Palmentioning

confidence: 99%

Section: Support Vector Regression (Svr)mentioning

confidence: 99%

Section: Hyperparametermentioning

confidence: 99%

Section: Model Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

et al. 2020

View full text Add to dashboard Cite

show abstract

A performance‐aware routing mechanism for flying ad hoc networks

Ali

Islam

Song

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Flying ad hoc networks (FANETs) are visioned to unlock the potential of the Internet of Drones in various application scenarios like surveillance, agriculture, health care, disaster management, and rescue operations. As the unmanned aerial vehicles possess fast movements and frequent topological variations, selection of the next hop, self‐adaptation, and avoidance of dissemination loops have proven to be the challenging issues that have a considerable impact on the performance of a FANET. We propose a performance‐aware routing mechanism, G‐OLSR, for efficient communication and collaboration among the unmanned aerial vehicles in a FANET environment. The self‐adaptation of the network in case of any topological changes is considered in the proposed mechanism. Moreover, the proposed mechanism avoids the dissemination loops and it, consequently, improves the performance of the network. The simulation results show that the proposed mechanism performs better in terms of delay, message overhead, packet delivery ratio, and throughput than Optimized Link State Routing.

show abstract

Characterizing spatial variability in coastal wetland biomass across multiple scales using UAV and satellite imagery

Doughty

Ambrose

Okin

et al. 2021

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

Coastal wetland biomass is an important indicator of wetland productivity, carbon storage, health, and vulnerability to climate change. The ability to estimate aboveground biomass (AGB) in wetlands at ecologically relevant scales is complicated by the spatial variability inherent to patterns in wetland vegetation and the biogeomorphic processes that help create them. Remote sensing provides an approach for mapping wetland biomass, but the spatial resolutions of satellite and airborne imagery often constrain the types of ecological patterns and processes that can be detected. Unmanned Aerial Vehicles (UAVs) have previously been used to capture fine-scale (≤1 m) variability in AGB in coastal wetland settings. However, it remains unclear if a UAV approach to estimating wetland biomass is transferrable across diverse wetland sites or how it compares to commonly used satellite-based approaches. Here, we test the capabilities of UAVs in remotely quantifying AGB and compare biomass estimation using UAV and Landsat satellite imagery (30 m resolution) in several wetland sites in Southern California. Field surveys highlight significant spatial variability in wetland plant community AGB and height that influence remote biomass estimation. Relationships between UAV vegetation indices and AGB were site-specific and influenced by vegetation types. Biomass estimation using UAVs (r 2 = 0.40, RMSE = 534.6 g m −2 ) showed better correlation with NDVI than a Landsatbased approach (r 2 = 0.26, RMSE = 596.8 g m −2 ). We found combining highresolution UAV AGB maps and Landsat NDVI to develop AGB models showed the highest correlation (r 2 = 0.45, RMSE = 659.7 g m −2 ) and provided additional spatial information to aid scaling field data to satellite imagery. Overall, UAVs captured more spatial complexity in aboveground biomass at finer scales than is possible with moderate-resolution Landsat pixels, indicating that UAVs can be used to characterize patterns of within-marsh variability resulting from local-scale (≤ 100s of meters) ecological processes.

show abstract

Integration of UAV, Sentinel-1, and Sentinel-2 Data for Mangrove Plantation Aboveground Biomass Monitoring in Senegal

Cited by 127 publications

References 88 publications

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

A performance‐aware routing mechanism for flying ad hoc networks

Characterizing spatial variability in coastal wetland biomass across multiple scales using UAV and satellite imagery

Contact Info

Product

Resources

About