Remote Estimation of Mangrove Aboveground Carbon Stock at the Species Level Using a Low-Cost Unmanned Aerial Vehicle System

Abstract

There is ongoing interest in developing remote sensing technology to map and monitor the spatial distribution and carbon stock of mangrove forests. Previous research has demonstrated that the relationship between remote sensing derived parameters and aboveground carbon (AGC) stock varies for different species types. However, the coarse spatial resolution of satellite images has restricted the estimated AGC accuracy, especially at the individual species level. Recently, the availability of unmanned aerial vehicles (UAVs) has provided an operationally efficient approach to map the distribution of species and accurately estimate AGC stock at a fine scale in mangrove areas. In this study, we estimated mangrove AGC in the core area of northern Shenzhen Bay, South China, using four kinds of variables, including species type, canopy height metrics, vegetation indices, and texture features, derived from a low-cost UAV system. Three machine-learning algorithm models, including Random Forest (RF), Support Vector Regression (SVR), and Artificial Neural Network (ANN), were compared in this study, where a 10-fold cross-validation was used to evaluate each model’s effectiveness. The results showed that a model that used all four type of variables, which were based on the RF algorithm, provided better AGC estimates (R2 = 0.81, relative RMSE (rRMSE) = 0.20, relative MAE (rMAE) = 0.14). The average predicted AGC from this model was 93.0 ± 24.3 Mg C ha−1, and the total estimated AGC was 7903.2 Mg for the mangrove forests. The species-based model had better performance than the considered canopy-height-based model for AGC estimation, and mangrove species was the most important variable among all the considered input variables; the mean height (Hmean) the second most important variable. Additionally, the RF algorithms showed better performance in terms of mangrove AGC estimation than the SVR and ANN algorithms. Overall, a low-cost UAV system with a digital camera has the potential to enable satisfactory predictions of AGC in areas of homogenous mangrove forests.

Reviews and syntheses: Enhancing research and monitoring of land-to-atmosphere greenhouse gases exchange in developing countries

“…Since they regularly monitor CO2 column-averaged dry-air mole fraction (XCO2) and are also open for public use, they can be another great resource for developing countries to study GHG magnitudes and dynamics in absence of precise high quality concentration measurements from tall towers. In addition, low-cost unmanned aerial vehicles equipped with digital cameras provide image data for estimating above ground biomass in forest (Li et al, 2019;Jayathunga et al, 2018;Mlambo et al, 2017).…”

MODEL PENDUGAAN DIAMETER POHON BERBASIS CITRA UNMANNED AERIAL VEHICLE (UAV) PADA HUTAN HUJAN TROPIS PAPUA: STUDI DI PULAU MANSINAM PAPUA BARAT (Model of Tree Diameter Estimation Based on Unmanned Aerial Vehicle (UAV) Image in Papua Tropical Rain Forest: a Study in Mansinam Island Papua Barat)

“…Penggunaan metode structure from motion (SFM) untuk membantu dalam proses pengambilan data telah banyak dilakukan. Iizuka et al (2018) menggunakan UAV dan SFM untuk menduga diameter setinggi dada dan tinggi pohon, Li et al (2019) dan Navarro et al (2020) menggunakan UAV dan SFM untuk melakukan pendugaan biomasa diatas permukaan tanah pada hutan mangrove, Panagiotidis et al (2017) dan Krause et al (2019) melakukan studi tentang ekstraksi informasi tajuk pohon dan tinggi pohon menggunakan UAV. Berdasarkan beberapa studi yang menggunakan metode UAV dan SFM telah mendapatkan kesimpulan bahwa penggunaan SFM memiliki potensi yang baik untuk mengetahui informasi terkait biofisik hutan (Iglhaut et al, 2019).…”

Remote mapping of foodscapes using sUAS and a low cost BG-NIR sensor

“…Machine learning algorithms are effective at operating on large volume and multivariate datasets. They can have high accuracy, and they have been successfully used when regression models are not suitable (Li et al, 2019;Marrs and Ni-Meister, 2019;Van Ewijk et al, 2014). In particular, the Breiman's Random Forests Model (RFM, Breiman, 2001) has been shown to be effective in other species distribution studies (see Carvalho et al, 2018;Zhang et al, 2019).…”