Learning from multimodal and multisensor earth observation dataset for improving estimates of mangrove soil organic carbon in Vietnam

• Published in: International Journal of Remote Sensing Vol. 42; no. 18; pp. 6866 - 6890
• Main Authors: Le, Nga Nhu, Pham, Tien Dat, Yokoya, Naoto, Ha, Nam Thang, Nguyen, Thi Thu Trang, Tran, Thi Dang Thuy, Pham, Tien Duc
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis 17.09.2021; Informa UK Limited; Taylor & Francis Ltd
• Subjects: Algorithms; Artificial intelligence; Blue carbon; Carbon; Carbon cycle; carbon markets; Carbon offsets; computer software; Conservation; Cost analysis; data collection; Datasets; Emissions control; Estimates; global carbon budget; Greenhouse gases; Machine learning; Mangrove conservation; mangrove soils; Mangroves; Modelling; Organic carbon; Particle swarm optimization; Regression; regression analysis; Remote sensing; river deltas; Root-mean-square errors; sample size; SAR (radar); Soil; soil organic carbon; Soils; Source code; Support vector machines; Surveying; surveys; Swarm intelligence; Synthetic aperture radar; Vietnam; Water depth; Vietnam
• ISSN: 0143-1161; 1366-5901; 1366-5901
• DOI: 10.1080/01431161.2021.1945158

Quantifying mangrove soil organic carbon (SOC) is key to better understanding the global carbon cycle, a critical phenomenon in reducing greenhouse gas emissions. However, it is challenging to have a large sample size in soil carbon measurements and analysis due to the high costs associated with them. In the current research, we propose a novel hybridized artificial intelligence model based on the categorical boosting regression (CBR) and the particle swarm optimization (PSO) algorithm for feature selection, namely, the CBR-PSO model for estimating mangrove SOC. We integrated multisensor optical (Sentinel-2) and synthetic aperture radar (Sentinel-1 and ALOS-2 PALSAR-2) remote sensing data to construct and verify the proposed model, drawing upon a survey in 85 soil cores at 100 cm depth in the Red River Delta, Vietnam. The CBR-PSO model estimated the mangrove SOC ranging from 44.74 to 91.92 Mg ha −1 (average = 68.76 Mg ha −1 ) with satisfactory accuracy (coefficient of determination (R 2 ) = 0.809 and root-mean-square error (RMSE) = 9.30 Mg ha −1 ). We also compared the proposed model's capability with four machine learning techniques, i.e. support vector regression (SVR), random forest regression (RFR), extreme gradient boosting regression (XGBR), and XGBR-PSO models. We show that multimodal and multisensor earth observation dataset combined with the CBR-PSO model can significantly improve the estimates of mangrove SOC. Our findings contribute novel and advanced machine learning approaches for robustness of SOC estimation using open-source software. Our novel framework, which is automated, fast, and reliable, developed in this study can be easily applicable to other mangrove ecosystems across the world, thus providing insights for a voluntary blue carbon offset marketplace for sustainable mangrove conservation.