A novel approach for estimation of aboveground biomass of a carbon-rich mangrove site in India

Regional mangrove vegetation carbon stocks predicted integrating UAV-LiDAR and satellite data

Using satellite RS data predicting mangrove vegetation carbon stock (MVC) is the popular and efficient approach at a large scale to protect mangroves and promote carbon trading. Satellite data have performed poorly in predicting MVC due to saturation issues. UAV-LiDAR data overcomes these limitations by providing detailed structural vegetation information. However, how to cross-scale integration of UAV-LiDAR and satellite RS data and the selection of features and machine learning methods hampered the practitioner in making a lightweight but efficient model to predict the MVC. Our study integrated UAV-LiDAR, Sentinel-1, and Sentinel-2 to extract spectral, structural, and textural features at the regional scale. We estimated the influences of different combinations between three vegetation features and machine learning methods (Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Regression Tree (GBDT), and Extreme Gradient Regression Tree (XGBOOST)) on the results of MVC prediction, and constructed a framework for estimating mangrove vegetation aboveground (ACG) and belowground (BCG) carbon storage in Zhanjiang, the largest mangrove area of China. Our research shows: 1) Compared to using satellite remote sensing (RS), integrating UAV and satellite RS data and fusing multiple vegetation features significantly improved the accuracy of mangrove vegetation carbon stock (MVC) predictions. 2) Structural features, particularly canopy height retrieved from UAV and satellite RS, are essential indicators for predicting MVC. Combined with spectral and structural features, regional MVC was precisely predicted. 3)Although the influence of different machine learning methods on MVC prediction was not significant, XGBOOST demonstrated relatively high precision. We recommend that mangrove practitioners integrate UAV and satellite RS data to predict MVC at a regional scale. Importantly, governments should prioritize the application of UAV-LiDAR in forestry monitoring and establish a long-term mangrove monitoring database to aid in estimating blue carbon resources and promoting blue carbon trading.

Remote sensing-based mangrove blue carbon assessment in the Asia-Pacific: A systematic review

Accurate measuring, mapping, and monitoring of mangrove forests support the sustainable management of mangrove blue carbon in the Asia-Pacific. Remote sensing coupled with modeling can efficiently and accurately estimate mangrove blue carbon stocks at larger spatiotemporal extents. This study aimed to identify trends in remote sensing/modeling employed in estimating mangrove blue carbon, attributes/variations in mangrove carbon sequestration estimated using remote sensing, and to compile research gaps and opportunities, followed by providing recommendations for future research. Using a systematic literature review approach, we reviewed 105 remote sensing-based peer-reviewed articles (1990 - June 2023). Despite their high mangrove extent, there was a paucity of studies from Myanmar, Bangladesh, and Papua New Guinea. The most frequently used sensor was Sentinel-2 MSI, accounting for 14.5 % of overall usage, followed by Landsat 8 OLI (11.5 %), ALOS-2 PALSAR-2 (7.3 %), ALOS PALSAR (7.2 %), Landsat 7 ETM+ (6.1 %), Sentinel-1 (6.7 %), Landsat 5 TM (5.5 %), SRTM DEM (5.5 %), and UAV-LiDAR (4.8 %). Although parametric methods like linear regression remain the most widely used, machine learning regression models such as Random Forest (RF) and eXtreme Gradient Boost (XGB) have become popular in recent years and have shown good accuracy. Among a variety of attributes estimated, below-ground mangrove blue carbon and the valuation of carbon stock were less studied. The variation in carbon sequestration potential as a result of location, species, and forest type was widely studied. To improve the accuracy of blue carbon measurements, standardized/coordinated and innovative methodologies accompanied by credible information and actionable data should be carried out. Technical monitoring (every 2-5 years) enhanced by remote sensing can provide accurate and precise data for sustainable mangrove management while opening ventures for voluntary carbon markets to benefit the environment and local livelihood in developing countries in the Asia-Pacific region.

Above ground tree biomass modeling using machine learning algorithms in western Terai Sal Forest of Nepal

The monitoring of forest biomass is a crucial biophysical parameter in forest ecosystems, as it provides valuable information for managing forests sustainably and tracking carbon circulation statistics. To achieve sustainable forest management, it is essential to monitor and study forest resources, particularly biomass. This study aimed to model above ground tree biomass (AGTB) using Machine Learning Algorithms (MLAs) in the western terai Sal forest of Nepal. AGTB was calculated using a systematic inventory sample plot, while spectral and textural variables were processed and masked for the study area using Sentinel-2A satellite imagery. Three MLAs namely support vector machine (SVM), random forest (RF), and stochastic gradient boosting (SGB), were employed for modeling with eight categorized variable datasets. Among the MLAs, the RF algorithm with a combination of gray-level co-occurrence matrix (GLCM) and raw bands (RB) dataset variable demonstrated the best performance, with a low RMSE value of 78.81 t ha-1 in the test data. However, the AGTB range from this model ranged from 118.34 to 425.97 t ha-1. The study found that traditional indices, raw bands, and GLCM texture from near-infrared were important variables for AGTB. Nevertheless, the RF algorithm and the dataset combination of GLCM plus raw bands (RB) exhibited excellent performance in all model runs. Thus, this pioneering study on comparative MLAs-based AGTB assessment with multiple datasets variables can provide valuable insights for new researchers and the development of novel approaches for biomass/carbon estimation techniques in Nepal.

A novel coupled framework for detecting hotspots of methane emission from the vulnerable Indian Sundarban mangrove ecosystem using data-driven models

Coastal mangroves have been lost to deforestation for anthropogenic activities such as agriculture over the past two decades. The genesis of methane (CH₄), a significant greenhouse gas (GHG) with a high potential for global warming, occurs through these mangrove beds. The mangrove forests in the Indian Sundarban deltaic region were studied for pre-monsoonal and post-monsoonal variations of CH₄ emission. Considering the importance of CH₄ emission, a process-based spatiotemporal (PBS) and an analytical neural network (ANN) model were proposed and used to estimate the amount of CH₄ emission from different land use land cover classes (LULC) of mangroves. The field work was performed in 2020, and gas samples of various LULC were directly collected from the mangrove bed using the enclosed box chamber method. Historical climatic data (1960-1989) were used to predict future climate scenarios and associated CH₄ emissions. The analysis and estimation activities were carried out utilizing satellite images from the pre-monsoonal and post-monsoonal seasons of the same year. The study revealed that pre-monsoonal CH₄ emission was higher in the south-west and northern parts of the deforested mangrove of the Indian Sundarban. A sensitivity study of the anticipated models was conducted using a variety of environmental input parameters and related main field observations. The measured precision area under curve of receiver operating characteristics was 0.753 for PBS and 0.718 for ANN models, respectively. The temperature factor (T_f) was the most crucial variable for CH₄ emissions. Based on the PBS model with coupled model intercomparison project-6 temperature data, a global circulation model was run to predict increasing CH₄ emissions up to 2100. The model revealed that the agricultural lands were the prime emitters of CH₄ in the Sundarban mangrove ecosystem.