Model-based estimation of large area forest canopy height and biomass using radar and optical remote sensing with limited lidar data

Urban forests provide ecosystem services; tree canopy cover is the basic quantification of ecosystem services. Ground assessment of the urban forest is limited; with continued refinement, remote sensing can become an essential tool for analyzing the urban forest. This study addresses three research questions that are essential for urban forest management using remote sensing: (1) Can object-based image analysis (OBIA) and non-image classification methods (such as random point-based evaluation) accurately determine urban canopy coverage using high-spatial-resolution aerial images? (2) Is it possible to assess the impact of natural disturbances in addition to other factors (such as urban development) on urban canopy changes in the classification map created by OBIA? (3) How can we use Light Detection and Ranging (LiDAR) data and technology to extract urban canopy metrics accurately and effectively? The urban forest canopy area and location within the City of St Peter, Minnesota (MN) boundary between 1938 and 2019 were defined using both OBIA and random-point-based methods with high-spatial-resolution aerial images. Impacts of natural disasters, such as the 1998 tornado and tree diseases, on the urban canopy cover area, were examined. Finally, LiDAR data was used to determine the height, density, crown area, diameter, and volume of the urban forest canopy. Both OBIA and random-point methods gave accurate results of canopy coverages. The OBIA is relatively more time-consuming and requires specialist knowledge, whereas the random-point-based method only shows the total coverage of the classes without locational information. Canopy change caused by tornado was discernible in the canopy OBIA-based classification maps while the change due to diseases was undetectable. To accurately exact urban canopy metrics besides tree locations, dense LiDAR point cloud data collected at the leaf-on season as well as algorithms or software developed specifically for urban forest analysis using LiDAR data are needed.

Download Full-text

Canopy Height Estimation Using Sentinel Series Images through Machine Learning Models in a Mangrove Forest

Remote Sensing ◽

10.3390/rs12091519 ◽

2020 ◽

Vol 12 (9) ◽

pp. 1519 ◽

Cited By ~ 3

Author(s):

Sujit Madhab Ghosh ◽

Mukunda Dev Behera ◽

Somnath Paramanik

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Forest Canopy ◽

Canopy Height ◽

Series Data ◽

Learning Models ◽

Biophysical Parameters ◽

Height Estimation ◽

Area Index ◽

Machine Learning Models

Canopy height serves as a good indicator of forest carbon content. Remote sensing-based direct estimations of canopy height are usually based on Light Detection and Ranging (LiDAR) or Synthetic Aperture Radar (SAR) interferometric data. LiDAR data is scarcely available for the Indian tropics, while Interferometric SAR data from commercial satellites are costly. High temporal decorrelation makes freely available Sentinel-1 interferometric data mostly unsuitable for tropical forests. Alternatively, other remote sensing and biophysical parameters have shown good correlation with forest canopy height. The study objective was to establish and validate a methodology by which forest canopy height can be estimated from SAR and optical remote sensing data using machine learning models i.e., Random Forest (RF) and Symbolic Regression (SR). Here, we analysed the potential of Sentinel-1 interferometric coherence and Sentinel-2 biophysical parameters to propose a new method for estimating canopy height in the study site of the Bhitarkanika wildlife sanctuary, which has mangrove forests. The results showed that interferometric coherence, and biophysical variables (Leaf Area Index (LAI) and Fraction of Vegetation Cover (FVC)) have reasonable correlation with canopy height. The RF model showed a Root Mean Squared Error (RMSE) of 1.57 m and R2 value of 0.60 between observed and predicted canopy heights; whereas, the SR model through genetic programming demonstrated better RMSE and R2 values of 1.48 and 0.62 m, respectively. The SR also established an interpretable model, which is not possible via any other machine learning algorithms. The FVC was found to be an essential variable for predicting forest canopy height. The canopy height maps correlated with ICESat-2 estimated canopy height, albeit modestly. The study demonstrated the effectiveness of Sentinel series data and the machine learning models in predicting canopy height. Therefore, in the absence of commercial and rare data sources, the methodology demonstrated here offers a plausible alternative for forest canopy height estimation.

Download Full-text