Evaluation of LAI Estimation of Mangrove Communities Using DLR and ELR Algorithms With UAV, Hyperspectral, and SAR Images

Abstract

The high-precision estimation of mangrove leaf area index (LAI) using a deep learning regression algorithm (DLR) always requires a large amount of training sample data. However, it is difficult for LAI field measurements to collect a sufficient amount of sample data in mangrove wetlands. To tackle this challenge, this paper proposed an approach for expanding training samples and quantitatively evaluated the performance of estimating LAI for mangrove communities using Deep Neural Networks (DNN) and Transformer algorithms. This study also explored the effects of unmanned aerial vehicle (UAV) and Sentinel-2A multispectral, orbital hyper spectral (OHS), and GF-3 SAR images on LAI estimation of different mangrove communities. Finally, this paper evaluated the LAI estimation ability of mangrove communities using ensemble learning regression (ELR) and DLR algorithms. The results showed that: (1) the UAV images achieved the better LAI estimation of different mangrove communities (R2 = 0.5974–0.6186), and GF-3 SAR images were better for LAI estimation of Avicennia marina with high coverage (R2 = 0.567). The optimal spectral range for estimating LAI for mangroves in the optical images was between 650–680 nm. (2) The ELR model outperformed single base model, and produced the high-accuracy LAI estimation (R2 = 0.5266–0.713) for different mangrove communities. (3) The average accuracy (R2) of the ELR model was higher by 0.0019–0.149 than the DLR models, which demonstrated that the ELR model had a better capability (R2 = 0.5865–0.6416) in LAI estimation. The Transformer-based LAI estimation of A. marina (R2 = 0.6355) was better than the DNN model, while the DNN model produced higher accuracy for Kandelia candel (KC) (R2 = 0.5577). (4) With the increase in the expansion ratio of the training sample (10–50%), the LAI estimation accuracy (R2) of DNN and Transformer models for different mangrove communities increased by 0.1166–0.2037 and 0.1037–0.1644, respectively. Under the same estimation accuracy, the sample enhancement method in this paper could reduce the number of filed measurements by 20–40%.

Estimation of Species-Scale Canopy Chlorophyll Content in Mangroves from UAV and GF-6 Data

“…RF, GBRT, and XGBoost algorithms are robust in quantitative inversion and are widely used in the estimation of mangrove parameters [15,47,55,56]. In this paper, the feature variables (reflectance bands or combined vegetation indices sensitive to CCC obtained after correlation analysis and feature variable selection) are used as input parame- The reflectance information of GF-6 satellite data is sensitive to vegetation parameters, such as LAI and LCC, and is suitable for estimating parameters related to vegetation growth to monitor vegetation health, so this paper will use GF-6 satellite data to estimate mangrove canopy chlorophyll content information [51][52][53][54].…”

“…RF, GBRT, and XGBoost algorithms are robust in quantitative inversion and are widely used in the estimation of mangrove parameters [15,47,55,56]. In this paper, the feature variables (reflectance bands or combined vegetation indices sensitive to CCC obtained after correlation analysis and feature variable selection) are used as input parameters for the machine learning regression algorithm, with CCC as the target variable.…”

Synergistic multi-altimeter for estimating water level in the coastal zone of Beibu Gulf using SEL, ALES + and BFAST algorithms

“…The Stacking ensemble learning (SEL) algorithm can integrate the advantages of each base model and weaken the effects of overfitting, improving the classification accuracy. It has been confirmed that the SEL algorithm has been successfully applied to crop classification (Sonobe et al, 2018), multi-type flooding delineating (Rahman et al, 2021), mangrove species classification (Fu et al, 2022a), LAI estimation of mangrove communities (Fu et al, 2022b), and other fields. However, the application of the SEL algorithm to waveform classification of altimeters lacks systematic justification.…”

Combining spectral and texture feature of UAV image with plant height to improve LAI estimation of winter wheat at jointing stage

“…One is a radiative transfer physical model, and the other is a statistical empirical model. The physical model is based on the reflection and absorption between light and crops, which has a certain mechanism and strong versatility ( Fu et al., 2022a ). However, the model involves complex formulas and requires many parameters, which makes it difficult to find the optimal solution ( Du et al., 2016 ).…”