Comparison of Capability of SAR and Optical Data in Mapping Forest above Ground Biomass Based on Machine Learning

Tavasoli, N.; Arefi, Hossein

doi:10.3390/iecg2020-07916

Cited by 5 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA analysis was used in this study to identify the main components and to help analyze a subset of features by a dimensionality reduction. PCA is widely used to eliminate waste data in remote sensing studies [88]. In this study, PCA was computed from the bands of the Sentinel-2 image, and it was used for AGB modeling by the means of Statistica (version 10) software.…”

Section: Statistical Analysis and Modeling Performancementioning

confidence: 99%

Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

Moradi

Darvishsefat

Pourrahmati

et al. 2022

Forests

View full text Add to dashboard Cite

Due to the challenges brought by field measurements to estimate the aboveground biomass (AGB), such as the remote locations and difficulties in walking in these areas, more accurate and cost-effective methods are required, by the use of remote sensing. In this study, Sentinel-2 data were used for estimating the AGB in pure stands of Carpinus betulus (L., common hornbeam) located in the Hyrcanian forests, northern Iran. For this purpose, the diameter at breast height (DBH) of all trees thicker than 7.5 cm was measured in 55 square plots (45 × 45 m). In situ AGB was estimated using a local volume table and the specific density of wood. To estimate the AGB from remotely sensed data, parametric and nonparametric methods, including Multiple Regression (MR), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), and Random Forest (RF), were applied to a single image of the Sentinel-2, having as a reference the estimations produced by in situ measurements and their corresponding spectral values of the original spectral (B2, B3, B4, B5, B6, B7, B8, B8a, B11, and B12) and derived synthetic (IPVI, IRECI, GEMI, GNDVI, NDVI, DVI, PSSRA, and RVI) bands. Band 6 located in the red-edge region (0.740 nm) showed the highest correlation with AGB (r = −0.723). A comparison of the machine learning methods indicated that the ANN algorithm returned the best ABG-estimating performance (%RMSE = 19.9). This study demonstrates that simple vegetation indices extracted from Sentinel-2 multispectral imagery can provide good results in the AGB estimation of C. betulus trees of the Hyrcanian forests. The approach used in this study may be extended to similar areas located in temperate forests.

show abstract

Section: Statistical Analysis and Modeling Performancementioning

confidence: 99%

Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

Moradi

Darvishsefat

Pourrahmati

et al. 2022

Forests

View full text Add to dashboard Cite

show abstract

“…Moreover, the orthorectified image of each polarization, γ 0 VH, and γ 0 VV, was used as the input image for generating texture features, to avoid any potential loss of texture information from speckle reduction [61]. Texture expresses the spatial distribution of grayscale characteristics in the image and plays a vital role in pattern recognition [62]. Image textures were calculated using the Grey Level Co-occurrence Matrix (GLCM) tool in SNAP, with an eleven by eleven moving window.…”

Section: Sentinel-1 Processing and Feature Extractionmentioning

confidence: 99%

Total Stem Biomass Estimation Using Sentinel-1 and -2 Data in a Dense Coniferous Forest of Complex Structure and Terrain

Georgopoulos

Sotiropoulos

Stefanidou

et al. 2022

Forests

View full text Add to dashboard Cite

Accurate above-ground biomass (AGB) estimation across multiple spatial and temporal scales is essential for mitigating climate change and optimizing forest management strategies. The aim of the present study was to investigate the potential of Sentinel optical and Synthetic Aperture Radar (SAR) data in reliably estimating the plot-level total stem biomass (TSB), which constitutes the dominant material among the different tree components of AGB (stem, branches, and leaves). The study area was located in a dense coniferous forest characterized by an uneven-aged structure and intense topography. A random forest (RF) regression analysis was performed to develop TSB predictive models using Sentinel-1 and -2 images in an individual and combined manner. Consequently, three RF models were produced and evaluated for their predictive performance through the k-fold cross-validation (CV) method. The results showcased that the individual use of Sentinel-1 contributed to the production of the most accurate plot-level TSB estimates (i.e., coefficient of determination-R2 = 0.74, relative mean square error (RMSE) = 1.76 Mg/1000 m2, mean absolute error (MAE) = 1.48 Mg/1000 m2), compared to the use of Sentinel-2 data individually and the Sentinel-1 and -2 combination. In fact, the synergistic use of optical and SAR data led to the generation of an RF model that only marginally underperformed the SAR model (R2 = 0.73 and R2 = 0.72, respectively).

show abstract

“…Destek Vektör Makinesi (DVM), karar ağaçları, K-en yakın komşu ve yapay sinir ağları (YSA) gibi makine öğrenme yöntemleri de TÜB kestiriminde başvurulan algoritmalardan olmaktadır (Nelson vd., 2009;Monnet vd., 2011). Son zamanlarda, Aşırı Gradyan Artırma (AGA) ve Rastgele Orman (RO) gibi makine öğrenme yöntemlerinin kullanıldığı TÜB kestirimi çalışmalarında da önemli sonuçlar elde edildiği görülmektedir (Pham vd., 2020;Tavasoli & Arefi, 2021).…”

Section: Introductionunclassified

Bartın’daki Sahil Çamı (Pinus pinaster Ait.) Ağaçlandırma Alanlarında Sentinel-1 ve Sentinel-2 Uydu Görüntüleri Kullanılarak Toprak Üstü Biyokütlenin Kestirilmesi

ÖZDEMİR,

DEMİRALAY,

ŞAHİN

2023

Turk J Remote Sens GIS

View full text Add to dashboard Cite

Ormanlar, yaklaşık olarak yeryüzünün üçte birini kaplayan, gezegendeki biyoçeşitliliğin yarısından fazlasına ev sahipliği yapan, atmosfere salınan karbonun önemli bir miktarını tutan, iklim değişimi konusunda da güçlü bir etkiye sahip dünya ekosistemindeki çok önemli bir bileşendir. Ormanlık alanların biyokütlesinin doğru bir şekilde kestirilmesi, karbon salınımlarının azaltılması ve karbon yutak alanlarının artırılması kapsamında büyük önem taşımaktadır. Uydu teknolojilerinin ve uzaktan algılama sistemlerinin gelişmesiyle birlikte aktif ve pasif sistemler ile Toprak Üstü Biyokütlenin (TÜB) kestiriminin yapılması mümkün hale gelmiştir. Bu çalışmada, Bartın’daki sahil çamı (Pinus pinaster Ait.) ağaçlandırmalarında, Avrupa Uzay Ajansı (ESA) tarafından araştırmacılara ücretsiz sunulan Sentinel-1 radar, Sentinel-2 optik uydu verileri ile Çoklu Doğrusal Regresyon (ÇDR) ve Rastgele Orman (RO) yöntemlerinden yararlanılarak bant ve bitki örtüsü indeksi değerlerinin TÜB kestirimine etkileri ve yersel örnekleme alan verilerinden elde edilen TÜB değerleri ile ilişkileri araştırılmaktadır. 16 modelin geliştirildiği çalışmada, Sentinel-1 VH geri saçılım değeri, Sentinel-2’den türetilmiş normalize edilmiş fark bitki örtüsü indeksi değeri (NDVI) füzyonu ve RO yöntemi kullanıldığı model ile TÜB kestiriminde en iyi sonuç elde edilmiştir (R2=0.61, RMSE= 49.412 t/ha).

show abstract

Comparison of Capability of SAR and Optical Data in Mapping Forest above Ground Biomass Based on Machine Learning

Cited by 5 publications

References 50 publications

Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

Total Stem Biomass Estimation Using Sentinel-1 and -2 Data in a Dense Coniferous Forest of Complex Structure and Terrain

Bartın’daki Sahil Çamı (Pinus pinaster Ait.) Ağaçlandırma Alanlarında Sentinel-1 ve Sentinel-2 Uydu Görüntüleri Kullanılarak Toprak Üstü Biyokütlenin Kestirilmesi

Contact Info

Product

Resources

About