Multiscale geostatistical analysis of sampled above-ground biomass and vegetation index products from HJ-1A/B, Landsat, and MODIS

2014 ◽  
Author(s):  
Junbang Wang ◽  
Wenyi Sun
Keyword(s):  
Vegetation Index ◽  
Geostatistical Analysis ◽  
Above Ground Biomass ◽  
Ground Biomass

scholarly journals Estimating Above-Ground Biomass of Potato Using Random Forest and Optimized Hyperspectral Indices

2021 ◽  
Vol 13 (12) ◽  
pp. 2339
Author(s):  
Haibo Yang ◽  
Fei Li ◽  
Wei Wang ◽  
Kang Yu
Keyword(s):  
Random Forest ◽  
Vegetation Index ◽  
Tuber Formation ◽  
Growth Stages ◽  
Spectral Indices ◽  
Above Ground Biomass ◽  
Full Spectrum ◽  
Ground Biomass ◽  
Tuber Bulking ◽  
Input Variables

Spectral indices rarely show consistency in estimating crop traits across growth stages; thus, it is critical to simultaneously evaluate a group of spectral variables and select the most informative spectral indices for retrieving crop traits. The objective of this study was to explore the optimal spectral predictors for above-ground biomass (AGB) by applying Random Forest (RF) on three types of spectral predictors: the full spectrum, published spectral indices (Pub-SIs), and optimized spectral indices (Opt-SIs). Canopy hyperspectral reflectance of potato plants, treated with seven nitrogen (N) rates, was obtained during the tuber formation and tuber bulking from 2015 to 2016. Twelve Pub-SIs were selected, and their spectral bands were optimized using band optimization algorithms. Results showed that the Opt-SIs were the best input variables of RF models. Compared to the best empirical model based on Opt-SIs, the Opt-SIs based RF model improved the prediction of AGB, with R2 increased by 6%, 10%, and 16% at the tuber formation, tuber bulking, and for across the two growth stages, respectively. The Opt-SIs can significantly reduce the number of input variables. The optimized Blue nitrogen index (Opt-BNI) and Modified red-edge normalized difference vegetation index (Opt-mND705) combined with an RF model showed the best performance in estimating potato AGB at the tuber formation stage (R2 = 0.88). In the tuber bulking stage, only using optimized Nitrogen planar domain index (Opt-NPDI) as the input variable of the RF model produced satisfactory accuracy in training and testing datasets, with the R2, RMSE, and RE being 0.92, 208.6 kg/ha, and 10.3%, respectively. The Opt-BNI and Double-peak nitrogen index (Opt-NDDA) coupling with an RF model explained 86% of the variations in potato AGB, with the lowest RMSE (262.9 kg/ha) and RE (14.8%) across two growth stages. This study shows that combining the Opt-SIs and RF can greatly enhance the prediction accuracy for crop AGB while significantly reduces collinearity and redundancies of spectral data.

Improvement in Estimation of Aboveground Biomass of Albizia lebbeck using Fraction Reflectance of Landsat TM Data

2015 ◽  
Vol 1 (01) ◽  
pp. 99-105
Author(s):  
O. P. Tripathi ◽  
J. Deka ◽  
J. Y. Yumnam ◽  
P. Mahanta
Keyword(s):  
Satellite Data ◽  
Vegetation Index ◽  
Linear Regression Analysis ◽  
Landsat Tm ◽  
Surface Reflectance ◽  
Above Ground Biomass ◽  
Mixed Pixel ◽  
Ground Biomass ◽  
Medium Resolution ◽  
Reflectance Data

The study emphasizes on the ability of spectral mixture analysis (SMA) to improve the estimate of above ground biomass from spectral reflectance of satellite data. Digital number (DN) values of satellite data were converted to surface reflectance and fraction reflectance data. Linear regression analysis was performed between above ground biomass data with both total surface reflectance and SMA produced fraction reflectance values separately. The analysis revealed that the best positive correlation was observed between AGB and the fraction reflectance values of FR_TM 5/3 with R2 = 0.865 whereas with the total reflectance data, atmospherically resistant vegetation index (ARVI) and TM5/3 resulted moderate correlation R2= 0.452 and - 0.248, respectively. Pixel level AGB ranges between 0.001t to 13.53t. The total AGB of the study area (275.85 ha) was estimated to be 14249t. Thus separation of endmembers from the mixed pixel from a course to medium resolution satellite data can play an important role in improving AGB estimation performance, especially for those sites with multiple cover features. The study demonstrates the potentiality of Landsat TM data in concatenate with SMA in improving the estimation of AGB which can be further improved by identifying all possible endmembers and highly configured methodology.

scholarly journals Novel Feature-Extraction Methods for the Estimation of Above-Ground Biomass in Rice Crops

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4369
Author(s):  
David Alejandro Jimenez-Sierra ◽  
Edgar Steven Correa ◽  
Hernán Darío Benítez-Restrepo ◽  
Francisco Carlos Calderon ◽  
Ivan Fernando Mondragon ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Vegetation Index ◽  
Ground Truth ◽  
Gaussian Mixture ◽  
Extraction Methods ◽  
Temporal Variations ◽  
Biomass Estimation ◽  
Growth Stages ◽  
Above Ground Biomass ◽  
Ground Biomass

Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and compared against an assembled ground-truth biomass measurements taken by destructive sampling. The proposed GBF-Sm-Bs approach outperformed competing methods by obtaining biomass estimation correlation of 0.995 with R2=0.991 and RMSE=45.358 g. This result increases the precision in the biomass estimation by around 62.43% compared to previous works.

ESTIMATION OF ABOVE GROUND BIOMASS OF THE THREE SITES (GRAZED SITE, PROTECTED SITE AND SEED SOWN SITE) FOR COMPARING THEIR PRODUCTIVITY IN KASHMIR VALLEY

2017 ◽  
Vol 23 (2) ◽  
Author(s):  
AFSHAN ANJUM BABA ◽  
SYED NASEEM UL-ZAFAR GEELANI ◽  
ISHRAT SALEEM ◽  
MOHIT HUSAIN ◽  
PERVEZ AHMAD KHAN ◽  
...  
Keyword(s):  
Protected Areas ◽  
Aboveground Biomass ◽  
Plant Biomass ◽  
Summer Season ◽  
Above Ground Biomass ◽  
Spring Season ◽  
Kashmir Valley ◽  
Ground Biomass ◽  
Maximum Value ◽  
Protected Site

The plant biomass for protected areas was maximum in summer (1221.56 g/m2) and minimum in winter (290.62 g/m2) as against grazed areas having maximum value 590.81 g/m2 in autumn and minimum 183.75 g/m2 in winter. Study revealed that at Protected site (Kanidajan) the above ground biomass ranged was from a minimum (1.11 t ha-1) in the spring season to a maximum (4.58 t ha-1) in the summer season while at Grazed site (Yousmarag), the aboveground biomass varied from a minimum (0.54 t ha-1) in the spring season to a maximum of 1.48 t ha-1 in summer seasonandat Seed sown site (Badipora), the lowest value of aboveground biomass obtained was 4.46 t ha-1 in spring while as the highest (7.98 t ha-1) was obtained in summer.

scholarly journals The climatic imprint of bimodal distributions in vegetation cover for western Africa

2016 ◽  
Vol 13 (11) ◽  
pp. 3343-3357 ◽  
Author(s):  
Zun Yin ◽  
Stefan C. Dekker ◽  
Bart J. J. M. van den Hurk ◽  
Henk A. Dijkstra
Keyword(s):  
Land Cover ◽  
Congo Basin ◽  
Shortwave Radiation ◽  
Mean Annual Precipitation ◽  
Above Ground Biomass ◽  
Precipitation Regime ◽  
Ground Biomass ◽  
Western Africa ◽  
Precipitation Regimes ◽  
Woody Cover

Abstract. Observed bimodal distributions of woody cover in western Africa provide evidence that alternative ecosystem states may exist under the same precipitation regimes. In this study, we show that bimodality can also be observed in mean annual shortwave radiation and above-ground biomass, which might closely relate to woody cover due to vegetation–climate interactions. Thus we expect that use of radiation and above-ground biomass enables us to distinguish the two modes of woody cover. However, through conditional histogram analysis, we find that the bimodality of woody cover still can exist under conditions of low mean annual shortwave radiation and low above-ground biomass. It suggests that this specific condition might play a key role in critical transitions between the two modes, while under other conditions no bimodality was found. Based on a land cover map in which anthropogenic land use was removed, six climatic indicators that represent water, energy, climate seasonality and water–radiation coupling are analysed to investigate the coexistence of these indicators with specific land cover types. From this analysis we find that the mean annual precipitation is not sufficient to predict potential land cover change. Indicators of climate seasonality are strongly related to the observed land cover type. However, these indicators cannot predict a stable forest state under the observed climatic conditions, in contrast to observed forest states. A new indicator (the normalized difference of precipitation) successfully expresses the stability of the precipitation regime and can improve the prediction accuracy of forest states. Next we evaluate land cover predictions based on different combinations of climatic indicators. Regions with high potential of land cover transitions are revealed. The results suggest that the tropical forest in the Congo basin may be unstable and shows the possibility of decreasing significantly. An increase in the area covered by savanna and grass is possible, which coincides with the observed regreening of the Sahara.

Above-ground biomass estimation of Indian tropical forests using X band Pol-InSAR and Random Forest

2021 ◽  
Vol 21 ◽  
pp. 100462
Author(s):  
Sadhana Yadav ◽  
Hitendra Padalia ◽  
Sanjiv K. Sinha ◽  
Ritika Srinet ◽  
Prakash Chauhan
Keyword(s):  
Random Forest ◽  
Tropical Forests ◽  
Biomass Estimation ◽  
Above Ground Biomass ◽  
Ground Biomass ◽  
X Band

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

2020 ◽  
Vol 5 (1) ◽  
pp. 13
Author(s):  
Negar Tavasoli ◽  
Hossein Arefi
Keyword(s):  
Machine Learning ◽  
Carbon Stock ◽  
Vegetation Indices ◽  
Forest Biomass ◽  
Principal Component ◽  
Optical Data ◽  
Above Ground Biomass ◽  
Ground Biomass ◽  
Texture Characteristics ◽  
Sentinel 2

Assessment of forest above ground biomass (AGB) is critical for managing forest and understanding the role of forest as source of carbon fluxes. Recently, satellite remote sensing products offer the chance to map forest biomass and carbon stock. The present study focuses on comparing the potential use of combination of ALOSPALSAR and Sentinel-1 SAR data, with Sentinel-2 optical data to estimate above ground biomass and carbon stock using Genetic-Random forest machine learning (GA-RF) algorithm. Polarimetric decompositions, texture characteristics and backscatter coefficients of ALOSPALSAR and Sentinel-1, and vegetation indices, tasseled cap, texture parameters and principal component analysis (PCA) of Sentinel-2 based on measured AGB samples were used to estimate biomass. The overall coefficient (R2) of AGB modelling using combination of ALOSPALSAR and Sentinel-1 data, and Sentinel-2 data were respectively 0.70 and 0.62. The result showed that Combining ALOSPALSAR and Sentinel-1 data to predict AGB by using GA-RF model performed better than Sentinel-2 data.

Sign in / Sign up

Export Citation Format

Share Document