Estimation Of Biophysical Parameters Research Articles

Spaceborne tomography of multi-species Indian tropical forests

Synthetic Aperture Radar (SAR) backscatter is the coherent combination of the scattering from multiple individual scatterers within the radar resolution cell, which results into a 2-D radar image. Tomographic SAR (TomoSAR) takes advantage of multiple SAR acquisitions to provide 3-D vertical structure of the imaged target. Over forests, parameters such as canopy structure, canopy density, leaf area and phenology contribute to different SAR scattering mechanisms along the vertical dimension of the trees. Tomography has been demonstrated in various earlier works for forest bio-physical parameter estimation using airborne data. In this research work, multi-polarimetric space-borne TanDEM-X tomograms are examined for the first time over a multi-species Indian tropical forest. Multiple TanDEM-X acquisitions are focused using Capon beamforming at five polarimetric channels — HH, HV, VV, HH − VV and HH + VV. Four distinct forest species compartments are selected representing different canopy structure and density. The tomograms obtained in different polarizations for these species are analyzed in detail to understand the scattering patterns across different forest species. Field surveys carried out in several forest locations provide in situ observations of forest height and vertical structure. It was observed that canopy gaps and leaf density play a crucial role for X-band SAR signal penetration through ground. For dense canopy species the backscatter contributions are spread through the canopy, while in case of sparse canopy species, the ground scattering is dominant. Vertical profiles obtained at surveyed plot locations are plotted in all polarizations, and provide a good agreement with field observations. Further, the obtained TomoSAR backscatter layers have a good correlation with field measured above-ground biomass (AGB). The AGB is modeled from TomoSAR with the HH-pol TomoSAR backscatter layer at 27 m canopy height leading to an AGB estimation with correlation r = 0.76 and RMSE of 50.4 t/ha.

Joint estimation of Plant Area Index (PAI) and wet biomass in wheat and soybean from C-band polarimetric SAR data

Retrieval of the Plant Area Index (PAI) and wet biomass from polarimetric SAR (PolSAR) data is of paramount importance for in-season monitoring of crop growth. Notably, the joint estimation of biophysical parameters might be effective instead of an individual parameter due to their inherent relationships (possibly nonlinear). The semi-empirical water cloud model (WCM) can be suitably utilized to estimate biophysical parameters from PolSAR data. Nevertheless, instability problems could occur during the model inversion process using traditional inversion approaches. Iterative optimization (IO) can have difficulty in finding the global minima while look up table (LUT) searches have a lower generalization capability. These challenges reduce the transferability of IO and LUT search inversions in computational efficiency and seldom account for the inter-correlation among the parameters. Alternatively, a machine learning regression technique with a regularization routine may provide a stable and optimum solution for ill-posed problems related to the inversion of the WCM. In the present work, the crop biophysical parameters viz. PAI and wet biomass are estimated simultaneously using the multi-target Random Forest Regression (MTRFR) technique. The accuracy of the retrieval method is analyzed using the in-situ measurements and quad-pol RADARSAT-2 data acquired during the SMAPVEX16 campaign over Manitoba, Canada. The inversion process is tested with different polarization combinations of SAR data for wheat and soybean. The validation used ground measured biophysical parameters for various crops, indicating promising results with a correlation coefficient (r) in the range of 0.6–0.8. In addition, the relationship between PAI and wet biomass using the multi-target and single output model is also assessed based on in-situ measurements. The results confirm that the inter-correlation between biophysical parameters is well preserved in the MTRFR based joint inversion technique for both wheat and soybean.

ESTIMATION OF BIOPHYSICAL PARAMETERS OF WHEAT CROP THROUGH MODIFIED WATER CLOUD MODEL USING SATELLITE DATA

Abstract. A modified water cloud model (WCM) was used to estimate the biophysical parameters of wheat crop using Sentinel-1A and Landsat-8 satellite images. The approach of combining the potential of SAR and optical data provided a new technique for the estimation of biophysical parameters of wheat crop. The biophysical parameters estimation was done using non-linear least squares optimization technique by minimizing the cost function between the backscattering coefficients (σ0) computed from the Sentinel-1A image and simulated by the modified WCM followed by look up table algorithm(LUT). The modified WCM integrates the full account of backscattering response on vegetation and bare soil by adding vegetation fraction. The modified WCM was found more sensitive than the original WCM because of incorporation of vegetation fraction (fveg) derived from the Landsat-8 satellite data. The estimated values of leaf area index (LAI) by modified WCM at VV polarization shows good correlation (R2 = 83.08 % and RMSE = 0.502 m2/m2) with the observed values. Whereas, leaf water area index (LWAI) shows comparatively poor correspondence (R2 = 76 % and RMSE = 0.560 m2/m2) with the observed data in comparison to LAI estimation at VV polarization. The performance indices show that the modified WCM was found more accurate for the estimation of wheat crop parameters during the whole growth season in Varanasi district, India. Thus, the modified WCM shows significant potential for the accurate estimation of LAI and LWAI of wheat crop on incorporating both SAR and optical satellite data.

In-season biomass estimation of oilseed rape (Brassica napus L.) using fully polarimetric SAR imagery

Accurate estimation of crop biophysical and biochemical parameters during crop growing seasons is essential for improving site-specific management and yield estimation. The potential ability of fully polarimetric synthetic aperture radar (SAR) data in estimating above-ground biomass of oilseed rape was investigated in this study. The temporal profile of different scattering intensity and polarimetric features during the entire growing season was identified with ground measurements. A polarimetric feature, relying on the polarimetric decomposition method, was put forward to estimate the biomass of oilseed rape. Validation results revealed great potential with a determination coefficient (R2) of 0.85, root mean squared error (RMSE) of 41.6 g/m2, and relative error (RE) of 28.5% for dry biomass, and an R2 of 0.76, RMSE of 527.4 g/m2 and RE of 28.6% for fresh biomass. Moreover, the use of full polarization SAR data was compared with single and dual polarization SAR data. The results suggest that when full polarization SAR data is available, a simpler model, higher saturation point and better accuracy can be achieved in biomass estimation of oilseed rape, which highlights the importance and value of polarimetry information in quantitative crop monitoring. This study provides guidelines for in-season monitoring of crop growth parameters with SAR data, which further improves crop monitoring capability in adverse weather conditions.

Advances in Radar Remote Sensing of Agricultural Crops: A Review

There are enormous advantages of a review article in the field of emerging technology like radar remote sensing applications in agriculture. This paper aims to report select recent advancements in the field of Synthetic Aperture Radar (SAR) remote sensing of crops. In order to make the paper comprehensive and more meaningful for the readers, an attempt has also been made to include discussion on various technologies of SAR sensors used for remote sensing of agricultural crops viz. basic SAR sensor, SAR interferometry (InSAR), SAR polarimetry (PolSAR) and polarimetric interferometry SAR (PolInSAR). The paper covers all the methodologies used for various agricultural applications like empirically based models, machine learning based models and radiative transfer theorem based models. A thorough literature review of more than 100 research papers indicates that SAR polarimetry can be used effectively for crop inventory and biophysical parameters estimation such are leaf area index, plant water content, and biomass but shown less sensitivity towards plant height as compared to SAR interferometry. Polarimetric SAR Interferometry is preferable for taking advantage of both SAR polarimetry and SAR interferometry. Numerous studies based upon multi-parametric SAR indicate that optimum selection of SAR sensor parameters enhances SAR sensitivity as a whole for various agricultural applications. It has been observed that researchers are widely using three models such are empirical, machine learning and radiative transfer theorem based models. Machine learning based models are identified as a better approach for crop monitoring using radar remote sensing data. It is expected that the review article will not only generate interest amongst the readers to explore and exploit radar remote sensing for various agricultural applications but also provide a ready reference to the researchers working in this field.

Estimation of the directional and whole apparent clumping index (ACI) from indirect optical measurements

Canopy clumping index (CI) indicates the non-random distribution of foliage components in space, and is an important structural parameter for better understanding the radiative transfer process in a canopy. The apparent clumping index (ACI), calculated using the logarithmic gap fraction averaging method, is reported by the LAI-2200 Plant Canopy Analyzer. While LAI-2200 calculates the gap fraction and ACI from different conical rings, calculation of ACI for other geometric units (e.g., an angular cell or an azimuth sector) and instruments has been lacked. Building upon the LAI-2200 ACI, this study compares the ACIs calculated for different geometric spaces from different optical instruments. The field data obtained from seasonal continuous measurements with LAI-2200, digital hemispheric photography (DHP), and AccuPAR at a paddy rice field in northeast China were used to calculate the directional ACIs at different levels—a directional cell (ΩA(θ, ϕ)), a concentric ring (ΩA(θ)), an azimuth sector (ΩA(ϕ)), and over the horizontal landscape (ΩA(ν)). The whole ACIs were calculated from the directional ACIs with an angular integration method, a simple averaging method, a non-linear correction method, and a variance-to-mean ratio method. The directional ACIs for paddy rice generally follow the order of ΩA(θ, ϕ) < ΩA(θ) and ΩA(ϕ) < ΩA(ν), displaying an increase of foliage randomness with the segment size. The ΩA(θ, ϕ) estimated from DHP indicates canopy clumping at the finest level and is consistent with the CIs estimated from the logarithmic averaging method (ΩLX) and the ratio method (the effective leaf area index (LAIe) divided by the LAI). The ACI metrics expand the current CI metrics and can be obtained with different optical instruments. The expanded metrics can be applied in the canopy radiative transfer modeling and in the estimation of canopy biophysical parameters for other vegetation ecosystems.

Physics-aware Gaussian processes in remote sensing

Earth observation from satellite sensory data poses challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression has excelled in biophysical parameter estimation tasks from airborne and satellite observations. GP regression is based on solid Bayesian statistics, and generally yields efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations between the state vector and the radiance observations is available though and could be useful to improve predictions and understanding. In this work, we review three GP models that respect and learn the physics of the underlying processes in the context of both forward and inverse modeling. After reviewing the traditional application of GPs for parameter retrieval, we introduce a Joint GP (JGP) model that combines in situ measurements and simulated data in a single GP model. Then, we present a latent force model (LFM) for GP modeling that encodes ordinary differential equations to blend data-driven modeling and physical constraints of the system governing equations. The LFM performs multi-output regression, adapts to the signal characteristics, is able to cope with missing data in the time series, and provides explicit latent functions that allow system analysis and evaluation. Finally, we present an Automatic Gaussian Process Emulator (AGAPE) that approximates the forward physical model using concepts from Bayesian optimization and at the same time builds an optimally compact look-up-table for inversion. We give empirical evidence of the performance of these models through illustrative examples of vegetation monitoring and atmospheric modeling.

Comparative analysis of UAV RS and traditional cotton leaf falling evaluation methods

Evaluating the spraying effect of defoliant is necessary condition to facilitate mechanized cotton harvesting. However, traditional method to evaluate the effect of spraying defoliation by manually calculating the number of cotton defoliation will produce large statistical error and increase the labor cost. Low altitude remote sensing provides accurate and timely estimation of biophysical parameters, such as leaf area index (LAI), crop growth and plant biomass. The objective of this work was to discover a high-precision evaluation way of spraying cotton defoliating by comparing the multispectral remote sensing evaluation method with the traditional evaluation method. UAV multispectral images were collected in a cotton field ofYellowRiver Basin inChina, and the images in five narrow bands included Red, Blue, Green, Near infrared (NIR) and Red Edge. The processing of multispectral images was performed in the Python environment, NDVI images and GNDVI images were created. Based on this, the NDVI data, GNDVI data and manual statistical data were compared. The results show that compared with traditional methods, the multispectral remote sensing evaluation method can be more accurate and effective in evaluating the spraying effect of cotton defoliant. Keywords: multispectral remote sensing, defoliation, evaluation, precision agriculture UAV DOI: 10.33440/j.ijpaa.20210402.178 Citation: Zhang Y Z, Li W H, Ran W X, Gu J, Lan Y B. Comparative analysis of UAV RS and traditional cotton leaf falling evaluation methods. Int J Precis Agric Aviat, 2021; 4(2): 40–44.

TOPOGRAPHIC ASPECTS IN THE SPATIAL AND TEMPORAL DYNAMIC OF NET RADIATION

ABSTRACT: The measurements obtained by remote sensing are influenced by issues related to relief. Based on that, this paper aims to analyze the spatial and temporal dynamics of the net radiation (Rn), considering the influence of topographic parameters on it, in Edgardia Experimental Farm (FEE). It was used the methodology based on the SEBAL algorithm (Surface Energy Balance Algorithm for Land) to estimate the net radiation by orbital images. In order to assess the topographic influence on the computing of net radiation, three methodologies were applied: without topographic correction (RnSem), cosine correction (RnCos) and C correction (RnC). These methodologies were applied on 21 images of the orbital platform Landsat-5/TM, from 1985 up to 2010. Due to the complex relief of the FEE, the cosine correction did not show effectiveness on the attenuation of topographic influence. For the values of RnC, we noticed an average reduction of 5.97% for the standard deviation, relative to the images without correction. These results show the importance of considering the relief, to achieve higher accuracies on the estimation of biophysical parameters with orbital images.

Simulating the Effects of the Airborne Lidar Scanning Angle, Flying Altitude, and Pulse Density for Forest Foliage Profile Retrieval

Foliage profile is a key biophysical parameter for forests. Airborne Light Detection and Ranging is an effective tool for vegetation parameter retrieval. Data acquisition conditions influence the estimation of biophysical parameters. To acquire accurate foliage profiles at the lowest cost, we used simulations to explore the effects of data acquisition conditions on forest foliage profile retrieval. First, a 3-D forest scene and the airborne small-footprint full-waveform LiDAR data were simulated by the DART model. Second, the foliage profile was estimated from LiDAR data based on a Geometric Optical and Radiative Transfer model. Lastly, the effects of the airborne LiDAR scanning angle, flying altitude, and pulse density on foliage profile retrieval were explored. The results indicated that the scanning angle was an important factor in the foliage profile retrieval, and the optimal scanning angle was 20°. The optimal scanning angle was independent of flying altitude and pulse density, and combinations of multiple scanning angles could improve the accuracy of the foliage profile estimation. The flying altitude and pulse density had little influence on foliage profile retrieval at plot level and could be ignored. In general, our study provides reliable information for selecting the optimal instrument operational parameters to acquire more accurate foliage profiles and minimize data acquisition costs.

Estimación de variables biofísicas del pastizal en un ecosistema de dehesa a partir de espectro-radiometría de campo e imágenes hiperespectrales aeroportadas

&lt;p&gt;The aim of this paper is the estimation of biophysical vegetation parameters from its optical properties. The variables Fuel Moisture Content (&lt;em&gt;FMC&lt;/em&gt;), Canopy Water Content (&lt;em&gt;CWC&lt;/em&gt;), Leaf Area Index (&lt;em&gt;LAI&lt;/em&gt;), dry matter (Cm) and AboveGround Biomass (AGB) were estimated in the laboratory from vegetation samples collected simultaneously with the acquisition of spectral data from the Compact Airborne Spectrographic Imager (CASI) sensor and the field spectroradiometer ASD FieldSpec® 3. Spectral vegetation indices found in the literature were computed from hyperspectral data. Their linear relationships with the biophysical variables measured in the field were analysed. Results show consistent relationships between analysed biophysical parameters and spectral indices, mainly those using SWIR and red-egde bands which reveal the importance of these spectral regions for the estimation of biophysical variables in herbaceous covers. Determination coefficients (&lt;em&gt;R&lt;sup&gt;2&lt;/sup&gt;&lt;/em&gt;) above 0.91 and &lt;em&gt;RRMSE&lt;/em&gt; of 21.4% have been obtained for the spectral indexes calculated whit ASD data, and 0.91 &lt;em&gt;R&lt;sup&gt;2 &lt;/sup&gt;&lt;/em&gt;and &lt;em&gt;RRMSE&lt;/em&gt; of 15.5% for the spectral indexes calculated whit CASI data.&lt;/p&gt;

Radiometric Correction of Airborne Radar Images Over Forested Terrain With Topography

Radiometric correction of radar images is essential to produce accurate estimates of biophysical parameters related to forest structure and biomass. We present a new algorithm to correct radiometry for 1) terrain topography and 2) variations of canopy reflectivity with viewing and tree-terrain geometry. This algorithm is applicable to radar images spanning a wide range of incidence angles over terrain with significant topography and can also take into account aircraft attitude, antenna steering angle, and target geometry. The approach includes elements of both homomorphic and heteromorphic terrain corrections to correct for topographic effects and is followed by an additional radiometric correction to compensate for variations of canopy reflectivity with viewing and tree-terrain geometry. The latter correction is based on lookup tables and enables derivation of biophysical parameters irrespective of viewing geometry and terrain topography. We evaluate the performance of the new algorithm with airborne radar data and show that it performs better than classical homomorphic methods followed by cosine-based corrections.

Effects of LiDAR point density, sampling size and height threshold on estimation accuracy of crop biophysical parameters.

Vegetation leaf area index (LAI), height, and aboveground biomass are key biophysical parameters. Corn is an important and globally distributed crop, and reliable estimations of these parameters are essential for corn yield forecasting, health monitoring and ecosystem modeling. Light Detection and Ranging (LiDAR) is considered an effective technology for estimating vegetation biophysical parameters. However, the estimation accuracies of these parameters are affected by multiple factors. In this study, we first estimated corn LAI, height and biomass (R2 = 0.80, 0.874 and 0.838, respectively) using the original LiDAR data (7.32 points/m2), and the results showed that LiDAR data could accurately estimate these biophysical parameters. Second, comprehensive research was conducted on the effects of LiDAR point density, sampling size and height threshold on the estimation accuracy of LAI, height and biomass. Our findings indicated that LiDAR point density had an important effect on the estimation accuracy for vegetation biophysical parameters, however, high point density did not always produce highly accurate estimates, and reduced point density could deliver reasonable estimation results. Furthermore, the results showed that sampling size and height threshold were additional key factors that affect the estimation accuracy of biophysical parameters. Therefore, the optimal sampling size and the height threshold should be determined to improve the estimation accuracy of biophysical parameters. Our results also implied that a higher LiDAR point density, larger sampling size and height threshold were required to obtain accurate corn LAI estimation when compared with height and biomass estimations. In general, our results provide valuable guidance for LiDAR data acquisition and estimation of vegetation biophysical parameters using LiDAR data.

An inversion approach for determining distribution of production and temperature sensitivity of soil respiration

Abstract. Physical soil properties create lags between temperature change and corresponding soil responses, which obscure true Q10 (temperature sensitivity) values and other biophysical parameters such as depth of production. This study examines an inversion approach for estimating Q10 and e-folding depth of CO2 production (Zp) using physically based soil models, constrained by observed high-frequency surface fluxes and/or concentrations. Our inversion strategy uses a one-dimensional (1-D) multi-layered soil model that simulates realistic temperature and gas diffusion. We tested inversion scenarios on synthetic data using a range of constraining parameters, time-averaging techniques, mechanisms to improve computational efficiency, and various methods of incorporating real data into the model. Overall, we have found that with carefully constrained data, inversion was possible. While inversions using exclusively surface-flux measurements could succeed, constraining the inversion using multiple shallow subsurface CO2 measurements proved to be most successful. Inversions constrained by these shallow measurements returned Q10 and Zp values with average errors of 1.85 and 0.16 % respectively. This work is a first step toward building a reliable framework for removing physical effects from high-frequency soil CO2 data. Ultimately, we hope that this process will lead to better estimates of biophysical soil parameters and their variability on short timescales.

Continuous monitoring of biophysicalEucalyptussp. parameters using interferometric synthetic aperture radar data in P and X bands

This work aims to verify the applicability of models obtained using interferometric synthetic aperture radar (SAR) data for estimation of biophysical Eucalyptus saligna parameters [diameter of breast height (DBH), total height and volume], as a method of continuous forest inventory. In order to obtain different digital elevation models, and the interferometric height (Hint) to retrieve the tree heights, SAR surveying was carried out by an airborne interferometric SAR in two frequencies X and P bands. The study area, located in the Brazilian southeast region (S 22°53′22″/W 45°26′16″ and S 22°53′22″/W 45°26′16″), comprises 128.64 hectares of Eucalyptus saligna stands. The methodological procedures encompassed: forest inventory, topographic surveying, radar mapping, radar processing, and multivariable regression techniques to build Eucalyptus volume, DBH, and height models. The statistical regression pointed out Hint and interferometric coherence as the most important variables for the total height and DBH estimation; for the volume model, however, only the Hint variable was selected. The performance of the biophysical models from the second campaign, two years later (2006), were consistent and its results are very promising for updating annual inventories needed for managing Eucalyptus plantations.

Estimativa do balanço de radiação por sensoriamento remoto de diferentes usos de solo no sudoeste da Amazônia brasileira

RESUMO Mudanças no uso do solo têm motivado pesquisas sobre a dinâmica de trocas radiativas e energéticas na Amazônia Brasileira que, por sua vez, geram demanda destas informações de superfície em escalas espaciais e temporais. Enquanto a medição destas trocas em torres micrometeorológicas fornece resultados pontuais, o sensoriamento remoto apresenta resultados acurados e de baixo custo para estimá-las em escala regional. Este estudo objetivou avaliar a distribuição espacial e temporal de estimativas de saldo de radiação e parâmetros biofísicos por sensoriamento remoto de diferentes usos do solo no sudoeste da Amazônia Brasileira. Foram selecionadas 04 áreas de solo coberto por floresta amazônica natural, floresta amazônica manejada, sistema silvipastoril e pastagem. O saldo de radiação, NDVI, índice de área foliar, albedo e temperatura radiométrica foram estimados pelo algoritmo SEBAL, usando imagens do sensor TM do satélite Landsat 5 em julho de 2009, 2010 e 2011. O NDVI, IAF, albedo e saldo de radiação apresentaram maiores valores na floresta natural, seguida por floresta manejada, sistema silvipastoril e pastagem. A temperatura radiométrica da superfície apresentou maiores valores para o sistema silvipastoril seguido por pastagem, floresta natural e floresta manejada.

Estimation of rice biophysical parameters using multitemporal RADARSAT-2 images

Compared with optical sensors, synthetic aperture radar (SAR) has the capability of acquiring images in all-weather conditions. Thus, SAR images are suitable for using in rice growth regions that are characterized by frequent cloud cover and rain. The objective of this paper was to evaluate the probability of rice biophysical parameters estimation using multitemporal RADARSAT-2 images, and to develop the estimation models. Three RADARSTA-2 images were acquired during the rice critical growth stages in 2014 near Meishan, Sichuan province, Southwest China. Leaf area index (LAI), the fraction of photosynthetically active radiation (FPAR), height, biomass and canopy water content (WC) were observed at 30 experimental plots over 5 periods. The relationship between RADARSAT-2 backscattering coefficients (σ0) or their ratios and rice biophysical parameters were analysed. These biophysical parameters were significantly and consistently correlated with the VV and VH σ0 ratio (σ0VV/ σ0VH) throughout all growth stages. The regression model were developed between biophysical parameters and σ0VV/ σ0VH. The results suggest that the RADARSAT-2 data has great potential capability for the rice biophysical parameters estimation and the timely rice growth monitoring.

Combined Use of Airborne LiDAR and Satellite GF-1 Data to Estimate Leaf Area Index, Height, and Aboveground Biomass of Maize During Peak Growing Season

A fast and efficient estimation of crop biophysical parameters is significantly important in many agricultural, ecological, and meteorological applications. This study investigated the potential of airborne LiDAR and satellite GF-1 data for estimating three biophysical parameters of maize: 1) leaf area index (LAI); 2) average canopy height $\left({{{\bf H}_{{\bf canopy}}}} \right)$ ; and 3) aboveground biomass (AGB) during the peak growing season. First, classification data of maize was produced using normalized surface height, GF-1 NDVI, and terrain slope through decision-making. Second, four representative remotely sensed (RS) metrics which have been widely used in forest studies were tested to develop multiplicative models with similar shapes for estimating each biophysical parameter of maize, respectively. Third, the estimation results were obtained and validated through leave-one-out cross-validation method yielding a root-mean-square error (rmse) of 0.37 for LAI, 0.17 m for ${{\bf H}_{{\bf canopy}}}$ , and ${0}.{49}\,{\bf kg}/{{\bf m}^{2}}$ for AGB. Finally, contributions to the estimation models from each RS metric were analyzed, and spatial patterns of the biophysical parameters across the entire study area were mapped. Based on these results, the following conclusions were drawn. 1) The four selected metrics from airborne LiDAR and satellite GF-1 data are also applicable and promising in estimating biophysical parameters of maize during the peak growing season. 2) Multiplicative model was proved to be a fast, simple but effective alternative by combining LiDAR-derived structure information and spectral content from GF-1 NDVI. These conclusions provide valuable information for estimation of biophysical parameters of maize during the peak growing season.

Comparing the performance of multispectral vegetation indices and machine-learning algorithms for remote estimation of chlorophyll content: a case study in the Sundarbans mangrove forest

Optical vegetation indices (VIs) have been used to retrieve and assess biophysical variables from satellite reflectance data. These indices, however, also are sensitive to a number of confounding factors, such as canopy geometry, soil optical properties, and solar position. This suggests that VIs should be used cautiously for biophysical parameter estimation. Among biophysical variables, chlorophyll content is of particular importance as an indicator of photosynthetic activity. The goal of this study is to investigate the performance of multispectral optical VIs for chlorophyll content estimation in the world’s largest mangrove forest, the Sundarbans, and to compare these with machine-learning algorithms (MLAs). To this end, we have investigated the performance of 15 multispectral VIs and six state-of-the-art MLAs that are widely used for adaptive data fitting. The MLAs are Artificial Neural Networks (ANNs), Genetic Algorithm (GA), Gaussian Processes for Machine Learning (GPML), Kernel Ridge Regression (KRR), Locally Weighted Polynomials (LWP), and Multivariate Adaptive Regression Splines (MARS). We use an in situ data set of reflectance and chlorophyll measurements to develop and validate our models. Each MLA was evaluated 500 times with random partitions of training and validation data. Results showed that the weight optimization and term selection used within GA produce the most reliable chlorophyll content estimation. However, green normalized difference VI (GNDVI) is a simple and computationally efficient VI that produces results that are nearly as accurate as GA in terms of model fit and performance. Results also show that all methods except ANNs and MARS produce a quasi-linear relationship between spectral reflectance and chlorophyll content. Statistical transformations of GNDVI and chlorophyll content have the capability of further reducing model error.

Comparative Evaluation of Inversion Approaches of the Radiative Transfer Model for Estimation of Crop Biophysical Parameters

Abstract The inversion of canopy reflectance models is widely used for the retrieval of vegetation properties from remote sensing. This study evaluates the retrieval of soybean biophysical variables of leaf area index, leaf chlorophyll content, canopy chlorophyll content, and equivalent leaf water thickness from proximal reflectance data integrated broadbands corresponding to moderate resolution imaging spectroradiometer, thematic mapper, and linear imaging self scanning sensors through inversion of the canopy radiative transfer model, PROSAIL. Three different inversion approaches namely the look-up table, genetic algorithm, and artificial neural network were used and performances were evaluated. Application of the genetic algorithm for crop parameter retrieval is a new attempt among the variety of optimization problems in remote sensing which have been successfully demonstrated in the present study. Its performance was as good as that of the look-up table approach and the artificial neural network was a poor performer. The general order of estimation accuracy for parameters irrespective of inversion approaches was leaf area index &gt; canopy chlorophyll content &gt; leaf chlorophyll content &gt; equivalent leaf water thickness. Performance of inversion was comparable for broadband reflectances of all three sensors in the optical region with insignificant differences in estimation accuracy among them.