Narayanarao Bhogapurapu

Dr. Narayanarao Bhogapurapu

Electrical and Computer Engineering, University of Massachusetts Amherst, Amherst, Massachusetts, USA
+1
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SGSwarnendu Sekhar Sekhar Ghosh
Swarnendu Sekhar Sekhar Ghosh
SDSubhadip Dey
Subhadip Dey
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
Saeid HomayouniSaeid Homayouni
Saeid Homayouni
ABAvik Bhattacharya
Avik Bhattacharya
HMHeather McNairn
Heather McNairn
Biophysical parameter retrieval using remote sensing has long been utilized for crop yield forecasting and economic practices. Remote sensing can provide information across a large spatial extent and in a timely manner within a season. Plant Area Index (PAI), Vegetation Water Content (VWC), and Wet-Biomass (WB) play a vital role in estimating crop growth and helping farmers make market decisions. Many parametric and non-parametric machine learning techniques have been utilized to estimate these parameters. A general non-parametric approach that follows a Bayesian framework is the Gaussian Process (GP). The parameters of this process-based technique are assumed to be random variables with a joint Gaussian distribution. The purpose of this work is to investigate Gaussian Process Regression (GPR) models to retrieve biophysical parameters of three annual crops utilizing combinations of multiple polarizations from C-band SAR data. RADARSAT-2 full-polarimetric images and in situ measurements of wheat, canola, and soybeans obtained from the SMAPVEX16 campaign over Manitoba, Canada, are used to evaluate the performance of these GPR models. The results from this research demonstrate that both the full-pol (HH+HV+VV) combination and the dual-pol (HV+VV) configuration can be used to estimate PAI, VWC, and WB for these three crops.

30 November 2019 in Preprints.org
Verified
Preprint
Open access
Dipankar MandalDipankar Mandal
Dipankar Mandal
DVDivya Sekhar Vaka
Divya Sekhar Vaka
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
VVVenkata Sai Vanama
Venkata Sai Vanama
VKVineet Kumar
Vineet Kumar
ABAvik Bhattacharya
Avik Bhattacharya
Sentinel-1 SAR data preprocessing is essential for several earth observation applications, including land cover classification, change detection, vegetation monitoring, urban growth, natural hazards, etc. The information can be extracted from the 2x2 covariance matrix [C2] of Sentinel-1 dual-pol (VV-VH) acquisitions. To generate the covariance matrix from Sentinel-1 single look complex (SLC) data, several preprocessing steps are required. The ESA SNAP S-1 toolbox can be used to preprocess the data to generate a [C2] matrix. The polarimetric analysis in respective application fields often starts with the covariance matrix. However, due to limited availability of Sentinel-1 SLC data preprocessing workflow standards for polarimetric applications in contemporary research methods, downstream applications unable to comply with these workflows directly. In this paper, we propose a couple of generic practices to preprocess Sentinel-1 SLC data in SNAP S-1 toolbox, which would be beneficial for the radar remote sensing user community.

16 May 2021 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
SDSubhadip Dey
Subhadip Dey
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
ABAvik Bhattacharya
Avik Bhattacharya
Dipankar MandalDipankar Mandal
Dipankar Mandal
JLJuan M Lopez-Sanchez
Juan M Lopez-Sanchez
Alejandro C. FreryAlejandro C. Frery
Alejandro C. Frery
We require spatio-temporal information about rice for executing and planning diverse management practices. In this regard, data obtained from Synthetic Aperture Radar (SAR) sensors are well suited for tracking morphological developments of rice across its phenology stages. This study proposes different target characterization parameters from polarimetric SAR data for rice phenology mapping. Six C-band Radarsat-2 images acquired over Vijayawada, India, are used for complete analysis. It is known that polarimetric information provides excellent sensitivity for identifying crop phenology stages. Hence, in this study, we assessed phenology classification results using a scattering-type parameter and scattering powers for full-polarimetric (FP) and extracted dual-polarimetric (DP) SAR data. Here, we utilized the real 4 ×4 Kennaugh matrix elements to derive these parameters equivalently for the two polarimetric modes (i.e. FP and DP). We obtained better overall classification accuracy for each phenology stages using the proposed parameters than the existing ones from FP and DP SAR data. We noted that the overall classification accuracy using the DP SAR data was only marginally lower than the FP SAR data. This marginal difference in the accuracies could be due to the absence of the cross-polarized component in the DP SAR data. We also demonstrate the usefulness of the scattering powers from DP SAR data for rice phenology monitoring.

2 November 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SDSubhadip Dey
Subhadip Dey
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
Saeid HomayouniSaeid Homayouni
Saeid Homayouni
ABAvik Bhattacharya
Avik Bhattacharya
HMHeather McNairn
Heather McNairn
Global crop mapping and monitoring requires high-resolution spatio-temporal information. In this regard, dual polarimetric Synthetic Aperture Radar (SAR) sensors provide high temporal and high spatial resolutions with large swath width. Generally, crop phenological development studies utilized SAR backscatter intensity-based descriptors. However, these descriptors are derived either from the covariance matrix elements or from the eigendecomposition. Therefore, this approach fails to utilize the complete polarization information of the scattered wave. In this study, we propose a target characterization parameter, θxP that utilizes the 2D Barakat degree of polarization and the elements of the covariance matrix. We also propose an unsupervised clustering scheme using θxP and the scattering entropy, HxP. We utilize time-series Sentinel-1 data of canola and wheat fields over a Canadian test site to show the sensitivity of θxP to the development of crop morphology at different phenological stages. During the initial growth stages, θxP values are low due to the low vegetation density. In contrast, at advanced phenological stages, we observe decreased values of θxP due to the appearance of complex canopy structure. Similarly, the effectiveness of the unsupervised HxP/θxP clustering plane is also evident from the temporal clustering plots. This innovative clustering framework is beneficial for the operational use of Sentinel-1 SAR data for agricultural applications.

8 April 2021 in Journal of Open Source Software
Verified
Journal Article
Open access
PDF file
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
SDSubhadip Dey
Subhadip Dey
Dipankar MandalDipankar Mandal
Dipankar Mandal
ABAvik Bhattacharya
Avik Bhattacharya
YRY S Rao
Y S Rao

13 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
PRPartha Deb Roy
Partha Deb Roy
SDSubhadip Dey
Subhadip Dey
Narayanarao BhogapurapuNarayanarao Bhogapurapu
Narayanarao Bhogapurapu
Somsubhra ChakrabortySomsubhra Chakraborty
Somsubhra Chakraborty
The presence of vegetation in agricultural fields affects the accuracy of soil moisture retrieval using synthetic aperture radar (SAR) data. As a result, the estimation of soil moisture using the existing Oh model produces high error values. The magnitude of this error primarily depends upon the nature of crops, crop coverage, and the roughness of the field. Hence, in this study, along with the Oh model, we proposed a novel approach using model-based decomposition to reduce the volume contribution of the vegetation. This proposed method is employed on fallow as well as different crop fields in the summer of 2023 in the Kharagpur region of India using the Sentinel-1 dual polarimetric SAR data. The Root Mean Square Error (RMSE) of the proposed method is ≈25% to 52% lower over different crop types as compared to the existing Oh model. Moreover, the proposed method is also compared with the Chang model, designed to estimate soil moisture in vegetative fields. The proposed method exhibits RMSE that is around ≈10% to 17% lower across various crop kinds, in comparison to the Chang model. Thus, the proposed novel approach, with the advantage of not requiring in situ plant descriptors, will simplify the application of dual polarimetric SAR data for soil moisture estimation in a variety of land-use scenarios.