Crop biomass estimation using multi regression analysis and neural networks from multitemporal L-band polarimetric synthetic aperture radar data

ABSTRACT Biomass has a direct relationship with agricultural production and may help to predict crop yield. Earth observation technology can contribute significantly to monitoring given the availability of temporally frequent and high-resolution radar or optical satellite data. Polarimetric Synthetic Aperture Radar (PolSAR) has several advantages for operational monitoring given that at these longer wavelengths atmospheric and illumination conditions do not affect acquisitions and considering the sensitivity of microwaves to the structural properties of targets. Therefore, SARs are a promising source of data for crop mapping and monitoring. With increasing access to SARs the development of robust methods to monitor crop productivity is timely. In this paper, we examine the use of machine learning and artificial intelligence approaches to analyze a time series of Polarimetric parameters for crop biomass estimation. In total, 14 polarimetric parameters from a time series of Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) airborne L-band data were used for biomass estimation for an intensively cropped site in western Canada. Then, Multiple linear regression (MR) and artificial neural network (ANN) models were developed and evaluated to estimate the biomass for canola, corn, and soybeans. According to the experimental results, the ANN provided more accurate biomass estimates compared to MR. Canola biomass, in general, showed less sensibility to almost all the polarimetric parameters. Nevertheless, Freeman-Double combined with vertical-vertical backscattering (VV) delivered the correlation coefficient (r) of 0.72, and the root mean square error (RMSE) of 56.55 g m−2of canola biomass. For corn, the highest correlation was observed between a pairing of horizontal- horizontal backscattering (HH) with Entropy (H) for biomass estimation yielding an r of 0.92 and RMSE of 196.71 g m−2. Horizontal-vertical backscattering (HV) and Yamaguchi-Surface (OY) delivered the highest sensitivity for soybeans (r of 0.82 and RMSE of 13.48 g m−2). If all crops are pooled, H combined with OY provided the most accurate estimates of biomass (r of 0.89 and RMSE of 135.31 g m−2). These results demonstrated that models which make use of polarimetric parameters that characterize the multiple sources of scattering typical of vegetation canopies can be used to estimate crop biomass accurately. Such results bode well for agricultural monitoring considering the increasing number of satellite SAR sensors with various frequencies, imaging modes and revisit times. As such, the time series analysis and methods proposed in this study could be used to monitor crop development and productivity using SAR space technologies.

[1]  D. Marquardt An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[2]  David S. Simonett,et al.  Remote Sensing with imaging radar: a review , 1970 .

[3]  F. Ulaby,et al.  Microwave Backscatter Dependence on Surface Roughness, Soil Moisture, and Soil Texture: Part I-Bare Soil , 1978, IEEE Transactions on Geoscience Electronics.

[4]  Fawwaz T. Ulaby,et al.  Relating the microwave backscattering coefficient to leaf area index , 1984 .

[5]  Simonetta Paloscia,et al.  Microwave polarization index for monitoring vegetation growth , 1988 .

[6]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[7]  Eric Pottier,et al.  A review of target decomposition theorems in radar polarimetry , 1996, IEEE Trans. Geosci. Remote. Sens..

[8]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[9]  Yaqiu Jin,et al.  Biomass retrieval from high-dimensional active/passive remote sensing data by using artificial neural networks , 1997 .

[10]  Eric Pottier,et al.  An entropy based classification scheme for land applications of polarimetric SAR , 1997, IEEE Trans. Geosci. Remote. Sens..

[11]  Stephen L. Durden,et al.  A three-component scattering model for polarimetric SAR data , 1998, IEEE Trans. Geosci. Remote. Sens..

[12]  Wim G.M. Bastiaanssen,et al.  Remote sensing for irrigated agriculture: examples from research and possible applications , 2000 .

[13]  G. Hoogenboom Contribution of agrometeorology to the simulation of crop production and its applications , 2000 .

[14]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[15]  P. Scharf,et al.  Calibrating Corn Color from Aerial Photographs to Predict Sidedress Nitrogen Need , 2002 .

[16]  R. J. Brown,et al.  Providing crop information using RADARSAT-1 and satellite optical imagery , 2002 .

[17]  L. Tian,et al.  A Review on Remote Sensing of Weeds in Agriculture , 2004, Precision Agriculture.

[18]  Hiroyoshi Yamada,et al.  Four-component scattering model for polarimetric SAR image decomposition , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Manolis I. A. Lourakis A Brief Description of the Levenberg-Marquardt Algorithm Implemented by levmar , 2005 .

[20]  박현준,et al.  Back Propagation , 1995, Artificial Neural Networks.

[21]  G. Civelekoglu,et al.  Prediction of Bromate Formation Using Multi-Linear Regression and Artificial Neural Networks , 2007 .

[22]  Eike Luedeling,et al.  Remote Sensing of Spider Mite Damage in California Peach Orchards Keywords: Aerial Imagery Integrated Pest Management Partial Least Squares (pls) Regression Prunus Persica Remote Sensing Spectral Reflectance Spectroradiometer , 2022 .

[23]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[24]  Nicolas Baghdadi,et al.  Potential of SAR sensors TerraSAR-X, ASAR/ENVISAT and PALSAR/ALOS for monitoring sugarcane crops on Reunion Island , 2009 .

[25]  John A. Richards,et al.  Remote Sensing with Imaging Radar , 2009 .

[26]  Zhaohua Deng,et al.  Understanding customer satisfaction and loyalty: An empirical study of mobile instant messages in China , 2010, Int. J. Inf. Manag..

[27]  Jakob van Zyl,et al.  Synthetic Aperture Radar Polarimetry: van Zyl/Synthetic Aperture , 2011 .

[28]  Heather McNairn,et al.  The sensitivity of RADARSAT-2 polarimetric SAR data to corn and soybean leaf area index , 2011 .

[29]  Manabu Watanabe,et al.  Polarimetric Decomposition Analysis of ALOS PALSAR Observation Data before and after a Landslide Event , 2012, Remote. Sens..

[30]  Fei Huang,et al.  Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement , 2012 .

[31]  Heather McNairn,et al.  Multiyear Crop Monitoring Using Polarimetric RADARSAT-2 Data , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[32]  George Miliaresis,et al.  Synthetic Aperture Radar Polarimetry , 2014 .

[33]  Heather McNairn,et al.  RADARSAT-2 Polarimetric SAR Response to Crop Biomass for Agricultural Production Monitoring , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[34]  Kalifa Goita,et al.  The Soil Moisture Active Passive Validation Experiment 2012 (SMAPVEX12): Prelaunch Calibration and Validation of the SMAP Soil Moisture Algorithms , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Monia Santini,et al.  An overview of available crop growth and yield models for studies and assessments in agriculture. , 2016, Journal of the science of food and agriculture.

[36]  Carlos López-Martínez,et al.  Crop scattering analysis of L-band PolSAR data for vegetation and soil monitoring , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[37]  Kalifa Goita,et al.  Evaluation of Simplified Polarimetric Decomposition for Soil Moisture Retrieval over Vegetated Agricultural Fields , 2016, Remote. Sens..

[38]  Lalit Kumar,et al.  Estimation of Winter Wheat Biomass and Yield by Combining the AquaCrop Model and Field Hyperspectral Data , 2016, Remote. Sens..

[39]  Fiona Cawkwell,et al.  Modeling Managed Grassland Biomass Estimation by Using Multitemporal Remote Sensing Data—A Machine Learning Approach , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[40]  Heather McNairn,et al.  Using multi-polarization C- and L-band synthetic aperture radar to estimate biomass and soil moisture of wheat fields , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[41]  P. Siqueira,et al.  Use of time-series L-band UAVSAR data for the classification of agricultural fields in the San Joaquin Valley , 2017 .

[42]  Irena Hajnsek,et al.  A Multi-Year Study on Rice Morphological Parameter Estimation with X-Band Polsar Data , 2017 .

[43]  Eric Pottier,et al.  Overview of Polarimetric Radar Imaging , 2017 .