Estimation of soil properties from the EU spectral library using long short-term memory networks

Abstract Recent advances in Deep learning altered the traditional way of data analysis in various domains. This study focuses primarily on the quantification of soil properties from the hyperspectral data obtained from LUCAS using Long Short-Term Memory Networks based deep learning model. Hyperspectral data is sequential in nature due to which LSTMs are preferred as these are predominantly used for sequential problems. In addition to this, Principal Component Analysis is also performed on the LUCAS dataset to reduce the dimensions for efficient calibration of LSTMs. Better performance is achieved using the proposed framework with best R2 of 0.94 in case of Organic Carbon and the effectiveness is shown by comparing it with existing models such as PLSR, SVR, PCR, MLR and SWR.

[1]  Budiman Minasny,et al.  Using deep learning to predict soil properties from regional spectral data , 2019, Geoderma Regional.

[2]  E. R. Stoner,et al.  REFLECTANCE PROPERTIES OF SOILS , 1986 .

[3]  R. Henry,et al.  Simultaneous Determination of Moisture, Organic Carbon, and Total Nitrogen by Near Infrared Reflectance Spectrophotometry , 1986 .

[4]  Claire R. Cousins,et al.  Spectral identification and quantification of salts in the Atacama Desert , 2016, Remote Sensing.

[5]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  L. Janik,et al.  Characterization and analysis of soils using mid-infrared partial least-squares .2. Correlations with some laboratory data , 1995 .

[7]  N. Holden,et al.  Optical sensing and chemometric analysis of soil organic carbon – a cost effective alternative to conventional laboratory methods? , 2011 .

[8]  H. Condit.  THE SPECTRAL REFLECTANCE OF AMERICAN SOILS , 1970 .

[9]  Emile Ndikumana,et al.  Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France , 2018, Remote. Sens..

[10]  Simranjit Singh,et al.  Efficient classification of the hyperspectral images using deep learning , 2018, Multimedia Tools and Applications.

[11]  Mikael Kågebäck,et al.  Word Sense Disambiguation using a Bidirectional LSTM , 2016, CogALex@COLING.

[12]  Yu Zhang,et al.  Prediction of Wind Turbine-Grid Interaction Based on a Principal Component Analysis-Long Short Term Memory Model , 2018, Energies.

[13]  Fanzhi Meng,et al.  A network threat analysis method combined with kernel PCA and LSTM-RNN , 2018, 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI).

[14]  W. Blum,et al.  Soil Protection Concept of The Council of Europe and Integrated Soil Research , 1993 .

[15]  J. C. Price,et al.  An Approach for Analysis of Reflectance Spectra , 1998 .

[16]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[17]  Debashis Chakraborty,et al.  QUANTITATIVE ASSESSMENT OF SOIL CHEMICAL PROPERTIES USING VISIBLE (VIS) AND NEAR-INFRARED (NIR) PROXIMAL HYPERSPECTRAL DATA , 2010 .

[18]  B. Bousquet,et al.  Towards quantitative laser-induced breakdown spectroscopy analysis of soil samples ☆ , 2007 .

[19]  A. Ruffell,et al.  Conjunctive use of quantitative and qualitative X-ray diffraction analysis of soils and rocks for forensic analysis. , 2004, Forensic science international.

[20]  Nitin K. Tripathi,et al.  Artificial neural network analysis of laboratory and in situ spectra for the estimation of macronutrients in soils of Lop Buri (Thailand) , 2003 .

[21]  H. Jenny,et al.  The soil resource. Origin and behavior , 1983, Vegetatio.

[22]  Eyal Ben-Dor,et al.  Near-Infrared Analysis as a Rapid Method to Simultaneously Evaluate Several Soil Properties , 1995 .

[23]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[24]  A. Agarwal,et al.  Efficient Hierarchical-PCA Dimension Reduction for Hyperspectral Imagery , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[25]  Manfred F. Buchroithner,et al.  Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery , 2018, Sensors.

[26]  Alex B. McBratney,et al.  A response-surface calibration model for rapid and versatile site-specific lime-requirement predictions in south-eastern Australia , 2001 .

[27]  M. Kovacevic,et al.  Soil type classification and estimation of soil properties using support vector machines , 2010 .

[28]  Paul Rodríguez,et al.  A Recurrent Neural Network that Learns to Count , 1999, Connect. Sci..

[29]  Alex B. McBratney,et al.  Simultaneous estimation of several soil properties by ultra-violet, visible, and near-infrared reflectance spectroscopy , 2003 .

[30]  Edwin Sybingco,et al.  Determination of soil nutrients and pH level using image processing and artificial neural network , 2017, 2017IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM).

[31]  Md. Tanvir Hossain,et al.  Short-Term Financial Time Series Forecasting Integrating Principal Component Analysis and Independent Component Analysis with Support Vector Regression , 2018 .

[32]  James B. Reeves,et al.  Near Infrared Reflectance Spectroscopy for the Analysis of Agricultural Soils , 1999 .

[33]  Van Camp Godelieve,et al.  Reports of the Technical Working Groups Established under the Thematic Strategy for Soil Protection.Vol. V: Monitoring. , 2004 .

[34]  Luca Montanarella,et al.  Combining Soil Databases for Topsoil Organic Carbon Mapping in Europe , 2016, PloS one.

[35]  Suresh Kumar,et al.  Prediction Modeling and Mapping of Soil Carbon Content Using Artificial Neural Network, Hyperspectral Satellite Data and Field Spectroscopy , 2015 .

[36]  Douglas L. Karlen,et al.  A conceptual framework for assessment and management of soil quality and health. , 1996 .

[37]  Kacem Chehdi,et al.  Regional prediction of soil organic carbon content over temperate croplands using visible near-infrared airborne hyperspectral imagery and synchronous field spectra , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[38]  Benjamin L. Turner,et al.  Phosphorus-31 nuclear magnetic resonance spectral assignments of phosphorus compounds in soil NaOH–EDTA extracts , 2003 .

[39]  Jing-jing Wang,et al.  A PCA-LSTM Model for Stock Index Prediction , 2018 .

[40]  G. McCarty,et al.  Mid-Infrared and Near-Infrared Diffuse Reflectance Spectroscopy for Soil Carbon Measurement , 2002 .

[41]  K. Shepherd,et al.  Development of Reflectance Spectral Libraries for Characterization of Soil Properties , 2002 .

[42]  Gang Wang,et al.  Spectral-spatial classification of hyperspectral image using autoencoders , 2013, 2013 9th International Conference on Information, Communications & Signal Processing.

[43]  Jon Atli Benediktsson,et al.  Exploiting spectral and spatial information in hyperspectral urban data with high resolution , 2004, IEEE Geoscience and Remote Sensing Letters.

[44]  Manfred F. Buchroithner,et al.  Quantitative Retrieval of Organic Soil Properties from Visible Near-Infrared Shortwave Infrared (Vis-NIR-SWIR) Spectroscopy Using Fractal-Based Feature Extraction , 2016, Remote. Sens..

[45]  R. V. Rossel,et al.  Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties , 2006 .

[46]  L. Montanarella,et al.  A map of the topsoil organic carbon content of Europe generated by a generalized additive model , 2015 .

[47]  Graham W. Taylor,et al.  Deep Learning Architectures for Soil Property Prediction , 2015, 2015 12th Conference on Computer and Robot Vision.

[48]  Arwyn Jones,et al.  The LUCAS topsoil database and derived information on the regional variability of cropland topsoil properties in the European Union , 2013, Environmental Monitoring and Assessment.

[49]  Luca Montanarella,et al.  Prediction of Soil Organic Carbon at the European Scale by Visible and Near InfraRed Reflectance Spectroscopy , 2013, PloS one.

[50]  Qingshan Liu,et al.  Cascaded Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Budiman Minasny,et al.  Using deep learning for digital soil mapping , 2018, SOIL.

[52]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[53]  H. Condit,et al.  Application of characteristic vector analysis to the spectral energy distribution of daylight and the spectral reflectance of american soils. , 1972, Applied optics.

[54]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[55]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[56]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.