Machine-Learning Approach Using SAR Data for the Classification of Oil Palm Trees That Are Non-Infected and Infected with the Basal Stem Rot Disease

Basal stem rot disease (BSR) in oil palm plants is caused by the Ganoderma boninense (G. boninense) fungus. BSR is a major disease that affects oil palm plantations in Malaysia and Indonesia. As of now, the only available sustaining measure is to prolong the life of oil palm trees since there has been no effective treatment for the BSR disease. This project used an ALOS PALSAR-2 image with dual polarization, Horizontal transmit and Horizontal receive (HH) and Horizontal transmit and Vertical receive (HV). The aims of this study were to (1) identify the potential backscatter variables; and (2) examine the performance of machine learning (ML) classifiers (Multilayer Perceptron (MLP) and Random Forest (RF) to classify oil palm trees that are non-infected and infected by G. boninense. The sample size consisted of 55 uninfected trees and 37 infected trees. We used the imbalance data approach (Synthetic Minority Over-Sampling Technique (SMOTE) in these classifications due to the differing sample sizes. The result showed backscatter variable HV had a higher correct classification for the G. boninense non-infected and infected oil palm trees for both classifiers; the MLP classifier model had a robust success rate, which correctly classified 100% for non-infected and 91.30% for infected G. boninense, and RF had a robust success rate, which correctly classified 94.11% for non-infected and 91.30% for infected G. boninense. In terms of model performance using the most significant variables, HV, the MLP model had a balanced accuracy (BCR) of 95.65% compared to 92.70% for the RF model. Comparison between the MLP model and RF model for the receiver operating characteristics (ROC) curve region, (AUC) gave a value of 0.92 and 0.95, respectively, for the MLP and RF models. Therefore, it can be concluded by using only the HV polarization, that both the MLP and RF can be used to predict BSR disease with a relatively high accuracy.

[1]  Jong-Sen Lee,et al.  Digital Image Enhancement and Noise Filtering by Use of Local Statistics , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  H. Shafri,et al.  Hyperspectral imagery for mapping disease infection in oil palm plantation using vegetation indices and red edge techniques. , 2009 .

[3]  M. Chakraborty,et al.  Rice crop parameter retrieval using multi-temporal, multi-incidence angle Radarsat SAR data , 2005 .

[4]  Sushma Panigrahy,et al.  Comparative evaluation of the sensitivity of multi‐polarized multi‐frequency SAR backscatter to plant density , 2006 .

[5]  Yunqian Ma,et al.  Imbalanced Datasets: From Sampling to Classifiers , 2013 .

[6]  Ian H. Witten,et al.  Weka-A Machine Learning Workbench for Data Mining , 2005, Data Mining and Knowledge Discovery Handbook.

[7]  C. Mohammed,et al.  Management of basidiomycete root‐ and stem‐rot diseases in oil palm, rubber and tropical hardwood plantation crops , 2014 .

[8]  Urszula Stańczyk,et al.  Rough Set and Artificial Neural Network Approach to Computational Stylistics , 2013 .

[9]  Hiroshi Tani,et al.  Random Forest classification model of basal stem rot disease caused by Ganoderma boninense in oil palm plantations , 2017 .

[10]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[11]  Hari Shanker Srivastava,et al.  Application potentials of synthetic aperture radar interferometry for land-cover mapping and crop-height estimation , 2006 .

[12]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[13]  Guoqing Sun,et al.  Sensitivity of multi-source SAR backscatter to changes of forest aboveground biomass , 2013, 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS.

[14]  Moses Azong Cho,et al.  Mapping tree species composition in South African savannas using an integrated airborne spectral and LiDAR system , 2012 .

[15]  Ellen Poliakoff,et al.  Machine learning algorithm validation with a limited sample size , 2019, PloS one.

[16]  Weimin Huang,et al.  Speckle filtering of Synthetic Aperture Radar images using filters with object-size-adapted windows , 2018, Int. J. Digit. Earth.

[17]  M. S. Moran,et al.  Opportunities and limitations for image-based remote sensing in precision crop management , 1997 .

[18]  Alexander A. Sawchuk,et al.  Adaptive Noise Smoothing Filter for Images with Signal-Dependent Noise , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Jean-Michel Roger,et al.  Evaluation of Oil-Palm Fungal Disease Infestation with Canopy Hyperspectral Reflectance Data , 2010, Sensors.

[20]  H. Sadighi,et al.  Assessing Farmers' Sustainable Agricultural Practice Needs: The Case of Corn Growers in Fars, Iran , 2010 .

[21]  Said Nawar,et al.  Comparison between Random Forests, Artificial Neural Networks and Gradient Boosted Machines Methods of On-Line Vis-NIR Spectroscopy Measurements of Soil Total Nitrogen and Total Carbon , 2017, Sensors.

[22]  Jianhua Yan,et al.  Comparison of ANN (MLP), ANFIS, SVM, and RF models for the online classification of heating value of burning municipal solid waste in circulating fluidized bed incinerators. , 2017, Waste management.

[23]  Xiaojun Yang,et al.  Improving Land Use/Cover Classification with a Multiple Classifier System Using AdaBoost Integration Technique , 2017, Remote. Sens..

[24]  Victor S. Frost,et al.  A Model for Radar Images and Its Application to Adaptive Digital Filtering of Multiplicative Noise , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[26]  Helmi Zulhaidi Mohd Shafri,et al.  Spectral discrimination of healthy and Ganoderma-infected oil palms from hyperspectral data , 2011 .

[27]  Qiusheng Wu,et al.  Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory , 2018, Remote. Sens..

[28]  Weifeng Li,et al.  Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery , 2014, Remote. Sens..

[29]  A. Susanto,et al.  Utilization of Fungi for the Biological Control of Insect Pests and Ganoderma Disease in the Indonesian Oil Palm Industry , 2014 .

[30]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[31]  Yichun Xie,et al.  Remote sensing imagery in vegetation mapping: a review , 2008 .

[32]  Manabu Watanabe,et al.  ALOS PALSAR: A Pathfinder Mission for Global-Scale Monitoring of the Environment , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Mansour Ebrahimi,et al.  Determining the Most Important Physiological and Agronomic Traits Contributing to Maize Grain Yield through Machine Learning Algorithms: A New Avenue in Intelligent Agriculture , 2014, PloS one.

[34]  Andrea Castelletti,et al.  Robustness Metrics: How Are They Calculated, When Should They Be Used and Why Do They Give Different Results? , 2018 .

[35]  Nikos E. Mastorakis,et al.  Multilayer perceptron and neural networks , 2009 .

[36]  Firouz Abdullah Al-Wassai,et al.  Image Fusion Technologies In Commercial Remote Sensing Packages , 2013, ArXiv.

[37]  Clement Atzberger,et al.  Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data , 2012, Remote. Sens..

[38]  José Claudio Mura,et al.  Simulated multipolarized MAPSAR images to distinguish agricultural crops , 2012 .

[39]  Michele Dalponte,et al.  Predicting stem diameters and aboveground biomass of individual trees using remote sensing data , 2018 .

[40]  B. Pradhan,et al.  Geospatial technologies for detection and monitoring of Ganoderma basal stem rot infection in oil palm plantations: a review on sensors and techniques , 2018 .

[41]  Hau-Wei Lee,et al.  A Review of Artificial Intelligence Algorithms Used for Smart Machine Tools , 2018, Inventions.

[42]  Xue Ying,et al.  An Overview of Overfitting and its Solutions , 2019, Journal of Physics: Conference Series.

[43]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[44]  L. Plümer,et al.  Original paper: Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance , 2010 .

[45]  Wenjiang Huang,et al.  Integrating Growth and Environmental Parameters to Discriminate Powdery Mildew and Aphid of Winter Wheat Using Bi-Temporal Landsat-8 Imagery , 2019, Remote. Sens..

[46]  B. Brisco,et al.  Rice monitoring and production estimation using multitemporal RADARSAT , 2001 .

[47]  D. Ahmad,et al.  Classification of Basal Stem Rot Disease in Oil Palm Plantations Using Terrestrial Laser Scanning Data and Machine Learning , 2020 .

[48]  Reza Ehsani,et al.  Early detection of basal stem rot disease (Ganoderma) in oil palms based on hyperspectral reflectance data using pattern recognition algorithms , 2014 .

[49]  Nor Azah Yusof,et al.  Detection and control of Ganoderma boninense: strategies and perspectives , 2013, SpringerPlus.

[50]  Saso Dzeroski,et al.  Estimating vegetation height and canopy cover from remotely sensed data with machine learning , 2010, Ecol. Informatics.

[51]  Matthew L. Clark,et al.  One-Dimensional Convolutional Neural Network Land-Cover Classification of Multi-Seasonal Hyperspectral Imagery in the San Francisco Bay Area, California , 2017, Remote. Sens..

[53]  Zhongxin Chen,et al.  Advances in research on crop identification using SAR , 2015, 2015 Fourth International Conference on Agro-Geoinformatics (Agro-geoinformatics).

[54]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[55]  Juan M. Lopez-Sanchez,et al.  Rice Phenology Monitoring by Means of SAR Polarimetry at X-Band , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[56]  Baharin Bin Ahmad,et al.  Potential of texture measurements of two-date dual polarization PALSAR data for the improvement of forest biomass estimation , 2012 .

[57]  Samsuzana Abd Aziz,et al.  Early detection of diseases in plant tissue using spectroscopy – applications and limitations , 2018 .

[58]  Fahad Najeeb,et al.  A comparative analysis of machine learning approaches for plant disease identification , 2017 .

[59]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[60]  B. Minasny,et al.  Mapping and identifying basal stem rot disease in oil palms in North Sumatra with QuickBird imagery , 2011, Precision Agriculture.

[61]  Jungho Im,et al.  Machine Learning Approaches for Estimating Forest Stand Height Using Plot-Based Observations and Airborne LiDAR Data , 2018 .

[62]  Consuelo Gonzalo-Martín,et al.  A random forest and superpixels approach to sharpen thermal infrared satellite imagery , 2017, Remote Sensing.

[63]  Fadi Thabtah,et al.  Data imbalance in classification: Experimental evaluation , 2020, Inf. Sci..