Almond cultivar identification using machine learning classifiers applied to UAV-based multispectral data

ABSTRACT In Portugal, almonds are a very important crop, due to their nutritional properties. In the northeastern part of the country, the almond sector has endured over time, with strong cultural traditions and key economic significance. In these areas, several cultivars are used. In effect, the presence of various almond cultivars implies differentiated management in irrigation, disease control, pruning system, and harvest planning. Therefore, cultivar classification is essential over large agricultural areas. Over the last decades, remote-sensing data have led to important breakthroughs in the classification of different cultivars for several crops. Nonetheless, for almonds, studies are incipient. Thus, this study aims to fill this knowledge gap and explore the classification of almond cultivars in an almond orchard. High-resolution multispectral data were acquired by an unmanned aerial vehicle (UAV). Vegetation indices (VIs) and tree structural parameters were, subsequently, estimated. To obtain an accurate cultivar identification, four machine learning classifiers, such as K-nearest neighbour (kNN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were applied and optimized through the fine-tuning process. The accuracy of machine learning classifiers was analysed. SVM and RF performed best with OAs of 76% and 74% using VIs and spectral bands (GREEN, GRVI, GN, REN, ClRE). Adding the canopy height model (CHM) improved performance, with RF and XGBoost having OAs of 88% and 84%. kNN performed worst with an OA of 73% using only VIs and spectral bands, 80% with VIs, spectral bands and CHM, and 93% with VIs, CHM, and tree crown area (TCA). The best performance was achieved by RF and XGBoost with OAs of 99% using VIs, CHM, and TCA. These results demonstrate the importance of the feature selection process. Moreover, this study reveals the feasibility of remote-sensing data and machine learning classifiers in the classification of almond cultivars.

[1]  C. Dordas,et al.  Water Stress Effects on the Morphological, Physiological Characteristics of Maize (Zea mays L.), and on Environmental Cost , 2022, Agronomy.

[2]  Alireza Pourreza,et al.  A comprehensive review of remote sensing platforms, sensors, and applications in nut crops , 2022, Comput. Electron. Agric..

[3]  C. N. Stewart,et al.  Sustainability Trait Modeling of Field-Grown Switchgrass (Panicum virgatum) Using UAV-Based Imagery , 2021, Plants.

[4]  Zhi Hong Kok,et al.  Support Vector Machine in Precision Agriculture: A review , 2021, Comput. Electron. Agric..

[5]  Preethi C,et al.  An Comprehensive Survey on Applications of Precision Agriculture in the Context of Weed Classification, Leave Disease Detection, Yield Prediction and UAV Image Analysis , 2021, Advances in Parallel Computing Technologies and Applications.

[6]  J. Gonçalves,et al.  Classification of an Intertidal Reef by Machine Learning Techniques Using UAV Based RGB and Multispectral Imagery , 2021, 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS.

[7]  A. Matese,et al.  Recent Advances in Unmanned Aerial Vehicles Forest Remote Sensing—A Systematic Review. Part II: Research Applications , 2021, Forests.

[8]  J. Rijal,et al.  Impact of climate change on navel orangeworm, a major pest of tree nuts in California. , 2020, The Science of the total environment.

[9]  Luís Pádua,et al.  Monitoring of Chestnut Trees Using Machine Learning Techniques Applied to UAV-Based Multispectral Data , 2020, Remote. Sens..

[10]  Giorgio Visani,et al.  Metrics for Multi-Class Classification: an Overview , 2020, ArXiv.

[11]  N. Guiomar,et al.  Hyperspectral Reflectance as a Basis to Discriminate Olive Varieties—A Tool for Sustainable Crop Management , 2020, Sustainability.

[12]  Eleni Vrochidou,et al.  Machine Vision Systems in Precision Agriculture for Crop Farming , 2019, J. Imaging.

[13]  Abdulhadi Shoufan,et al.  Machine Learning-Based Drone Detection and Classification: State-of-the-Art in Research , 2019, IEEE Access.

[14]  N. C. Eli-Chukwu,et al.  Applications of Artificial Intelligence in Agriculture: A Review , 2019, Engineering, Technology & Applied Science Research.

[15]  Aalap Doshi,et al.  A comprehensive review on automation in agriculture using artificial intelligence , 2019, Artificial Intelligence in Agriculture.

[16]  Alessandro Matese,et al.  Remotely Sensed Vegetation Indices to Discriminate Field-Grown Olive Cultivars , 2019, Remote. Sens..

[17]  Pasquale Daponte,et al.  A review on the use of drones for precision agriculture , 2019, IOP Conference Series: Earth and Environmental Science.

[18]  Emanuel Peres,et al.  UAV-Based Automatic Detection and Monitoring of Chestnut Trees , 2019, Remote. Sens..

[19]  J. M. Molina-Martínez,et al.  Remote Image Capture System to Improve Aerial Supervision for Precision Irrigation in Agriculture , 2019, Water.

[20]  Jon Atli Benediktsson,et al.  Multisource and Multitemporal Data Fusion in Remote Sensing , 2018, ArXiv.

[21]  Bernd Bischl,et al.  Tunability: Importance of Hyperparameters of Machine Learning Algorithms , 2018, J. Mach. Learn. Res..

[22]  Maggi Kelly,et al.  Identification of Citrus Trees from Unmanned Aerial Vehicle Imagery Using Convolutional Neural Networks , 2018, Drones.

[23]  F. Guzzetti,et al.  Visual interpretation of stereoscopic NDVI satellite images to map rainfall-induced landslides , 2018, Landslides.

[24]  Enes Ayan,et al.  Data augmentation importance for classification of skin lesions via deep learning , 2018, 2018 Electric Electronics, Computer Science, Biomedical Engineerings' Meeting (EBBT).

[25]  Hiroshi Inoue,et al.  Data Augmentation by Pairing Samples for Images Classification , 2018, ArXiv.

[26]  Antje Kirchner,et al.  Using Support Vector Machines for Survey Research , 2018 .

[27]  Fu Jiang,et al.  XGBoost Classifier for DDoS Attack Detection and Analysis in SDN-Based Cloud , 2018, 2018 IEEE International Conference on Big Data and Smart Computing (BigComp).

[28]  Maryam Dehghani,et al.  WOODLAND MAPPING AT SINGLE-TREE LEVELS USING OBJECT-ORIENTED CLASSIFICATION OF UNMANNED AERIAL VEHICLE (UAV) IMAGES , 2017 .

[29]  S. Franklin,et al.  Hierarchical land cover and vegetation classification using multispectral data acquired from an unmanned aerial vehicle , 2017 .

[30]  Afef Abdelkrim,et al.  Machine learning framework for image classification , 2016, 2017 International Conference on Information and Digital Technologies (IDT).

[31]  Joaquim J. Sousa,et al.  Very high resolution aerial data to support multi-temporal precision agriculture information management , 2017, CENTERIS/ProjMAN/HCist.

[32]  Michael A. Lefsky,et al.  Review of studies on tree species classification from remotely sensed data , 2016 .

[33]  Xiaoqiu Chen,et al.  Assessing plant senescence reflectance index-retrieved vegetation phenology and its spatiotemporal response to climate change in the Inner Mongolian Grassland , 2016, International Journal of Biometeorology.

[34]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[35]  Adrien Michez,et al.  Discrimination of Deciduous Tree Species from Time Series of Unmanned Aerial System Imagery , 2015, PloS one.

[36]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[37]  Julien Michel,et al.  Stable Mean-Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote Sensing Images , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[39]  Laurent Tits,et al.  Stem Water Potential Monitoring in Pear Orchards through WorldView-2 Multispectral Imagery , 2013, Remote. Sens..

[40]  S. Imandoust,et al.  Application of K-Nearest Neighbor (KNN) Approach for Predicting Economic Events: Theoretical Background , 2013 .

[41]  N. Lima,et al.  Mycobiota and mycotoxins of almonds and chestnuts with special reference to aflatoxins , 2012 .

[42]  N. Lima,et al.  Three new species of Aspergillus section Flavi isolated from almonds and maize in Portugal , 2012, Mycologia.

[43]  Fabio Tozeto Ramos,et al.  Multi-class classification of vegetation in natural environments using an Unmanned Aerial system , 2011, 2011 IEEE International Conference on Robotics and Automation.

[44]  Gerald Schaefer,et al.  Mean Shift and Its Application in Image Segmentation , 2011 .

[45]  Ned Horning,et al.  Random Forests : An algorithm for image classification and generation of continuous fields data sets , 2010 .

[46]  S. Alegre,et al.  Productive potential of six almond cultivars under regulated deficit irrigation , 2010 .

[47]  William Stafford Noble,et al.  Support vector machine , 2013 .

[48]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[49]  M. Oliveira,et al.  XIII GREMPA Meeting on almonds and pistachios , 2005 .

[50]  P. Martínez-Gómez,et al.  Chilling and heat requirements of almond cultivars for flowering , 2003 .

[51]  M. S. Moran,et al.  Remote Sensing for Crop Management , 2003 .

[52]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[53]  A. Haara,et al.  Tree Species Classification using Semi-automatic Delineation of Trees on Aerial Images , 2002 .

[54]  R. Savé,et al.  Differences in drought tolerance in two almond cultivars: "Lauranne" and "Masbovera" , 2001 .

[55]  A. Gitelson,et al.  Use of a green channel in remote sensing of global vegetation from EOS- MODIS , 1996 .

[56]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[57]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[58]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .