Pre-harvest classification of crop types using a Sentinel-2 time-series and machine learning

Abstract Timely crop type information (preferably before harvest) is useful for predicting food surpluses or shortages. This study assesses the performance of several machine learning classifiers, namely SVM (support vector machine), DT (decision tree), k-NN (k-nearest neighbour), RF (random forest) and ML (maximum likelihood) for crop type mapping based on a series of Sentinel-2 images. Four experiments with different combinations of image sets were carried out. The first three experiments were undertaken with 1) single-date (uni-temporal) images; 2) combinations of five images selected from the best performing single-date images; and 3) five images selected manually based on crop development stages. The fourth experiment involved the chronologic addition of images to assess the performance of the classifiers when only pre-harvest images are used, with the purpose of investigating how early in the season reasonable accuracies can be achieved. The experiments were carried out in two different sites in the Western Cape Province of South Africa to provide a good representation of the grain-producing areas in the region which has a Mediterranean climate. The significance of image selection on classification accuracies as well as the performance of machine learning classifiers when only pre-harvest images are used were evaluated. The classification results were analysed by comparing overall accuracies and kappa coefficients, while McNemar′s test and ANOVA (analysis of variance) were used to assess the statistical significance of the differences in accuracies among experiments. The results show that by selecting images based on individual performance, a viable alternative to selecting images based on crop developmental stages is offered, and that the classification of crops with an entire time series can be just as accurate as when they are classified with a subset of hand-selected images. We also found that good classification accuracies (77.2%) can be obtained with the use of SVM and RF as early as eight weeks before harvest. This result shows that pre-harvest images have the potential to identify crops accurately, which holds much potential for operational within-season crop type mapping.

[1]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[2]  Xiaojin Zhu,et al.  Crop Type Classification by Simultaneous Use of Satellite Images of Different Resolutions , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[3]  J. Kovacs,et al.  Object-oriented crop mapping and monitoring using multi-temporal polarimetric RADARSAT-2 data , 2014 .

[4]  Adriaan Van Niekerk,et al.  Evaluation of a rule-based compositing technique for Landsat-5 TM and Landsat-7 ETM+ images , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Claire Marais-Sicre,et al.  Improved Early Crop Type Identification By Joint Use of High Temporal Resolution SAR And Optical Image Time Series , 2016, Remote. Sens..

[6]  He You,et al.  Radar Data Processing With Applications , 2016 .

[7]  Peter Vogt,et al.  A cloud mask methodology for high resolution remote sensing data combining information from high and medium resolution optical sensors , 2011 .

[8]  Prasad S. Thenkabail,et al.  Mapping rice areas of South Asia using MODIS multitemporal data , 2011 .

[9]  Francesca Bovolo,et al.  Automatic cloud-free image generation from high-resolution multitemporal imagery , 2017 .

[10]  Alireza Soffianian,et al.  Crop type mapping in a highly fragmented and heterogeneous agricultural landscape: A case of central Iran using multi-temporal Landsat 8 imagery , 2016, Comput. Electron. Agric..

[11]  Li Wang,et al.  Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA , 2015, Remote. Sens..

[12]  Christopher Conrad,et al.  Per-Field Irrigated Crop Classification in Arid Central Asia Using SPOT and ASTER Data , 2010, Remote. Sens..

[13]  Adriaan van Niekerk,et al.  Effect of feature dimensionality on object-based land cover classification: A comparison of three classifiers , 2013 .

[14]  S. Carpenter,et al.  Solutions for a cultivated planet , 2011, Nature.

[15]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[16]  Pengyu Hao,et al.  Early-season crop mapping using improved artificial immune network (IAIN) and Sentinel data , 2018, PeerJ.

[17]  Mirijam Gaertner,et al.  Resilience of Invaded Riparian Landscapes: The Potential Role of Soil-Stored Seed Banks , 2014, Environmental Management.

[18]  Heather McNairn,et al.  Early season monitoring of corn and soybeans with TerraSAR-X and RADARSAT-2 , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Luis Alonso,et al.  Estimating chlorophyll content of crops from hyperspectral data using a normalized area over reflectance curve (NAOC) , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[20]  Christopher Conrad,et al.  Integration of Optical and Synthetic Aperture Radar Imagery for Improving Crop Mapping in Northwestern Benin, West Africa , 2014, Remote. Sens..

[21]  Soe W. Myint,et al.  A support vector machine to identify irrigated crop types using time-series Landsat NDVI data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Clement Atzberger,et al.  First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe , 2016, Remote. Sens..

[23]  Gérard Dedieu,et al.  Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical Imagery , 2015, Remote. Sens..

[24]  J. Campbell.  Introduction to remote sensing , 1987 .

[25]  Konrad Schindler,et al.  Mapping of Agricultural Crops from Single High-Resolution Multispectral Images - Data-Driven Smoothing vs. Parcel-Based Smoothing , 2015, Remote. Sens..

[26]  Douglas K. Bolton,et al.  Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics , 2013 .

[27]  Pedro Antonio Gutiérrez,et al.  Object-Based Image Classification of Summer Crops with Machine Learning Methods , 2014, Remote. Sens..

[28]  Giorgos Mallinis,et al.  A Hidden Markov Models Approach for Crop Classification: Linking Crop Phenology to Time Series of Multi-Sensor Remote Sensing Data , 2015, Remote. Sens..

[29]  M. Boschetti,et al.  Assessing in-season crop classification performance using satellite data: a test case in Northern Italy , 2016 .

[30]  M. Jurado-Expósito,et al.  Discriminating cropping systems and agro-environmental measures by remote sensing , 2008, Agronomy for Sustainable Development.

[31]  Yang Shao,et al.  Monitoring agricultural cropping patterns across the Laurentian Great Lakes Basin using MODIS-NDVI data , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[32]  Danny Lo Seen,et al.  How Reliable is the MODIS Land Cover Product for Crop Mapping Sub-Saharan Agricultural Landscapes? , 2014, Remote. Sens..

[33]  Jaco Kemp,et al.  Effect of pan-sharpening multi-temporal Landsat 8 imagery for crop type differentiation using different classification techniques , 2017, Comput. Electron. Agric..

[34]  J. Six,et al.  Object-based crop identification using multiple vegetation indices, textural features and crop phenology , 2011 .

[35]  Kenneth Grogan,et al.  A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring , 2016, Remote. Sens..

[36]  Chen Zhongxin,et al.  Crop discrimination in Northern China with double cropping systems using Fourier analysis of time-series MODIS data , 2008 .

[37]  Elizabeth M. Middleton,et al.  Selection of Hyperspectral Narrowbands (HNBs) and Composition of Hyperspectral Twoband Vegetation Indices (HVIs) for Biophysical Characterization and Discrimination of Crop Types Using Field Reflectance and Hyperion/EO-1 Data , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[38]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[39]  Alexandre Bouvet,et al.  Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications , 2017 .

[40]  Manuel Lameiras Campagnolo,et al.  Reliable Crop Identification with Satellite Imagery in the Context of Common Agriculture Policy Subsidy Control , 2015, Remote. Sens..

[41]  Xin Du,et al.  Remote sensing-based global crop monitoring: experiences with China's CropWatch system , 2014, Int. J. Digit. Earth.

[42]  Saskia Foerster,et al.  Crop type mapping using spectral-temporal profiles and phenological information , 2012 .

[43]  Xavier Blaes,et al.  Efficiency of crop identification based on optical and SAR image time series , 2005 .

[44]  Christelle Vancutsem,et al.  Mean Compositing, an alternative strategy for producing temporal syntheses. Concepts and performance assessment for SPOT VEGETATION time series , 2007 .

[45]  Neil Flood,et al.  Seasonal Composite Landsat TM/ETM+ Images Using the Medoid (a Multi-Dimensional Median) , 2013, Remote. Sens..

[46]  Deren Li,et al.  Cloud Detection for High-Resolution Satellite Imagery Using Machine Learning and Multi-Feature Fusion , 2016, Remote. Sens..

[47]  Stéphane Dupuy,et al.  A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM) , 2017, Remote. Sens..

[48]  Daphne LaDue,et al.  Strengths and Limitations of Current Radar Systems for Two Stakeholder Groups in the Southern Plains , 2010 .

[49]  Christoph Hütt,et al.  COMBINED ANALYSIS OF SENTINEL-1 AND RAPIDEYE DATA FOR IMPROVED CROP TYPE CLASSIFICATION: AN EARLY SEASON APPROACH FOR RAPESEED AND CEREALS , 2016 .