Mapping sugarcane in complex landscapes by integrating multi-temporal Sentinel-2 images and machine learning algorithms

Sugarcane is an important type of cash crop and plays a crucial role in global sugar production. Clarifying the magnitude of sugarcane planting will likely provide very evident supports for local land use management and policy-making. However, sugarcane growth environment in complex landscapes with frequent rainy weather conditions poses many challenges for its rapid mapping. This study thus tried and used 10-m Sentinel-2 images as well as crop phenology information to map sugarcane in Longzhou county of China in 2018. To minimize the influences of cloudy and rainy conditions, this study firstly fused all available images in each phenology stage to obtain cloud-free remote sensing images of three phenology stage (seedling, elongation and harvest) with the help of Google Earth Engine platform. Then, the study used the fused images to compute the normalized difference vegetation index (NDVI) of each stage. A three-band NDVI dataset along with 4000 training samples and 2000 random validation samples was finally used for sugarcane mapping. To assess the robustness of the three-band NDVI dataset with phenological characteristics for sugarcane mapping, this study employed five classifiers based on machine learning algorithms, including two support vector machine classifiers (Polynomial-SVM and RBF-SVM), a random forest classifier (RF), an artificial neural network classifier (ANN) and a decision tree classifier (CART-DT). Results showed that except for ANN classifier, Polynomial-SVM, RBF-SVM, RF and CART-DT classifiers displayed high accuracy sugarcane resultant maps with producer’s and user’s accuracies of greater than 91%. The ANN classifier tended to overestimate area of sugarcane and underestimate area of forests. Overall performances of five classifiers suggest Polynomial-SVM has the best potential to improve sugarcane mapping at the regional scale. Also, this study observed that most sugarcane (more than 75% of entire study area) tends to grow in flat regions with slope of less than 10°. This study emphasizes the importance of considering phenology in rapid sugarcane mapping, and suggests the potential of fine-resolution Sentinel-2 images and machine learning approaches in high-accuracy land use management and decision-making.

[1]  S. Dech,et al.  Comparison and enhancement of MODIS cloud mask products for Southeast Asia , 2013 .

[2]  Yan-sui Liu,et al.  Revitalize the world’s countryside , 2017, Nature.

[3]  Bo Yu,et al.  Analysis of satellite-derived landslide at Central Nepal from 2011 to 2016 , 2018, Environmental Earth Sciences.

[4]  Jo Dewulf,et al.  Comparative Life Cycle Assessment of four alternatives for using by-products of cane sugar production. , 2009 .

[5]  Yansui Liu,et al.  Spatio-temporal change of urban–rural equalized development patterns in China and its driving factors , 2013 .

[6]  Yan-sui Liu,et al.  Targeted poverty alleviation and land policy innovation: Some practice and policy implications from China , 2018 .

[7]  Christopher Conrad,et al.  Optimising Phenological Metrics Extraction for Different Crop Types in Germany Using the Moderate Resolution Imaging Spectrometer (MODIS) , 2017, Remote. Sens..

[8]  Claire Marais-Sicre,et al.  Land Cover and Crop Type Classification along the Season Based on Biophysical Variables Retrieved from Multi-Sensor High-Resolution Time Series , 2015, Remote. Sens..

[9]  Clement Atzberger,et al.  Object Based Image Analysis and Data Mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas , 2012 .

[10]  Bo Huang,et al.  Using satellite data to estimate particulate air quality in a subtropical city: an evaluation of accuracy and sampling issues , 2015 .

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  Yan-sui Liu.  Introduction to land use and rural sustainability in China , 2018 .

[13]  B. Brisco,et al.  Precision Agriculture and the Role of Remote Sensing: A Review , 1998 .

[14]  Na Zhao,et al.  Mapping of Urban Surface Water Bodies from Sentinel-2 MSI Imagery at 10 m Resolution via NDWI-Based Image Sharpening , 2017, Remote. Sens..

[15]  Peter M. Atkinson,et al.  Mapping paddy rice fields by applying machine learning algorithms to multi-temporal Sentinel-1A and Landsat data , 2018 .

[16]  Liu Yansui,et al.  Rocky land desertification and its driving forces in the karst areas of rural Guangxi, Southwest China , 2008 .

[17]  S. Panigrahy,et al.  Influence of Atmospheric Water Vapour on IRS NIR Measurements for Detecting Vegetation Signal. Part I: A Simulation Study Using MODTRAN , 2012, Journal of the Indian Society of Remote Sensing.

[18]  Bo Li,et al.  Tracking annual changes of coastal tidal flats in China during 1986-2016 through analyses of Landsat images with Google Earth Engine. , 2020, Remote sensing of environment.

[19]  Yansui Liu,et al.  Anthropogenic contributions dominate trends of vegetation cover change over the farming-pastoral ecotone of northern China , 2018, Ecological Indicators.

[20]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

[21]  Tung Fung,et al.  Combining EO-1 Hyperion and Envisat ASAR data for mangrove species classification in Mai Po Ramsar Site, Hong Kong , 2014 .

[22]  A. Huete,et al.  A feedback based modification of the NDVI to minimize canopy background and atmospheric noise , 1995 .

[23]  R. Pu,et al.  A comparative analysis of high spatial resolution IKONOS and WorldView-2 imagery for mapping urban tree species , 2012 .

[24]  Yan-sui Liu,et al.  The allocation and management of critical resources in rural China under restructuring: Problems and prospects , 2016 .

[25]  Grazia Zulian,et al.  Mapping ecosystem service capacity, flow and demand for landscape and urban planning: a case study in the Barcelona metropolitan region , 2016 .

[26]  Changsheng Li,et al.  Mapping paddy rice agriculture in South and Southeast Asia using multi-temporal MODIS images , 2006 .

[27]  Chongcheng Chen,et al.  Automatic and adaptive paddy rice mapping using Landsat images: Case study in Songnen Plain in Northeast China. , 2017, The Science of the total environment.

[28]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[29]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[30]  Lorenzo Bruzzone,et al.  A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

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

[32]  T. Kuemmerle,et al.  Mapping and modelling past and future land use change in Europe’s cultural landscapes , 2019, Land Use Policy.

[33]  Raghavan Srinivasan,et al.  Using Satellite and Field Data with Crop Growth Modeling to Monitor and Estimate Corn Yield in Mexico , 2002 .

[34]  Liangpei Zhang,et al.  An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

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

[36]  M. Herold,et al.  Improving near-real time deforestation monitoring in tropical dry forests by combining dense Sentinel-1 time series with Landsat and ALOS-2 PALSAR-2 , 2018 .

[37]  Edwin W. Pak,et al.  An extended AVHRR 8‐km NDVI dataset compatible with MODIS and SPOT vegetation NDVI data , 2005 .

[38]  Yan-sui Liu,et al.  Strategic adjustment of land use policy under the economic transformation , 2018 .

[39]  Yan-sui Liu,et al.  Key issues of land use in China and implications for policy making , 2014 .

[40]  Zhengjia Liu,et al.  Detecting Changes of Wheat Vegetative Growth and Their Response to Climate Change Over the North China Plain , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[41]  Vanete Thomaz Soccol,et al.  Biotechnological potential of agro-industrial residues. I: sugarcane bagasse , 2000 .

[42]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[43]  Giorgos Mountrakis,et al.  Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites , 2018 .

[44]  Laurence Hubert-Moy,et al.  Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities , 2019, Remote Sensing of Environment.

[45]  Huifang Li,et al.  An effective thin cloud removal procedure for visible remote sensing images , 2014 .

[46]  Yi Liang,et al.  A New Technique for Remote Sensing Image Classification Based on Combinatorial Algorithm of SVM and KNN , 2017, Int. J. Pattern Recognit. Artif. Intell..

[47]  Y. Shimabukuro,et al.  Forest dynamics and land-use transitions in the Brazilian Atlantic Forest: the case of sugarcane expansion , 2015, Regional Environmental Change.

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

[49]  Yan-sui Liu,et al.  Land consolidation boosting poverty alleviation in China: Theory and practice , 2019, Land Use Policy.

[50]  Yansui Liu,et al.  Towards realistic assessment of cultivated land quality in an ecologically fragile environment: A satellite imagery-based approach , 2010 .

[51]  Yong Zha,et al.  Assessment of grassland degradation near Lake Qinghai, West China, using Landsat TM and in situ reflectance spectra data , 2004 .

[52]  Liping Di,et al.  Object-Based Plastic-Mulched Landcover Extraction Using Integrated Sentinel-1 and Sentinel-2 Data , 2018, Remote. Sens..

[53]  Wei Wu,et al.  A comparison of support vector machines, artificial neural network and classification tree for identifying soil texture classes in southwest China , 2018, Comput. Electron. Agric..

[54]  Ioannis Papoutsis,et al.  Scalable Parcel-Based Crop Identification Scheme Using Sentinel-2 Data Time-Series for the Monitoring of the Common Agricultural Policy , 2018, Remote. Sens..

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

[56]  Tao Zhou,et al.  Mapping Winter Wheat with Multi-Temporal SAR and Optical Images in an Urban Agricultural Region , 2017, Sensors.

[57]  Bogdan Zagajewski,et al.  Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images , 2017 .

[58]  Yang‐Rui Li,et al.  Sugarcane Agriculture and Sugar Industry in China , 2014, Sugar Tech.

[59]  Yan-sui Liu,et al.  Land consolidation for rural sustainability in China: Practical reflections and policy implications , 2018 .

[60]  Wolfram Mauser,et al.  Inversion of a canopy reflectance model using hyperspectral imagery for monitoring wheat growth and estimating yield , 2009, Precision Agriculture.

[61]  S. Gopal,et al.  Remote sensing of forest change using artificial neural networks , 1996, IEEE Trans. Geosci. Remote. Sens..

[62]  Cullen Schaffer.  Overfitting avoidance as bias , 2004, Machine Learning.

[63]  Agnès Bégué,et al.  Forecasting Regional Sugarcane Yield Based on Time Integral and Spatial Aggregation of MODIS NDVI , 2013, Remote. Sens..

[64]  Mingxing Chen,et al.  Challenges and the way forward in China’s new-type urbanization , 2016 .

[65]  George P. Petropoulos,et al.  A new synergistic approach for monitoring wetlands using Sentinels -1 and 2 data with object-based machine learning algorithms , 2018, Environ. Model. Softw..

[66]  Jeffrey P. Walker,et al.  Towards operational SAR-based flood mapping using neuro-fuzzy texture-based approaches , 2018, Remote Sensing of Environment.

[67]  R. Halvorsen,et al.  Methods for landscape characterisation and mapping: A systematic review , 2018, Land Use Policy.

[68]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[69]  Xiuping Jia,et al.  Comparing six pixel-wise classifiers for tropical rural land cover mapping using four forms of fully polarimetric SAR data , 2017 .

[70]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

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

[72]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.