Improving the mapping of crop types in the Midwestern U.S. by fusing Landsat and MODIS satellite data

Abstract Mapping crop types is of great importance for assessing agricultural production, land-use patterns, and the environmental effects of agriculture. Indeed, both radiometric and spatial resolution of Landsat’s sensors images are optimized for cropland monitoring. However, accurate mapping of crop types requires frequent cloud-free images during the growing season, which are often not available, and this raises the question of whether Landsat data can be combined with data from other satellites. Here, our goal is to evaluate to what degree fusing Landsat with MODIS Nadir Bidirectional Reflectance Distribution Function (BRDF)-Adjusted Reflectance (NBAR) data can improve crop-type classification. Choosing either one or two images from all cloud-free Landsat observations available for the Arlington Agricultural Research Station area in Wisconsin from 2010 to 2014, we generated 87 combinations of images, and used each combination as input into the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) algorithm to predict Landsat-like images at the nominal dates of each 8-day MODIS NBAR product. Both the original Landsat and STARFM-predicted images were then classified with a support vector machine (SVM), and we compared the classification errors of three scenarios: 1) classifying the one or two original Landsat images of each combination only, 2) classifying the one or two original Landsat images plus all STARFM-predicted images, and 3) classifying the one or two original Landsat images together with STARFM-predicted images for key dates. Our results indicated that using two Landsat images as the input of STARFM did not significantly improve the STARFM predictions compared to using only one, and predictions using Landsat images between July and August as input were most accurate. Including all STARFM-predicted images together with the Landsat images significantly increased average classification error by 4% points (from 21% to 25%) compared to using only Landsat images. However, incorporating only STARFM-predicted images for key dates decreased average classification error by 2% points (from 21% to 19%) compared to using only Landsat images. In particular, if only a single Landsat image was available, adding STARFM predictions for key dates significantly decreased the average classification error by 4 percentage points from 30% to 26% (p

[1]  V. Radeloff,et al.  Author's Personal Copy Mapping Abandoned Agriculture with Multi-temporal Modis Satellite Data , 2022 .

[2]  R. DeFries,et al.  Land‐use choices: balancing human needs and ecosystem function , 2004 .

[3]  B. Wardlow,et al.  Analysis of time-series MODIS 250 m vegetation index data for crop classification in the U.S. Central Great Plains , 2007 .

[4]  Michael A. Lefsky,et al.  A flexible spatiotemporal method for fusing satellite images with different resolutions , 2016 .

[5]  J. Townshend,et al.  Carbon emissions from tropical deforestation and regrowth based on satellite observations for the 1980s and 1990s , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Zhengwei Yang,et al.  CropScape: A Web service based application for exploring and disseminating US conterminous geospatial cropland data products for decision support , 2012 .

[7]  Feng Gao,et al.  A simple and effective method for filling gaps in Landsat ETM+ SLC-off images , 2011 .

[8]  P. Hostert,et al.  Mapping farmland abandonment and recultivation across Europe using MODIS NDVI time series. , 2015 .

[9]  Volker C. Radeloff,et al.  The effect of Landsat ETM/ETM + image acquisition dates on the detection of agricultural land abandonment in Eastern Europe , 2012 .

[10]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

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

[12]  Mathew R. Schwaller,et al.  On the blending of the Landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Thomas Hilker,et al.  Improved classification of conservation tillage adoption using high temporal and synthetic satellite imagery , 2011 .

[14]  Cornelius Senf,et al.  Mapping land cover in complex Mediterranean landscapes using Landsat: Improved classification accuracies from integrating multi-seasonal and synthetic imagery , 2015 .

[15]  Tim R. McVicar,et al.  Assessing the accuracy of blending Landsat–MODIS surface reflectances in two landscapes with contrasting spatial and temporal dynamics: A framework for algorithm selection , 2013 .

[16]  N. Ramankutty,et al.  Farming the planet: 1. Geographic distribution of global agricultural lands in the year 2000 , 2008 .

[17]  F. Javier García-Haro,et al.  A comparison of STARFM and an unmixing-based algorithm for Landsat and MODIS data fusion , 2015 .

[18]  Michael E. Schaepman,et al.  Sentinels for science: potential of Sentinel-1, -2, and -3 missions for scientific observations of ocean, cryosphere, and land , 2012 .

[19]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[20]  E. Lambin,et al.  The emergence of land change science for global environmental change and sustainability , 2007, Proceedings of the National Academy of Sciences.

[21]  D. Roy,et al.  The availability of cloud-free Landsat ETM+ data over the conterminous United States and globally , 2008 .

[22]  S. Carpenter,et al.  Global Consequences of Land Use , 2005, Science.

[23]  Joanne C. White,et al.  A new data fusion model for high spatial- and temporal-resolution mapping of forest disturbance based on Landsat and MODIS , 2009 .

[24]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[25]  K. Beurs,et al.  Dryland vegetation phenology across an elevation gradient in Arizona, USA, investigated with fused MODIS and Landsat data , 2014 .

[26]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[27]  Paul M. Mather,et al.  Support vector machines for classification in remote sensing , 2005 .

[28]  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.

[29]  G. Asner,et al.  Spectral unmixing of vegetation, soil and dry carbon cover in arid regions: Comparing multispectral and hyperspectral observations , 2002 .

[30]  Tim R. McVicar,et al.  Determining temporal windows for crop discrimination with remote sensing: a case study in south-eastern Australia , 2004 .

[31]  Lenore Fahrig,et al.  Functional landscape heterogeneity and animal biodiversity in agricultural landscapes. , 2011, Ecology letters.

[32]  B. Wardlow,et al.  Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains , 2008 .

[33]  Xianhong Xie,et al.  Land cover classification of finer resolution remote sensing data integrating temporal features from time series coarser resolution data , 2014 .

[34]  Lei Zhang,et al.  Forest cover classification using Landsat ETM+ data and time series MODIS NDVI data , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[35]  Giles M. Foody,et al.  Feature Selection for Classification of Hyperspectral Data by SVM , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[36]  Xiaoxia Wang,et al.  Land Cover Classification of Landsat Data with Phenological Features Extracted from Time Series MODIS NDVI Data , 2014, Remote. Sens..

[37]  Zhengwei Yang,et al.  Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program , 2011 .

[38]  Brian G. Wolff,et al.  Forecasting Agriculturally Driven Global Environmental Change , 2001, Science.

[39]  K. Beurs,et al.  Evaluation of Landsat and MODIS data fusion products for analysis of dryland forest phenology , 2012 .

[40]  Robert E. Wolfe,et al.  A Landsat surface reflectance dataset for North America, 1990-2000 , 2006, IEEE Geoscience and Remote Sensing Letters.

[41]  N. Ramankutty,et al.  Green surprise? How terrestrial ecosystems could affect earth’s climate , 2003 .

[42]  Joanne C. White,et al.  Generation of dense time series synthetic Landsat data through data blending with MODIS using a spatial and temporal adaptive reflectance fusion model. , 2009 .

[43]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[44]  Lin Yan,et al.  Automated crop field extraction from multi-temporal Web Enabled Landsat Data , 2014 .

[45]  C. Woodcock,et al.  Resolution dependent errors in remote sensing of cultivated areas , 2006 .

[46]  Bing Zhang,et al.  Object-Based Crop Classification with Landsat-MODIS Enhanced Time-Series Data , 2015, Remote. Sens..

[47]  W. Parton,et al.  Agricultural intensification and ecosystem properties. , 1997, Science.

[48]  P. Gong,et al.  Efficient corn and soybean mapping with temporal extendability: A multi-year experiment using Landsat imagery , 2014 .

[49]  D. Roy,et al.  Multi-temporal MODIS-Landsat data fusion for relative radiometric normalization, gap filling, and prediction of Landsat data , 2008 .

[50]  Wei Zhang,et al.  An Enhanced Spatial and Temporal Data Fusion Model for Fusing Landsat and MODIS Surface Reflectance to Generate High Temporal Landsat-Like Data , 2013, Remote. Sens..

[51]  Abdollah A. Jarihani,et al.  Blending Landsat and MODIS Data to Generate Multispectral Indices: A Comparison of "Index-then-Blend" and "Blend-then-Index" Approaches , 2014, Remote. Sens..