A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach
Open accessAbstract
Accurate and timely spatial classification of crop types based on remote sensing data is important for both scientific and practical purposes. Spatially explicit crop-type information can be used to estimate crop areas for a variety of monitoring and decision-making applications such as crop insurance, land rental, supply-chain logistics, and financial market forecasting. However, there is no publically available spatially explicit in-season crop-type classification information for the U.S. Corn Belt (a landscape predominated by corn and soybean). Instead, researchers and decision-makers have to wait until four to six months after harvest to have such information from the previous year. The state-of-the-art research on crop-type classification has been shifted from relying on only spectral features of single static images to combining together spectral and time-series information. While Landsat data have a desirable spatial resolution for field-level crop-type classification, the ability to extract temporal phenology information based on Landsat data remains a challenge due to low temporal revisiting frequency and inevitable cloud contamination. To address this challenge and generate accurate, cost-effective, and in-season crop-type classification, this research uses the USDA's Common Land Units (CLUs) to aggregate spectral information for each field based on a time-series Landsat image data stack to largely overcome the cloud contamination issue while exploiting a machine learning model based on Deep Neural Network (DNN) and high-performance computing for intelligent and scalable computation of classification processes. Experiments were designed to evaluate what information is most useful for training the machine learning model for crop-type classification, and how various spatial and temporal factors affect the crop-type classification performance in order to derive timely crop type information. All experiments were conducted over Champaign County located in central Illinois, and a total of 1322 Landsat multi-temporal scenes including all the six optical spectral bands spanning from 2000 to 2015 were used. Computational experiments show the inclusion of temporal phenology information and evenly distributed spatial training samples in the study domain improves classification performance. The shortwave infrared bands show notably better performance than the widely used visible and near-infrared bands for classifying corn and soybean. In comparison with USDA's Crop Data Layer (CDL), this study found a relatively high Overall Accuracy (i.e. the number of the corrected classified fields divided by the number of the total fields) of 96% for classifying corn and soybean across all CLU fields in the Champaign County from 2000 to 2015. Furthermore, our approach achieved 95% Overall Accuracy by late July of the concurrent year for classifying corn and soybean. The findings suggest the methodology presented in this paper is promising for accurate, cost-effective, and in-season classification of field-level crop types, which may be scaled up to large geographic extents such as the U.S. Corn Belt.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The method of training a DCNN based on spectral differences between images acquired by UAVs from different angles is similar to the idea of training a DNN through time series information.
“This method is similar to the idea concerning training the DNN model through time series information (Cai et al., 2018).”
From Deep learning in remote sensing applications: A meta-analysis and review (2019) · cites this paper as Cai et al., 2018
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · see citing works
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · see citing works
Red and photographic infrared linear combinations for monitoring vegetation
Tucker, C. J. (1979) · Remote Sensing of Environment · doi:10.1016/0034-4257(79)90013-0 · Cited by 11,933 · see citing works
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · see citing works
Overview of the radiometric and biophysical performance of the MODIS vegetation indices
HUETE, A. R., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., & Ferreira, L. G. (2002) · Remote Sensing of Environment · doi:10.1016/s0034-4257(02)00096-2 · Cited by 9,954 · see citing works
Proceedings of the 25th international conference on Machine learning - ICML '08
(2008) · doi:10.1145/1390156 · Cited by 6,865 · see citing works
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · see citing works
Landsat-8: Science and product vision for terrestrial global change research
Roy, D. P., Wulder, M. A., Loveland, T. R., Woodcock, C. E., Allen, R. G., Anderson, M. C., Helder, D. L., Irons, J. R., Johnson, D. M., Kennedy, R. E., et al. (2014) · Remote Sensing of Environment · doi:10.1016/j.rse.2014.02.001 · Cited by 2,723 · see citing works
Global land cover classification at 1 km spatial resolution using a classification tree approach
Hansen, M. C., DeFries, R., Townshend, J. R. G., & Sohlberg, R. A. (2000) · International Journal of Remote Sensing · doi:10.1080/014311600210209 · Cited by 2,284 · see citing works
Gao, F., Masek, J. G., Schwaller, M. R., et al. (2006) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2006.872081 · Cited by 1,990 · see citing works
Development of a 2001 National Land-Cover Database for the United States
Homer, C. G., Huang, C., Yang, L., Wylie, B. K., & Coan, M. J. (2004) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.70.7.829 · Cited by 1,567 · see citing works
Seasonality extraction by function fitting to time-series of satellite sensor data
Jönsson, P., & Eklundh, L. (2002) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2002.802519 · Cited by 1,292 · see citing works
Boryan, C., Yang, Z., Mueller, R., & Craig, M. (2011) · Geocarto International · doi:10.1080/10106049.2011.562309 · Cited by 1,212 · see citing works
Yuan, F., Sawaya, K. E., Loeffelholz, B. C., & Bauer, M. E. (2005) · Remote Sensing of Environment · doi:10.1016/j.rse.2005.08.006 · Cited by 1,147 · see citing works
Vogelmann, J. E., Howard, S. M., Yang, L., Larson, C. R., Wylie, B. K., & Driel, J. N. V. (2001) · Photogrammetric Engineering & Remote Sensing · Cited by 1,120 · see citing works
A review of large area monitoring of land cover change using Landsat data
Hansen, M. C., & Loveland, T. R. (2012) · Remote Sensing of Environment · doi:10.1016/j.rse.2011.08.024 · Cited by 1,061 · see citing works
Duro, D. C., Franklin, S. E., & Dubé, M. G. (2011) · Remote Sensing of Environment · doi:10.1016/j.rse.2011.11.020 · Cited by 998 · see citing works
LIU, J., Liu, M., Tian, H., Zhuang, D., Zhang, Z., Zhang, W. Y., Tang, X., & DENG, X. (2005) · Remote Sensing of Environment · doi:10.1016/j.rse.2005.08.012 · Cited by 976 · see citing works
Sellers, P. J., Berry, J. A., Collatz, G. J., Field, C. B., & HALL, F. G. (1992) · Remote Sensing of Environment · doi:10.1016/0034-4257(92)90102-p · Cited by 942 · see citing works
Remote estimation of leaf area index and green leaf biomass in maize canopies
Gitelson, A. A., Viña, A., Arkebauer, T. J., et al. (2003) · Geophysical Research Letters · doi:10.1029/2002gl016450 · Cited by 902 · see citing works
Wardlow, B. D., Egbert, S. L., & Kastens, J. H. (2007) · Remote Sensing of Environment · doi:10.1016/j.rse.2006.11.021 · Cited by 888 · see citing works
Self-citationSexton, J. O., Song, X.-P., Feng, M., Noojipady, P., Anand, A., Huang, C., Kim, D.-H., Collins, K. M., Channan, S., DiMiceli, C., et al. (2013) · International Journal of Digital Earth · doi:10.1080/17538947.2013.786146 · Cited by 829 · see citing works
Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics
Bolton, D. K., & Friedl, M. A. (2013) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2013.01.007 · Cited by 800 · see citing works
Mapping paddy rice agriculture in South and Southeast Asia using multi-temporal MODIS images
Xiao, X., Boles, S. H., Frolking, S., Li, C., Babu, J. Y., Salas, W., & Moore, B. (2005) · Remote Sensing of Environment · doi:10.1016/j.rse.2005.10.004 · Cited by 780 · see citing works
Wardlow, B. D., & Egbert, S. L. (2007) · Remote Sensing of Environment · doi:10.1016/j.rse.2007.07.019 · Cited by 771 · see citing works
Self-citationA scalable satellite-based crop yield mapper
Lobell, D. B., Thau, D., Seifert, C. A., Engle, E., & Little, B. B. (2015) · Remote Sensing of Environment · doi:10.1016/j.rse.2015.04.021 · Cited by 618 · see citing works
Self-citationDeep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data
You, J., Li, X., Low, M., Lobell, D. B., & Ermon, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11172 · Cited by 603 · see citing works
Toward mapping crop progress at field scales through fusion of Landsat and MODIS imagery
Feng Gao, A., Anderson, M. C., Xiaoyang Zhang, A., Yang, Z., Alfieri, J. G., Kustas, W. P., Mueller, R., Johnson, D. M., & Prueger, J. H. (2016) · Remote Sensing of Environment · doi:10.1016/j.rse.2016.11.004 · Cited by 496 · see citing works
The use of satellite data for crop yield gap analysis
Lobell, D. B. (2012) · Field Crops Research · doi:10.1016/j.fcr.2012.08.008 · Cited by 396 · see citing works
Xiao, X., Boles, S. H., Liu, J., Zhuang, D., & Liu, M. (2002) · Remote Sensing of Environment · doi:10.1016/s0034-4257(02)00051-2 · Cited by 355 · see citing works
TOWNSHEND, J. R. G., Masek, J. G., Huang, C., Vermote, E. F., Feng Gao, A., Channan, S., Sexton, J., Feng, M., Narasimhan, R., Kim, D., et al. (2012) · International Journal of Digital Earth · doi:10.1080/17538947.2012.713190 · Cited by 324 · see citing works
Cropland distributions from temporal unmixing of MODIS data
Lobell, D. B., & Asner, G. P. (2004) · Remote Sensing of Environment · doi:10.1016/j.rse.2004.08.002 · Cited by 311 · see citing works
Detection of land cover changes using MODIS 250 m data
Zhan, X., Sohlberg, R. A., Townshend, J. R. G., DiMiceli, C., Carroll, M., EASTMAN, J. C., Hansen, M. C., & DeFries, R. (2002) · Remote Sensing of Environment · doi:10.1016/s0034-4257(02)00081-0 · Cited by 305 · see citing works
Li, P., Jiang, L., & Feng, Z. (2013) · Remote Sensing · doi:10.3390/rs6010310 · Cited by 296 · see citing works
Fusing Landsat and MODIS Data for Vegetation Monitoring
Feng Gao, A., Hilker, T., Zhu, X., Anderson, M. C., Masek, J. G., Wang, P., & Yang, Y. (2015) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2015.2434351 · Cited by 289 · see citing works
Song, X., Potapov, P. V., Krylov, A., King, L., Bella, C. M. D., Hudson, A. R., Khan, A., Adusei, B., Stehman, S. V., & Hansen, M. C. (2017) · Remote Sensing of Environment · doi:10.1016/j.rse.2017.01.008 · Cited by 282 · see citing works
Landsat ecosystem disturbance adaptive processing system (LEDAPS) algorithm description
Schmidt, G. L., Jenkerson, C. B., Masek, J. G., et al. (2013) · Antarctica A Keystone in a Changing World · doi:10.3133/ofr20131057 · Cited by 251 · see citing works
Crop type mapping using spectral–temporal profiles and phenological information
Foerster, S., Kaden, K., Foerster, M., et al. (2012) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2012.07.015 · Cited by 227 · see citing works
Long-term land cover dynamics by multi-temporal classification across the Landsat-5 record
Sexton, J., Urban, D. L., Donohue, M. J., & Conghe Song, A. (2012) · Remote Sensing of Environment · doi:10.1016/j.rse.2012.10.010 · Cited by 210 · see citing works
Corn and Soybean Mapping in the United States Using MODIS Time‐Series Data Sets
Chang, J., Hansen, M. C., Pittman, K. W., et al. (2007) · Agronomy Journal · doi:10.2134/agronj2007.0170 · Cited by 177 · see citing works
Flood, N. (2014) · Remote Sensing · doi:10.3390/rs6097952 · Cited by 177 · see citing works
Monitoring conterminous United States (CONUS) land cover change with Web-Enabled Landsat Data (WELD)
Hansen, M. C., Egorov, A., Potapov, P. V., Stehman, S. V., Tyukavina, A., Turubanova, S. A., Roy, D. P., Goetz, S. J., Loveland, T. R., Ju, J., et al. (2013) · Remote Sensing of Environment · doi:10.1016/j.rse.2013.08.014 · Cited by 176 · see citing works
Evaluating high resolution SPOT 5 satellite imagery for crop identification
Yang, C., Everitt, J. H., & Murden, D. (2011) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2010.12.012 · Cited by 175 · see citing works
Niel, T. G. V., & McVicar, T. R. (2004) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2004.06.003 · Cited by 148 · see citing works
Hansen, M. C., Egorov, A., Roy, D. P., Potapov, P. V., Ju, J., Turubanova, S. A., Kommareddy, I., & Loveland, T. R. (2010) · Remote Sensing Letters · doi:10.1080/01431161.2010.519002 · Cited by 123 · see citing works
Estimating crop water stress with ETM+ NIR and SWIR data
Ghulam, A., Li, Z.-L., Qin, Q., et al. (2008) · Agricultural and Forest Meteorology · doi:10.1016/j.agrformet.2008.05.020 · Cited by 102 · see citing works
Self-citationA multi-resolution approach to national-scale cultivated area estimation of soybean
King, L., Adusei, B., Stehman, S. V., Potapov, P. V., Song, X., Krylov, A., Bella, C. M. D., Loveland, T. R., Johnson, D. M., & Hansen, M. C. (2017) · Remote Sensing of Environment · doi:10.1016/j.rse.2017.03.047 · Cited by 83 · see citing works
Land-cover Classification Using Radarsat and Landsat Imagery for St. Louis, Missouri
Huang, H., Legarsky, J., & Othman, M. (2007) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.73.1.37 · Cited by 41 · see citing works
Gao, F., Wang, P., & Masek, J. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2023417 · Cited by 8 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep learning in remote sensing applications: A meta-analysis and review
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.04.015 · Cited by 2,456 · see citing works
Hao, X., & Demir, E. (2024) · Journal of Modelling in Management · doi:10.1108/jm2-01-2023-0009 · Cited by 92 · see citing works
- Authors
- Cai, Y., Guan, K., Peng, J., Wang, S., Seifert, C., Wardlow, B., & Li, Z.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- Stanford University (US)
- University of Nebraska–Lincoln (US)
- University of Massachusetts Boston (US)
- Corresponding author
- Guan, Kaiyu
- Peng, Jian
- Venue
- Remote Sensing of Environment
- Publisher
- Elsevier BV
- Published
- 2018-06
- Volume
- 210
- Pages
- 35-47
- ISSN
- 0034-4257 (ISSN-L)
- OpenAlex
- W2791592925
- Cited by
- 540
- References
- 50
- Citations by year
- 2026: 42 · 2025: 63 · 2024: 95 · 2023: 67 · 2022: 91 · 2021: 76 · 2020: 59 · 2019: 40 · 2018: 6
- FWCI
- 34.05
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 288 d)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Locations
- Remote Sensing of Environment (acceptedVersion)
- Funders
- National Aeronautics and Space Administration (80NSSC18K0170, NNX16AI56G)
- National Science Foundation (0725070, 1429699, 1238993)
- Topics
- Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Engineering › Media Technology › Remote-Sensing Image Classification
- Keywords
- crop classification, maize, soybean, crop phenology, shortwave infrared bands, cloud contamination, Corn Belt, Champaign County, Illinois, deep neural network, high-performance computing, crop area estimation, crop insurance, land lease, supply chain logistics, financial market forecasting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
