Incorporating Multi-Temporal Remote Sensing and a Pixel-Based Deep Learning Classification Algorithm to Map Multiple-Crop Cultivated Areas
Source abstract
Abstract
The accurate monitoring of crop areas is essential for food security and agriculture, but accurately extracting multiple-crop distribution over large areas remains challenging. To solve the above issue, in this study, the Pixel-based One-dimensional convolutional neural network (PB-Conv1D) and Pixel-based Bi-directional Long Short-Term Memory (PB-BiLSTM) were proposed to identify multiple-crop cultivated areas using time-series NaE (a combination of NDVI and EVI) as input for generating a baseline classification. Two approaches, Snapshot and Stochastic weighted averaging (SWA), were used in the base-model to minimize the loss function and improve model accuracy. Using an ensemble algorithm consisting of five PB-Conv1D and seven PB-BiLSTM models, the temporal vegetation index information in the base-model was comprehensively exploited for multiple-crop classification and produced the Pixel-Based Conv1D and BiLSTM Ensemble model (PB-CB), and this was compared with the PB-Transformer model to validate the effectiveness of the proposed method. The multiple-crop cultivated area was extracted from 2005, 2010, 2015, and 2020 in North China by using the PB-Conv1D combine Snapshot (PB-CDST) and PB-CB models, which are a performance-optimized single model and an integrated model, respectively. The results showed that the mapping results of the multiple-crop cultivated area derived by PB-CDST (OA: 81.36%) and PB-BiLSTM combined with Snapshot (PB-BMST) (OA: 79.40%) showed exceptional accuracy compared to PB-Transformer combined with Snapshot and SWA (PB-TRSTSA) (OA: 77.91%). Meanwhile, the PB-CB (OA: 83.43%) had the most accuracy compared to the pixel-based single algorithm. The MODIS-derived PB-CB method accurately identified multiple-crop areas for wheat, corn, and rice, showing a strong correlation with statistical data, exceeding 0.7 at the municipal level and 0.6 at the county level.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Remote Sensing and Land Use · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
Key Laboratory of Earth Observation of Hainan Province, Hainan Aerospace Information Research Institute, Sanya 572029, China
Remote Sensing Information and Digital Earth Center, College of Computer Science and Technology, Qingdao University, Qingdao 266071, China
College of Earth and Planetary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
Department of Agricultural Extension and Rural Development, Bangabandhu Sheikh Mujibur Rahman Agricultural University, Gazipur 1706, Bangladesh
Funding
Science and Technology Support Plan for Youth Innovation of Colleges and Universities of Shandong Province of China · Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources · Finance Science and Technology Project of Hainan Province · Shandong Key Research and Development Project · 2023 Zhonglou District of Changzhou City Science and Technology Research Project
References (64)
Show source-provided references
1. Training sample selection for robust multi-year within-season crop classification using machine learning10.1016/j.compag.2023.107927 ↗
2. Using the 500m MODIS land cover product to derive a consistent continental scale 30m Landsat land cover classification10.1016/j.rse.2017.05.024 ↗
3. Assessing the suitability of data from Sentinel-1A and 2A for crop classification10.1080/15481603.2017.1351149 ↗
4. Crop classification using multi-configuration SAR data in the North China plain10.1080/01431161.2011.587844 ↗
5. A novel cotton mapping index combining Sentinel-1 SAR and Sentinel-2 multispectral imagery10.1016/j.isprsjprs.2021.08.021 ↗
6. Early season large-area winter crop mapping using MODIS NDVI data, growing degree days information and a Gaussian mixture model10.1016/j.rse.2017.04.026 ↗
7. Wang, X., Zhang, S., Feng, L., Zhang, J., and Deng, F. (2020). Mapping maize cultivated area combining MODIS EVI time series and the spatial variations of phenology over huanghuaihai plain. Appl. Sci., 10.10.3390/app10082667 ↗
8. Wu, Z., Zhang, J., Deng, F., Zhang, S., Zhang, D., Xun, L., Javed, T., Liu, G., Liu, D., and Ji, M. (2021). Fusion of gf and modis data for regional-scale grassland community classification with evi2 time-series and phenological features. Remote Sens., 13.10.3390/rs13050835 ↗
9. A curve fitting procedure to derive inter-annual phenologies from time series of noisy satellite NDVI data10.1016/j.rse.2006.08.002 ↗
10. A deep learning approach for forecasting non-stationary big remote sensing time series10.1007/s12517-020-06140-w ↗
11. Spatio-temporal distribution of rice phenology and cropping systems in the Mekong Delta with special reference to the seasonal water flow of the Mekong and Bassac rivers10.1016/j.rse.2005.09.007 ↗
12. Phenology-based classification of crop species and rotation types using fused MODIS and Landsat data: The comparison of a random-forest-based model and a decision-rule-based model10.1016/j.still.2020.104838 ↗
13. Phenology-based sample generation for supervised crop type classification
14. A phenology-based approach to map crop types in the San Joaquin Valley, California10.1080/01431161.2010.527397 ↗
15. He, T., Xie, C., Liu, Q., Guan, S., and Liu, G. (2019). Evaluation and Comparison of Random Forest and A-LSTM Networks for Large-scale Winter Wheat Identification. Remote Sens., 11.10.3390/rs11141665 ↗
16. Improved maize cultivated area estimation over a large scale combining MODIS-EVI time series data and crop phenological information10.1016/j.isprsjprs.2014.04.023 ↗
17. Wang, X., Zhang, J., Xun, L., Wang, J., Wu, Z., Henchiri, M., Zhang, S., Zhang, S., Bai, Y., and Yang, S. (2022). Evaluating the Effectiveness of Machine Learning and Deep Learning Models Combined Time-Series Satellite Data for Multiple Crop Types Classification over a Large-Scale Region. Remote Sens., 14.10.3390/rs14102341 ↗
18. Transfer learning approach based on satellite image time series for the crop classification problem10.1186/s40537-023-00735-2 ↗
19. End-to-end learned early classification of time series for in-season crop type mapping10.1016/j.isprsjprs.2022.12.016 ↗
20. Deep learning based multi-temporal crop classification10.1016/j.rse.2018.11.032 ↗
21. Identifying the spatiotemporal changes of annual harvesting areas for three staple crops in China by integrating multi-data sources10.1088/1748-9326/ab80f0 ↗
22. Mapping cotton cultivated area combining remote sensing with a fused representation-based classification algorithm10.1016/j.compag.2020.105940 ↗
23. Chen, S.W., and Tao, C.S. (2017, January 18–21). Multi-temporal PolSAR crops classification using polarimetric-feature-driven deep convolutional neural network. Proceedings of the 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP), Shanghai, China.10.1109/RSIP.2017.7958818 ↗
24. Gadiraju, K.K., Ramachandra, B., Chen, Z., and Vatsavai, R.R. (2020, January 23–27). Multimodal Deep Learning Based Crop Classification Using Multispectral and Multitemporal Satellite Imagery. Proceedings of the KDD ‘20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event.10.1145/3394486.3403375 ↗
25. Multivariate LSTM-FCNs for time series classification10.1016/j.neunet.2019.04.014 ↗
26. LeCun, Y., and Bengio, Y. (1995). The Handbook of Brain Theory and Neural Networks, MIT Press.
27. Bridging optical and SAR satellite image time series via contrastive feature extraction for crop classification10.1016/j.isprsjprs.2022.11.020 ↗
28. Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery10.1016/j.rse.2018.04.050 ↗
29. Classification of Land Cover and Land Use Using Deep Learning10.1007/978-981-16-5078-9_28 ↗
30. Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate models10.1016/j.isprsjprs.2018.01.021 ↗
31. Remote Sensing of Environment Deep learning in environmental remote sensing: Achievements and challenges10.1016/j.rse.2020.111716 ↗
32. Rußwurm, M., and Korner, M. (2018). Multi-temporal land cover classification with sequential recurrent encoders. ISPRS Int. J. Geo-Inf., 7.10.3390/ijgi7040129 ↗
33. DeepCropMapping: A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping10.1016/j.rse.2020.111946 ↗
34. Learning spectral-spatialoral features via a recurrent convolutional neural network for change detection in multispectral imagery10.1109/TGRS.2018.2863224 ↗
35. Attention is all you need
36. Self-attention for raw optical Satellite Time Series Classification10.1016/j.isprsjprs.2020.06.006 ↗
37. Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E., and Weinberger, K.Q. (2017). Snapshot ensembles: Train 1, get M for free. arXiv.
38. Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., and Wilson, A.G. (2018). Averaging weights leads to wider optima and better generalization. arXiv.
39. Crop type mapping in the central part of the North China Plain using Sentinel-2 time series and machine learning10.1016/j.compag.2022.107577 ↗
40. Temporal Sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series10.1016/j.cj.2022.07.005 ↗
41. Near real-time prediction of U.S. corn yields based on time-series MODIS data10.1016/j.rse.2014.03.008 ↗
42. GLC_FCS30: Global land-cover product with fine classification system at 30m using time-series Landsat imagery10.5194/essd-13-2753-2021 ↗
43. Crop conditional Convolutional Neural Networks for massive multi-crop plant disease classification over cell phone acquired images taken on real field conditions10.1016/j.compag.2019.105093 ↗
44. Dropout: A Simple Way to Prevent Neural Networks from Overfitting
45. Bermúdez, J.D., Achanccaray, P., Sanches, I.D., Cue, L., Happ, P., and Feitosa, R.Q. (2017, January 6–9). Evaluation of Recurrent Neural Networks for Crop Recognition from Multitemporal Remote Sensing Images. Proceedings of the Anais do XXVII Congresso Brasileiro de Cartografia, Rio deJaneiro, Brazil.
46. Towards interpreting multi-temporal deep learning models in crop mapping10.1016/j.rse.2021.112599 ↗
47. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
48. Predicting subsurface thermohaline structure from remote sensing data based on long short-term memory neural networks10.1016/j.rse.2021.112465 ↗
49. Cao, C., Dragićević, S., and Li, S. (2019). Short-term forecasting of land use change using recurrent neural network models. Sustainability, 11.10.3390/su11195376 ↗
50. Sainte Fare Garnot, V., Landrieu, L., Giordano, S., and Chehata, N. (2020, January 13–19). Satellite image time series classification with pixel-set encoders and temporal self-attention. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01234 ↗
51. Deep learning without poor local minima
52. Evaluating an ensemble classification approach for crop diversity verification in Danish greening subsidy control
53. A data-driven analysis of occupant workspace dissatisfaction10.1016/j.buildenv.2021.108270 ↗
54. Powers, D.M.W. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.
55. A Novel Automatic Method for Alfalfa Mapping Using Time Series of Landsat-8 OLI Data10.1109/JSTARS.2018.2874726 ↗
56. Identifying crop planting areas using Fourier-transformed feature of time series MODIS leaf area index and sparse-representation-based classification in the North China Plain10.1080/01431161.2018.1492181 ↗
57. Stacked spectral feature space patch: An advanced spectral representation for precise crop classification based on convolutional neural network10.1016/j.cj.2021.12.011 ↗
58. Response of cotton phenology to climate change on the North China Plain from 1981 to 201210.1038/s41598-017-07056-4 ↗
59. National-scale soybean mapping and area estimation in the United States using medium resolution satellite imagery and field survey10.1016/j.rse.2017.01.008 ↗
60. Optimizing selection of training and auxiliary data for operational land cover classification for the LCMAP initiative10.1016/j.isprsjprs.2016.11.004 ↗
61. A new generation of the United States National Land Cover Database: Requirements, research priorities, design, and implementation strategies10.1016/j.isprsjprs.2018.09.006 ↗
62. MODIS phenology-derived, multi-year distribution of conterminous U.S. crop types10.1016/j.rse.2017.06.033 ↗
63. A comprehensive change detection method for updating the National Land Cover Database to circa 201110.1016/j.rse.2013.01.012 ↗
64. A land cover change detection and classification protocol for updating Alaska NLCD 2001 to 201110.1016/j.rse.2017.04.021 ↗