Abstract
Farmland is the cornerstone of agriculture and is important for food security and social production. Farmland assessment is essential but traditional methods are usually expensive and slow. Deep learning methods have been developed and widely applied recently in image recognition, semantic understanding, and many other application domains. In this research, we used fully convolutional networks (FCN) as the deep learning model to evaluate farmland grades. Normalized difference vegetation index (NDVI) derived from Landsat images was used as the input data, and the China National Cultivated Land Grade Database within Jiangsu Province was used to train the model on cloud computing. We also applied an image segmentation method to improve the original results from the FCN and compared the results with classical machine learning (ML) methods. Our research found that the FCN can predict farmland grades with an overall F1 score (the harmonic mean of precision and recall) of 0.719 and F1 score of 0.909, 0.590, 0.740, 0.642, and 0.023 for non-farmland, level I, II, III, and IV farmland, respectively. Combining the FCN and image segmentation method can further improve prediction accuracy with results of fewer noise pixels and more realistic edges. Compared with conventional ML, at least in farmland evaluation, FCN provides better results with higher precision, recall, and F1 score. Our research indicates that by using remote sensing NDVI data, the deep learning method can provide acceptable farmland assessment without fieldwork and can be used as a novel supplement to traditional methods. The method used in this research will save a lot of time and cost compared with traditional means.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10661-022-10848-5/MediaObjects/10661_2022_10848_Fig10_HTML.png)
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are not publicly available due we have signed a non-disclosure agreement with the provider of the farmland quality data but are available from the corresponding author on reasonable request.
References
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., & Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. ar**v preprint ar**v:1603.04467. https://doi.org/10.48550/ar**v.1603.04467
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2010). Slic superpixels.
Aung, S. W. Y., Khaing, S. S., & Aung, S. T. (2018). Multi-label land cover indices classification of satellite images using deep learning. International Conference on Big Data Analysis and Deep Learning Applications (pp. 94–103). Springer, Singapore.
Bégué, A., Lebourgeois, V., Bappel, E., Todoroff, P., Pellegrino, A., Baillarin, F., & Siegmund, B. (2010). Spatio-temporal variability of sugarcane fields and recommendations for yield forecast using NDVI. International Journal of Remote Sensing, 31(20), 5391–5407. https://doi.org/10.1080/01431160903349057
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2014). Semantic image segmentation with deep convolutional nets and fully connected crfs. ar**v preprint ar**v:1412.7062. https://doi.org/10.48550/ar**v.1412.7062
China, M. O. L. A. R. O. (2013). China land & Resources Almanac. Geological Publishing House.
Chuai, X., Huang, X., Wang, W., Wu, C., & Zhao, R. (2014). Spatial simulation of land use based on terrestrial ecosystem carbon storage in coastal Jiangsu, China. Scientific Reports, 4, 5667. https://doi.org/10.1038/srep05667
Ding, C. (2003). Land policy reform in China: assessment and prospects. Land Use Policy, 20(2), 109–120. https://doi.org/10.1016/S0264-8377(02)00073-X
Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2), 167–181. https://doi.org/10.1023/B:VISI.0000022288.19776.77
Fu, G., Liu, C., Zhou, R., Sun, T., & Zhang, Q. (2017). Classification for high resolution remote sensing imagery using a fully convolutional network. Remote Sensing, 9(5), 498. https://doi.org/10.3390/rs9050498
Guoqiang, W., Lingchao, W., Yan, T., Jianfeng, Y., Jianbo, Y., & Chaohui, W. (2007). Foundation and method for gathering agricultural land classification achievements at provincial level (in Chinese). Transactions of the Chinese Society of Agricultural Engineering, 23(6), 271–275.
He, X., Zemel, R. S., & Carreira-Perpiñán, M. Á. (2004). Multiscale conditional random fields for image labeling. Computer vision and pattern recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on.
Jiangsu Provincial Bureau of Statistics. (2019). Statistical Communique of the 2017 National Economic and Social Development of Jiangsu Province (in Chinese). Statistical Science and Practice.
Jiangsu Provincial Bureau of Statistics, J. B. o. I., National Bureau of Statistics. (2019). Statistical Communique of the 2017 National Economic and Social Development of Jiangsu Province (in Chinese). Statistical Science and Practice 03, 22–28.
**, H., Shi, D., Lou, Y. B., Zhang, J., Ye, Q., & Jiang, N. (2021). Evaluation of the quality of cultivated-layer soil based on different degrees of erosion in slo** farmland with purple soil in China. CATENA, 198, 105048.
**, X., ** and monitoring. Remote Sensing, 8(1), 70. https://doi.org/10.3390/rs8010070
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems.
Lafferty, J., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic Models for Segmenting and Labeling Sequence Data.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Li, L., Hao, T., & Chi, T. (2017). Evaluation on China's forestry resources efficiency based on big data. Journal of Cleaner Production, 142, 513–523. https://doi.org/10.1016/j.jclepro.2016.02.078
Lichtenberg, E., & Ding, C. (2008). Assessing farmland protection policy in China. Land Use Policy, 25(1), 59–68. https://doi.org/10.1016/j.landusepol.2006.01.005
Liu, Y., Fang, F., & Li, Y. (2014). Key issues of land use in China and implications for policy making. Land Use Policy, 40, 6–12. https://doi.org/10.1016/j.landusepol.2013.03.013
Liu, Y., Minh Nguyen, D., Deligiannis, N., Ding, W., & Munteanu, A. (2017). Hourglass-shapenetwork based semantic segmentation for high resolution aerial imagery. Remote Sensing, 9(6), 522. https://doi.org/10.3390/rs9060522
Liu, Y., Starzyk, J. A., & Zhu, Z. (2008). Optimized approximation algorithm in neural networks without overfitting. IEEE Transactions on Neural Networks, 19(6), 983–995. https://doi.org/10.1109/TNN.2007.915114
Long, J., Liu, Y., **ng, S., Qiu, L., Huang, Q., Zhou, B., Shen, J., & Zhang, L. (2018). Effects of sampling density on interpolation accuracy for farmland soil organic matter concentration in a large region of complex topography. Ecological Indicators, 93, 562–571. https://doi.org/10.1016/j.ecolind.2018.05.044
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
Ma, J., Zhang, C., & Lu, Y. (2019). Cultivated land quality evaluation based on inversion of NPP based on long-term sequence remote sensing data (in Chinese). Transactions of the Chinese Society for Agricultural Machinery, 50(1), 202–208.
Ma, J. H., Wu, K. N., Zhao, H. F., Xu, Y., & Zhou, Z. J. (2013). Research on the dynamic cultivated land quality monitoring system based on the agricultural land gradation (in Chinese). Chinese Journal of Agricultural Resources and Regional Planning, 34(5), 133–139. https://doi.org/10.7621/cjarrp.1005-9121.20130522
Mangan, A. P., & Whitaker, R. T. (1999). Partitioning 3D surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4), 308–321. https://doi.org/10.1109/2945.817348
Nagy, A., Fehér, J., & Tamás, J. (2018). Wheat and maize yield forecasting for the Tisza river catchment using MODIS NDVI time series and reported crop statistics. Computers and Electronics in Agriculture, 151, 41–49. https://doi.org/10.1016/j.compag.2018.05.035
Neyman, J. (1961). Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability. Univ of California Press.
Padarian, J., Minasny, B., & McBratney, A. (2019). Using deep learning to predict soil properties from regional spectral data. Geoderma Regional, 16, e00198. https://doi.org/10.1016/j.geodrs.2018.e00198
Paisitkriangkrai, S., Sherrah, J., Janney, P., & Van Den Hengel, A. (2016). Semantic labeling of aerial and satellite imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(7), 2868–2881. https://doi.org/10.1109/JSTARS.2016.2582921
Persello, C., & Stein, A. (2017). Deep fully convolutional networks for the detection of informal settlements in VHR images. IEEE Geoscience and Remote Sensing Letters, 14(12), 2325–2329. https://doi.org/10.1109/LGRS.2017.2763738
Prechelt, L. (1998). Automatic early stop** using cross validation: quantifying the criteria. Neural Networks, 11(4), 761–767. https://doi.org/10.1016/S0893-6080(98)00010-0
Qian, F., Wang, Q., Bian, Z., Dong, X., & Zheng, L. (2011). Farmland quality evaluation and site assessment in Lingyuan city. Transactions of the Chinese Society of Agricultural Engineering, 27(11), 325–329.
SAC and AQSIQ. (2012). Regulation for gradation on agriculture land quality (in Chinese). GBT28407-2012. National Standards of People's Republic of China. Bei**g.
Shao, J. A., Ge, X., Wei, C., & **e, D. (2007). Classification and gradation of cultivated land quality in Bishan County of Chongqing, China. Chinese Geographical Science, 17(1), 82–91. https://doi.org/10.1007/s11769-007-0082-1
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. ar**v preprint ar**v:1409.1556. https://doi.org/10.48550/ar**v.1409.1556
Song, W., & Liu, M. (2017). Farmland conversion decreases regional and national land quality in China. Land Degradation & Development, 28(2), 459–471. https://doi.org/10.1002/ldr.2518
Sun, Y., Chen, Y., Wang, X., & Tang, X. (2014). Deep learning face representation by joint identification-verification. Advances in Neural Information Processing Systems, 27.
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems, 27.
Takoutsing, B., Weber, J., Aynekulu, E., Martín, J. A. R., Shepherd, K., Sila, A., Tchoundjeu, Z., & Diby, L. (2016). Assessment of soil health indicators for sustainable production of maize in smallholder farming systems in the highlands of Cameroon. Geoderma, 276, 64–73. https://doi.org/10.1016/j.geoderma.2016.04.027
Talukdar, S., Singha, P., Mahato, S., Pal, S., Liou, Y. A., & Rahman, A. (2020). Land-use land-cover classification by machine learning classifiers for satellite observations—A review. Remote Sensing, 12(7), 1135. https://doi.org/10.3390/rs12071135
Vedaldi, A., & Soatto, S. (2008). Quick shift and kernel methods for mode seeking. European Conference on Computer Vision.
Wang, J., Wang, X., Zhou, S., Wu, S., Zhu, Y., & Lu, C. (2016). Optimization of Sample Points for Monitoring Arable Land Quality by Simulated Annealing while Considering Spatial Variations. International Journal of Environmental Research and Public Health, 13(10), 980. https://doi.org/10.3390/ijerph13100980
Wang, N., & Yeung, D. Y. (2013). Learning a deep compact image representation for visual tracking. Advances in Neural Information Processing Systems, 26.
Wen Liangyou, K. X., Zhang Bangbang, Sun **aobing, **n Yunna, Zhang Qingpu. (2019). Construction and application of arable land quality evaluation system based on sustainable development demand. Transactions of the Chinese Society of Agricultural Engineering, 35(10), 234–242. https://doi.org/10.11975/j.issn.1002-6819.2019.10.030
Wu, C., Liu, G., Huang, C., & Liu, Q. (2019). Soil quality assessment in Yellow River Delta: Establishing a minimum data set and fuzzy logic model. Geoderma, 334, 82–89. https://doi.org/10.1016/j.geoderma.2018.07.045
**angbin, K., **g, J., Yi, L., Cuizhen, L., & **g, Q. (2008). Planning method of the prime farmland protection zone based on farmland utilization grade. Transactions of the Chinese Society of Agricultural Engineering, 2008(10).
**e, H., He, Y., & **e, X. (2017). Exploring the factors influencing ecological land change for China's Bei**g–Tian**–Hebei region using big data. Journal of Cleaner Production, 142, 677–687. https://doi.org/10.1016/j.jclepro.2016.03.064
**ng, Y., Xu, J., Tan, J., Li, D., & Zha, W. (2019). Deep CNN for removal of salt and pepper noise. IET Image Processing, 13(9), 1550–1560.
**, Z., & Caowen, M. (2018). Research on the inversion model of cultivated land quality based on normalized difference vegetation index (in Chinese). Chinese Journal of Soil Science, 4, 779–787.
Yun, Y., **aojuan, Z., & Yueming, H. (2018). Evaluation of cultivated land quality in Pearl River Delta based on GA-BP neural network (in Chinese). Ecology and Environmental Sciences, 27(5), 964–973.
Zhang, C., Wang, X., & Liu, Y. (2019). Changes in quantity, quality, and pattern of farmland in a rapidly develo** region of China: a case study of the Ningbo region. Landscape and Ecological Engineering, 15(3), 323–336. https://doi.org/10.1007/s11355-019-00382-x
Zhao, W., & Du, S. (2016). Spectral–spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach. IEEE Transactions on Geoscience and Remote Sensing, 54(8), 4544–4554. https://doi.org/10.1109/TGRS.2016.2543748
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. (2015). Conditional random fields as recurrent neural networks. Proceedings of the IEEE International Conference on Computer Vision.
Funding
This work was supported by the Young Scientists Fund of the National Natural Science Foundation of China (Grant No. 42201282), by the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China (Grant No. 21KJB170010), and by the National Natural Science Foundation of China (Grant No. 42271271).
Author information
Authors and Affiliations
Contributions
Conceptualization, J.W. and X.L.; methodology, X.L. and Y.L.; software, J.W. and Y.L.; validation, X.W. and S.Z.; formal analysis, X.W.; investigation, J.W.; resources, J.W.; writing—original draft preparation, J.W.; writing—review and editing, J.W.; visualization, X.W.; supervision, X.L.; project administration, J.W.; funding acquisition, J.W., X.L., and S.Z. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, J., Li, X., Wang, X. et al. Farmland quality assessment using deep fully convolutional neural networks. Environ Monit Assess 195, 239 (2023). https://doi.org/10.1007/s10661-022-10848-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10661-022-10848-5