Abstract
North Indian states are largely covered with agricultural land which plays an important role in nation’s economy development. Remote sensing offers a cost-effective and efficient solution for sustainable monitoring and mapping of agricultural land. In past, various classification algorithms were developed and implemented for agriculture applications. But the conventional techniques are generally based on machine learning algorithms which are easy to implement but at the same time require human intervention on decision making. Nowadays, deep learning algorithms are becoming more popular due to the presence of trained models and one-time processing. However, the deep learning model required a large amount of computation time and needs to be tested in different regions for different applications. In the present work, the deep learning algorithm has been tested over agricultural land (over a part of Punjab state, India) using Sentinel-2 imagery. The major classes considered in the present analysis are vegetation area, water, and buildup area. For validation purposes, output classified maps are compared with reference datasets which were acquired from field observations for some points. The statistical results have shown that more than 80% of accuracy has been obtained using a deep learning algorithm. This study has many applications in the monitoring and mapping of land use land cover regions using a deep learning algorithm.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Similar content being viewed by others
Keywords
1 Introduction
Agriculture land is the backbone of the Indian economy and the major source of national income via agriculture and allied activities. Agriculture is acting as a supply chain of food products and raw material for industrial development, commercial activities, and international trade [1]. It has also been observed that in India, agriculture activities have been continuously decreased due to urbanization or the growth of other sectors [2]. But still as compared to other countries the rate is high [3]. It is more important to perform a comprehensive assessment of agriculture concerning crop production which is essential to meet the demands of the food supply chain [4]. For mapping and validating the agricultural land, field observation methods are generally followed which are time-consuming, expensive, and tedious tasks and also sometimes not feasible for inaccessible areas [5].
For large land-use and land-cover mapping and monitoring, remote sensing plays an important role at a lower cost. Remote Sensing (RS) dataset can be broadly categorized into two types first is optical sensor and another is microwave [6]. The optical remote sensing dataset is further classified such as Landsat-8 [7], Sentinel-2 [8], MODIS (Moderate Resolution Imaging Spectroradiometer) [9], AVIS (Avian Information System) the classification requires the training data to classify the input data such as DL (Deep Learning), ANN (Artificial Neural Network), CNN (Convolutional Neural Network). The microwave remote sensing dataset is also classified such as SAR (Synthetic Aperture Radar), SCATSAT-1 (Scatterometer Satellite-1) [10] represents the classified dataset obtained from two different classifier LMM (Linear Mixer Model) and ANN (Artificial Neural Network), respectably. In past, various techniques have been developed and modified to improve the utilization of remotely sensed data [11]. However, most of the traditional techniques or models are generally based on machine learning algorithms and proven as significant in large area mapping [12]. But such methods are generally based on either supervised or unsupervised models [13]. From the literature [14], it has been seen that unsupervised methods are not able to extract the actual information satellite imagery due to dependency on untrained data [15]. On the other hand, supervised methods provide better results but are limited by the requirement of training data which varies from person to person [16].
In literature, various datasets have been explored such as Sentinel 1 dataset for agriculture land mapping [17], a high-resolution satellite dataset to classify the cloud, shadow, and land cover [18] as shown in Table 1. Moreover, [19] investigated the suitability and potential of DCNN in the supervised classification of POLSAR (Polarimetric Synthetic Aperture Radar) dataset. Spatial information was naturally employed in terrain classification due to the properties of convolutional networks. The deep learning algorithms take the advantage of the trained model to reduce the intervention of the user’s skill. However, the deep learning model requires more computation power and time and needs to be tested in different regions for different applications [20].
The main aim of this research paper is to estimate and validate agriculture using a deep learning algorithm over a part of Punjab state, India using the Sentinel-2 dataset. In the study area, the major classes are vegetation area, water, and buildup area [23]. Previously the classification of the agriculture land is done to the door-to-door survey. Here in the proposed work remote sensing dataset is being used for automatic classification of agriculture land. The introduction is followed by the study site and the associated dataset in Sect. 2; Sect. 3 describes the methodology of the deep learning algorithm with the Tensor Flow model for agriculture land cover classification using the sentinel-2 dataset. The experimental results are discussed in Sect. 4. At last, the conclusion has been drawn in Sect. 5.
2 Study Area and Satellite Dataset
The study site lies in district Fatehgarh Sahib and Patiala, Punjab, having geographic coordinates between 30°26’N–30°33’N in latitude and 76°21’E–76°29’E in longitude as shown in Fig. 1. The class categories existing over the study area are agriculture, buildup, and water. The data is acquired on 19 February 2018 using the European Space Agency (ESA) based on Sentinel-2. It offers the information in twelve different spectral bands such as (a) 4 VIS and NIR bands at 10 m of spatial resolution, (b) 6 Red and SWIR bands at 20 m of spatial resolution, and (c) 3 atmospheric correction bands at 60 m of spatial resolution. The sentinel dataset offers a range of applications in various scientific domains.
3 Methodology
The flowchart of the proposed methodology is shown in Fig. 2 which involves the three basic steps: (a) Pre-processing that involves the area of interest (AOI) acquisition from atmospherically and radiometrically correction sentinel-2 data, (b) implementation of deep learning module to train the model, (c) classification. This framework is designed specifically to work with remotely sensed imagery to solve geographic problems through deep learning technologies [33]. The model must be trained to look for specific features using a set of input label raster that indicates know samples of the features [34].
3.1 Preprocessing
In the present work, we are dealing with the agricultural land and therefore, the data has been pre-processed using the “Sen2cor” software tool for performing atmospheric and radiometric corrections [25]. Afterward, the AOI is extracted from the Sentinel-2 tile and fed to the deep learning model.
3.2 Deep Learning Process
Initially, the sample was extracted from the input dataset with the knowledge of field data and then, builds the raster with the help of training samples. Afterward, the Tensor Flow model is used to train the models using specific parameters. Once the model is trained, then it is used as the input to the classification procedure. It is noted that while implementing the deep learning process, the computer specification includes the Intel Xeon 3.2 2400 MHz 8.25 4C CPU, 16 GB of RAM, 512 GB of SSD, and NVIDIA Quadro P620 2 GB (4) MDP GFX.
3.3 Classification
Once the activation output is obtained, the classified maps have been generated using the automatic Otsu threshold method for each class category i.e. build-up area, agricultural, water, and rest all the categories have been assigned to mixed categories.
4 Experimental Analysis
The methodology shown in Fig. 3 was applied to process the dataset sentinel-2. There after the processed dataset was further analyzed to map in the form of classified dataset. To get the desired classified dataset such as vegetation, water and build-up area the classification scheme has been performed. The land cover regions were generated for each of the deep learning-based classification approaches for each category separately i.e. (a) vegetation area, (b) buildup area, and (c) water area, respectively [35].
From Fig. 4, the thematic map derived from sentinel-2 and additional data using deep learning classification algorithm show the variation in vegetation, buildup, water, mix (buildup & vegetation), and mix (water & vegetation) [36]. The main reason behind the existence of mixed categories due to limited spatial resolution. District Fatehgarh Sahib and Patiala had the samples to be collected of total number and were the effective category within the study area [37].
Moreover, the statistical analysis has also been computed for deep learning algorithms such as recalls rate, precision, loss, and accuracy. Figure 5 represents the statistical analysis to highlight the performance of the deep learning model. From the statistical analysis, the validated precision (88% accuracy) and average (98% accuracy) at the 100th epoch for 10 k folds and while the loss and recall rate started to raise. To hand was no significant raise or reduction after the 100th epoch, and the training was completed at that epoch to attain the highest accuracy possible without any over-fitting the network [21].
5 Conclusion
This study highlights the performance of a deep learning algorithm for agricultural land using the Sentinel-2 satellite dataset. The deep learning algorithm confirmed that all classes contributed in the classification process. Also, all the mixed categories have been separated to improve the accuracy of classification [38]. From the present study, it has been concluded that deep learning plays a significant role in the extraction of accurate class categories from satellite images. However, the results may be affected due to the limited spatial resolution of the satellite dataset. It is expected that different vegetation types could be explored using high spatial resolution and hyperspectral dataset. This research has a wide contribution in agriculture field to decide the area suitable for crop field. This research will prove to be more useful in finding areas that burn straw. Future recommendations also involved the exploration of deep learning algorithms for different land-use and land-cover types using different sensors at the global level.
References
Sicre, C.M., Fieuzal, R., Baup, F.: Contribution of multispectral (optical and radar) satellite images to the classification of agricultural surfaces. Int. J. Appl. Earth Obs. Geoinf. 84, 1–13 (2020)
Lu, D., Mausel, P., Brondízio, E., Moran, E.: Change detection techniques. Int. J. Remote Sens. 25, 2365–2401 (2004). https://doi.org/10.1080/0143116031000139863
Adepoju, K.A., Adelabu, S.A.: Improving accuracy evaluation of Landsat-8 OLI using image composite and multisource data with Google Earth Engine. Remote Sens. Lett. 11, 107–116 (2020). https://doi.org/10.1080/2150704X.2019.1690792
Singh, G., Sethi, G.K.: Automatic land cover classification using learning techniques with dynamic features. Int. J. Innov. Technol. Explor. Eng. 8, 499–503 (2019)
Khamparia, A., Singh, A., Luhach, A.K., Pandey, B., Pandey, D.K.: Classification and identification of primitive Kharif crops using supervised deep convolutional networks. Sustain. Comput. Inform. Syst. (2019). https://doi.org/10.1016/j.suscom.2019.07.003
Sood, V., Gusain, H.S., Gupta, S., Taloor, A.K., Singh, S.: Detection of snow/ice cover changes using subpixel-based change detection approach over Chhota-Shigri glacier, Western Himalaya, India. Quat. Int. (2020). https://doi.org/10.1016/j.quaint.2020.05.016
Zhong, L., Hu, L., Zhou, H.: Deep learning based multi-temporal crop classification. Remote Sens. Environ. 221, 430–443 (2019). https://doi.org/10.1016/j.rse.2018.11.032
Virnodkar, S.S., Pachghare, V.K., Patil, V.C., Kumar, S.: CaneSat dataset to leverage convolutional neural networks for sugarcane classification from Sentinel-2. J. King Saud Univ. - Comput. Inf. Sci. (2020). https://doi.org/10.1016/j.jksuci.2020.09.005
Singh, S., Sood, V., Prashar, S., Kaur, R.: Response of topographic control on nearest-neighbor diffusion-based pan-sharpening using multispectral MODIS and AWiFS satellite dataset. Arab. J. Geosci. 13, 1–9 (2020). https://doi.org/10.1007/s12517-020-05686-z
Sood, V., Gusain, H.S., Gupta, S., Singh, S., Kaur, S.: Evaluation of SCATSAT-1 data for snow cover area mapping over a part of Western Himalayas. Adv. Sp. Res. 66, 2556–2567 (2020). https://doi.org/10.1016/j.asr.2020.08.017
Singh, S., Tiwari, R.K., Sood, V., Gusain, H.S.: Detection and validation of spatiotemporal snow cover variability in the Himalayas using Ku-band (13.5 GHz) SCATSAT-1 data. Int. J. Remote Sens. 42, 805–815 (2021). https://doi.org/10.1080/2150704X.2020.1825866
Aznar-sánchez, J.A., Piquer-rodríguez, M., Velasco-muñoz, J.F., Manzano-agugliaro, F.: Worldwide research trends on sustainable land use in agriculture. Land Use Policy 87, 1–15 (2019)
Singh, S., Tiwari, R.K., Gusain, H.S., Sood, V.: Potential applications of SCATSAT-1 satellite sensor: a systematic review. IEEE Sens. J. 1748, 1 (2020). https://doi.org/10.1109/jsen.2020.3002720
Sood, V., Gupta, S., Gusain, Sh.S., Singh, S.: Spatial and quantitative comparison of topographically derived different classification algorithms using AWiFS data over Himalayas. J. Indian Soc. Remote Sens. 4, 1–12 (2018). https://doi.org/10.1007/s12524-018-0861-4
Singh, S., Tiwari, R.K., Gusain, H.S., Sood, V.: Potential applications of SCATSAT-1 satellite sensor: a systematic review. IEEE Sens. J. 20, 12459–12471 (2020). https://doi.org/10.1109/JSEN.2020.3002720
Sankar, S., Srinivasan, P., Luhach, A.K., Somula, R., Chilamkurti, N.: Energy-aware grid-based data aggregation scheme in routing protocol for agricultural internet of things. Sustain. Comput. Inform. Syst. 28, 100422 (2020). https://doi.org/10.1016/j.suscom.2020.100422
Shendryk, Y., Rist, Y., Ticehurst, C., Thorburn, P.: Deep learning for multi-modal classification of cloud, shadow and land cover scenes in PlanetScope and Sentinel-2 imagery. ISPRS J. Photogramm. Remote Sens. 157, 124–136 (2019)
Ndikumana, E., Ho, D., Minh, T., Baghdadi, N., Courault, D., Hossard, L.: Deep recurrent neural network for agricultural classification using multitemporal SAR Sentinel-1 for Camargue, France. Remote Sens. 10, 1–16 (2018). https://doi.org/10.3390/rs10081217
Zhou, Z., Li, S., Shao, Y.: Crops classification from Sentinel-2A multi-spectral remote sensing images based on convolutional neural networks. In: IGARSS, pp. 5300–5303 (2018)
Viana-Soto, A., Aguado, I., Martínez, S.: Assessment of post-fire vegetation recovery using fire severity and geographical data in the mediterranean region (Spain). Environ. - MDPI 4, 1–17 (2017). https://doi.org/10.3390/environments4040090
Dyrmann, M., Karstoft, H., Midtiby, H.S.: Plant species classification using deep convolutional neural network. Biosyst. Eng. 151, 72–80 (2016). https://doi.org/10.1016/j.biosystemseng.2016.08.024
Omer, G., Mutanga, O., Abdel-Rahman, E.M., Adam, E.: Performance of support vector machines and artificial neural network for mapping endangered tree species using WorldView-2 data in Dukuduku Forest, South Africa. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 8, 4825–4840 (2015). https://doi.org/10.1109/JSTARS.2015.2461136
Ka, A., Sa, A.: Improved Landsat-8 Oli and Sentinel-2 Msi classification in mountainous terrain using machine learning on Google earth engine, pp. 632–645 (2018)
Kussul, N., Lavreniuk, M., Skakun, S., Shelestov, A.: Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci. Remote Sens. Lett. 14, 778–782 (2017). https://doi.org/10.1109/LGRS.2017.2681128
Adagbasa, E.G., Adelabu, S.A., Okello, T.W.: Application of deep learning with stratified K-fold for vegetation species discrimation in a protected mountainous region using Sentinel-2 image. Geocarto Int. 1–21 (2019). https://doi.org/10.1080/10106049.2019.1704070
Ienco, D., Interdonato, R., Gaetano, R., Ho, D., Minh, T.: Combining Sentinel-1 and Sentinel-2 Satellite Image Time Series for land cover mapping via a multi-source deep learning architecture. ISPRS J. Photogramm. Remote Sens. 158, 11–22 (2019). https://doi.org/10.1016/j.isprsjprs.2019.09.016
El Mendili, L., Puissant, A., Chougrad, M., Sebari, I.: Towards a multi-temporal deep learning approach for mapping urban fabric using Sentinel 2 images. Remote Sens. 12, 423 (2020). https://doi.org/10.3390/rs12030423
Mazzia, V., Khaliq, A., Chiaberge, M.: Improvement in land cover and crop classification based on temporal features learning from Sentinel-2 data using recurrent-Convolutional Neural Network (R-CNN). Appl. Sci. 10, 1–23 (2020). https://doi.org/10.3390/app10010238
Campos-Taberner, M., et al.: Understanding deep learning in land use classification based on Sentinel-2 time series. Sci. Rep. 10, 1–12 (2020). https://doi.org/10.1038/s41598-020-74215-5
Ganesh, P., Volle, K., Burks, T.F., Mehta, S.S.: Orange: mask R-CNN based orange detection and segmentation. IFAC Pap. 52, 70–75 (2019). https://doi.org/10.1016/j.ifacol.2019.12.499
Peterson, K.T., Sagan, V., Sloan, J.J., Sloan, J.J.: Deep learning-based water quality estimation and anomaly detection using Landsat-8/ Sentinel-2 virtual constellation and cloud computing. GIScience Remote Sens. 57, 1–16 (2020). https://doi.org/10.1080/15481603.2020.1738061
Wang, M., Zhang, H., Sun, W., Li, S., Wang, F., Yang, G.: A coarse-to-fine deep learning based land use change detection method for high-resolution remote sensing images. Remote Sens. 12 (1933)
Vreugdenhil, M., et al.: Sensitivity of Sentinel-1 backscatter to vegetation dynamics: an Austrian case study. Remote Sens. 10, 1–19 (2018). https://doi.org/10.3390/rs10091396
Grosso, M.M.: Optical and SAR remote sensing synergism for mapping vegetation types in the endangered Cerrado/Amazon Ecotone of Nova. Remote Sens. 11, 01–25 (2019)
Stendardi, L., et al.: Exploiting time series of Sentinel-1 and Sentinel-2 imagery to detect meadow phenology in mountain regions. Remote Sens. 11, 1–24 (2019). https://doi.org/10.3390/rs11050542
Jozdani, S.E., Johnson, B.A., Chen, D.: Comparing deep neural networks, ensemble classifiers, and support vector machine algorithms for object-based urban land use/land cover classification. Remote Sens. 11, 1–24 (2019). https://doi.org/10.3390/rs11141713
Otunga, C., Odindi, J., Mutanga, O., Adjorlolo, C.: Evaluating the potential of the red edge channel for C3 (Festuca spp.) grass discrimination using Sentinel-2 and Rapid Eye satellite image data. Geocarto Int. 34, 1123–1143 (2019). https://doi.org/10.1080/10106049.2018.1474274
Sood, V., Gusain, H.S., Gupta, S., Taloor, A.K., Singh, S.: Detection of snow/ice cover changes using subpixel-based change detection approach over Chhota-Shigri glacier, Western Himalaya, India. Quat. Int. 575, 204–212 (2020). https://doi.org/10.1016/j.quaint.2020.05.016
Acknowledgment
The authors would like to thank the U.S. Geological Survey (USGS), NASA for providing the ESA’s Sentinel-2 dataset via an online platform (https://earthexplorer.usgs.gov/). They also like to thank Chitkara University, HP for providing infrastructural and laboratory facilities for the smooth conduct of the experiment.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singh, G., Sethi, G.K., Singh, S. (2021). Performance Analysis of Deep Learning Classification for Agriculture Applications Using Sentinel-2 Data. In: Luhach, A.K., Jat, D.S., Bin Ghazali, K.H., Gao, XZ., Lingras, P. (eds) Advanced Informatics for Computing Research. ICAICR 2020. Communications in Computer and Information Science, vol 1393. Springer, Singapore. https://doi.org/10.1007/978-981-16-3660-8_19
Download citation
DOI: https://doi.org/10.1007/978-981-16-3660-8_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3659-2
Online ISBN: 978-981-16-3660-8
eBook Packages: Computer ScienceComputer Science (R0)