Palm, Rubber and Rice Crops Classification and Diagnostic Using CNN Approach and NDVI in Thailand

Authors

  • Yannis. Lavigne

    INSA Toulouse, Toulouse Cedex 31077, France
  • Laurent. Mezeix

    Faculty of Engineering, Department of Advanced Materials Engineering, Burapha University, Chonburi 20131, Thailand

DOI:

https://doi.org/10.30564/sadr.v1i1.9564
Received: 11 January 2025 | Revised: 19 February 2025 | Accepted: 26 February 2025 | Published Online: 10 March 2025

Abstract

To support agricultural development in Thailand, accurate data collection and analysis of land use are essential. Understanding the spatial distribution and growth patterns of key crops enables better planning and resource allocation. This study proposes a deep learning-based approach for land cover classification, specifically targeting three significant crops: rice, rubber, and palm. A Convolutional Neural Network (CNN) is employed to classify satellite imagery into these three categories. The datasets used in this research are derived from high-resolution Pleiades satellite imagery and consist of three independent datasets, each containing 200,000 image tiles of 100x100 pixels. For each crop type, a dedicated CNN model are trained and optimized, achieving classification accuracies exceeding 90%. After prediction, a post-processing step is implemented to merge tile-level classifications into continuous land cover maps. This enables a clearer spatial visualization of crop distribution. Furthermore, a clustering algorithm is applied to identify individual agricultural fields, which facilitates further analysis. Vegetation health and maturity are assessed using the Normalized Difference Vegetation Index (NDVI), from which the approximate age of the crops is inferred. These parameters are then used to estimate the potential agricultural yield or production for each field. To validate the approach, a large area of 100 square kilometers is analyzed, and the model’s classification results are compared against manually labeled reference data provided by the Thailand Space Agency. The comparison reveals a classification discrepancy of -12% for palm crops and approximately -20% for both rice and rubber, demonstrating the model's high potential for scalable crop monitoring.

Keywords:

Convolutional Neural Network (CNN); Image Processing; Land Cover; Satellite Image; NDVI

References

[1] UN, 2023. Global Issues Population. Available from: https://www.un.org/en/global-issues/population (cited 10 August 2023).

[2] Griffiths, P., Nendel, C., Hostert, P., 2019. Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping. Remote Sensing of Environment. 220, 135–151. DOI: https://doi.org/10.1016/j.rse.2018.10.031

[3] Palazzi, V., Bonafoni, S., Alimenti, F., et al., 2019. Feeding the world with microwaves: how remote and wireless sensing can help precision agriculture. IEEE Microwave. 20(12), 72–86. DOI: https://doi.org/10.1109/MMM.2019.2941618

[4] Yu, L., Gong, P., Clinton, N., et al., 2014. Meta-discoveries from a synthesis of satellite-based land-cover mapping research. International Journal of Remote Sensing. 35(13), 4573–4588. DOI: https://doi.org/10.1080/01431161.2014.930206

[5] Saah, D., Tenneson, K., Poortinga, A., et al., 2019. Land cover mapping in data scarce environments: challenges and opportunities. Frontiers in Environmental Science. 7, 150. DOI: https://doi.org/10.3389/fenvs.2019.00150

[6] Som-ard, J., Immitzer, M., Vuolo, F., et al., 2022. Mapping of crop types in 1989, 1999, 2009 and 2019 to assess major land cover trends of the Udon Thani Province, Thailand. Computers and Electronics in Agriculture. 198, 107083. DOI: https://doi.org/10.1016/j.compag.2022.107083

[7] Dorber, M., Verones, F., Nakaoka, M., et al., 2020. Can we locate shrimp aquaculture areas from space? – A case study for Thailand. Remote Sensing Applications: Society and Environment. 20, 100416. DOI: https://doi.org/10.1016/j.rsase.2020.100416

[8] Chirachawala, C., Shrestha, S., Babel, M., et al., 2019. Evaluation of global land use/land cover products for hydrologic simulation in the Upper Yom River Basin, Thailand. Science of the Total Environment. 708, 135148. DOI: https://doi.org/10.1016/j.scitotenv.2019.135148

[9] Bouvet, A., Le Toan, T., Lam-Dai, L., et al.., 2018. An above-ground biomass map of African savannahs and woodlands at 25 m resolution derived from ALOS PALSAR. Remote Sensing of Environment. 206, 156–173. DOI: https://doi.org/10.1016/j.rse.2017.12.030

[10] Johnson, D.M., 2019. Using the Landsat archive to map crop cover history across the United States. Remote Sensing of Environment. 232, 111286. DOI: https://doi.org/10.1016/j.rse.2019.111286

[11] Singha, M., Rahman, M., Huete, A., et al., 2020. Identifying floods and flood-affected paddy rice fields in Bangladesh based on Sentinel-1 imagery and Google Earth Engine. ISPRS Journal of Photogrammetry and Remote Sensing. 166, 278–293. DOI: https://doi.org/10.1016/j.isprsjprs.2020.06.011

[12] Yang, H., Pan, B., Li, N., et al., 2021. A systematic method for spatio-temporal phenology estimation of paddy rice using time series Sentinel-1 images. Remote Sensing of Environment. 259, 112394. DOI: https://doi.org/10.1016/j.rse.2021.112394

[13] Zhu, A.X., Zhao, F.H., Pan, H.B., et al., 2021. Mapping rice paddy distribution using remote sensing by coupling deep learning with phenological characteristics. Remote Sensing. 13(7), 71360. DOI: https://doi.org/10.3390/rs13071360

[14] Watanabe, F., Tani, H., Wang, X., et al., 2020. Inland water’s trophic status classification based on machine learning and remote sensing data. Remote Sensing Applications: Society and Environment. 19, 100326. DOI: https://doi.org/10.1016/j.rsase.2020.100326.

[15] Yoo, C., Han, D., Im, J., et al., 2019. Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images. ISPRS Journal of Photogrammetry and Remote Sensing. 157, 155–170. DOI: https://doi.org/10.1016/j.isprsjprs.2019.09.009

[16] Panahi, M., Sadhasivam, N., Pourghasemi, H.R., et al., 2020. Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). Journal of Hydrology. 588, 125033. DOI: https://doi.org/10.1016/j.jhydrol.2020.125033

[17] Li, W., Chen, C., Zhang, M., et al., 2019. Data augmentation for hyperspectral image classification with deep CNN. IEEE Geoscience and Remote Sensing Letters. 16(4), 593–597. DOI: https://doi.org/10.1109/LGRS.2018.2878773

[18] Guo, Y., Liu, Y., Wang, L., et al., 2020. Plant disease identification based on deep learning algorithm in smart farming. Discrete Dynamics in Nature and Society. 2020(1), 2479172. DOI: https://doi.org/10.1155/2020/2479172

[19] Kanda, P.S., Xia, K., Sanusi, O.H., 2021. A deep learning-based recognition technique for plant leaf classification. IEEE Access. 9, 162590–162613. DOI: https://doi.org/10.1109/ACCESS.2021.3131726

[20] Olsen, A., Konovalov, D.A., Philippa, B., et al., 2019. DeepWeeds: a multiclass weed species image dataset for deep learning. Scientific Reports. 9(1), 3843. DOI: https://doi.org/10.1038/s41598-018-38343-3

[21] Kipli, K., Dahlan, M.R., Rahman, A.A., et al., 2023. Deep learning applications for oil palm tree detection and counting. Smart Agricultural Technology. 5, 100241. DOI: https://doi.org/10.1016/j.atech.2023.100241

[22] Thorp, K.R., Drajat, D., 2021. Deep machine learning with Sentinel satellite data to map paddy rice production stages across West Java, Indonesia. Remote Sensing of Environment. 265, 112679. DOI: https://doi.org/10.1016/j.rse.2021.112679

[23] Yan, C., Li, Z., Zhang, Z., et al., 2023. High-resolution mapping of paddy rice fields from unmanned airborne vehicle images using enhanced-TransUnet. Computers and Electronics in Agriculture. 210, 107867. DOI: https://doi.org/10.1016/j.compag.2023.107867

[24] Xia, L., Zhang, Y., Liu, S., et al., 2022. A full resolution deep learning network for paddy rice mapping using Landsat data. ISPRS Journal of Photogrammetry and Remote Sensing. 194, 91–107. DOI: https://doi.org/10.1016/j.isprsjprs.2022.10.005

[25] Mentet, M., Hongkarnjanakul, N., Schwob, C., et al., 2022. Method to apply and visualize physical models associated to a land cover performed by CNN: a case study of vegetation and water cooling effect in Bangkok, Thailand. Remote Sensing Applications: Society and Environment. 28, 100856. DOI: https://doi.org/10.1016/j.rsase.2022.100856

[26] Jinru, X., Su, B., 2017. Significant remote sensing vegetation indices: a review of developments and applications. Journal of Sensors. 2017, 1–17. DOI: https://doi.org/10.1155/2017/1353691

[27] Huete, A.R., 2004. 11 - Remote sensing for environmental monitoring. In: Artiola, J.F., Pepper, I.L., Brusseau, M.L. (eds.). Environmental Monitoring and Characterization. Academic Press: Burlington, MA, USA. pp. 183–206. DOI: https://doi.org/10.1016/B978-012064477-3/50013-8

[28] Bhandari, A., Kumar, A., Singh, G.K., 2012. Feature extraction using normalized difference vegetation index (NDVI): a case study of Jabalpur City. Procedia Technology. 6, 612–621. DOI: https://doi.org/10.1016/j.protcy.2012.10.074

[29] Rahmanida, Y., Shidiq, I.P.A., Rokhmatuloh, et al., 2021. Spatial distribution of rice productivity utilizes Sentinel-2A and NDVI algorithm in Nagrak Sub-district, Sukabumi Regency. Proceedings of The International Conference on Environment, Sustainability Issues, and Community Development; October 21, 2020; Semarang, Indonesia. pp. 1–6. DOI: https://doi.org/10.1088/1755-1315/623/1/012037

[30] Marzukhi, F., Elahami, A., Bohari, S., 2016. Detecting nutrients deficiencies of oil palm trees using remotely sensed data. Proceedings of The 8th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing (IGRSM 2016); April 13–14, 2016; Kuala Lumpur, Malaysia. pp. 1–11. DOI: https://doi.org/10.1088/1755-1315/37/1/012040

[31] Chen, G., Thill, J.C., Anantsuksomsri, S., et al., 2018. Stand age estimation of rubber (Hevea brasiliensis) plantations using an integrated pixel- and object-based tree growth model and annual Landsat time series. ISPRS Journal of Photogrammetry and Remote Sensing. 144, 94–104. DOI: https://doi.org/10.1016/j.isprsjprs.2018.07.003

[32] Fitton, D., Laurens, E., Hongkarnjanakul, N., et al., 2022. Land cover classification through convolutional neural network model assembly: a case study of a local rural area in Thailand. Remote Sensing Applications: Society and Environment. 26, 100740. DOI: https://doi.org/10.1016/j.rsase.2022.100740

[33] Sangbuapuan, N., 2013. Strengthening the rice production in Thailand through Community Rice Centers (CRCs) using ICT policies. Proceedings of The 2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS); June 16–20, 2013; Niigata, Japan. pp. 553–558. DOI: https://doi.org/10.1109/ICIS.2013.6607899

[34] Ritchie, H., Roser, M., 2021. Forests and deforestation. Our World in Data. Available from: https://ourworldindata.org/palm-oil (cited 7 September 2023).

[35] Statista, 2023. Statista – The Statistics Portal. Available from: https://www.statista.com/ (cited 25 August 2023).

[36] Chermprayong, P., Hongkarnjanakul, N., Rouquette, D., et al., 2021. Convolutional neural network for Thailand’s Eastern Economic Corridor (EEC) land cover classification using overlapping process on satellite images. Remote Sensing Applications: Society and Environment. 23, 100543. DOI: https://doi.org/10.1016/j.rsase.2021.100543

[37] Emparanza, P.R., Hongkarnjanakul, N., Rouquette, D., et al., 2020. Land cover classification in Thailand’s Eastern Economic Corridor (EEC) using convolutional neural network on satellite images. Remote Sensing Applications: Society and Environment. 20, 100394. DOI: https://doi.org/10.1016/j.rsase.2020.100394

[38] Sentagne, T., Zerbola, M., Garcia, M., et al., 2023. Method to map human and infrastructure vulnerability using CNN land cover: case study of floating tank explosion at petrochemical plants of Laem Chabang, Thailand. Journal of Loss Prevention in the Process Industries. 83, 105057. DOI: https://doi.org/10.1016/j.jlp.2023.105057

[39] Marty, B., Gaudin, R., Piperno, T., et al., 2024. Methodology to classify high voltage transmission poles using CNN approach from satellite images for safety public regulation application: Study case of rural area in Thailand. Systems and Soft Computing. 6, 200080. DOI: https://doi.org/10.1016/j.sasc.2024.200080

[40] Xie, J., Hu, K., Guo, Y., et al., 2021. On loss functions and CNNs for improved bioacoustic signal classification. Ecological Informatics. 64, 101331. DOI: https://doi.org/10.1016/j.ecoinf.2021.101331

[41] Hasan, F., Ali, M., Rahman, M., 2011. A digital approach of satellite image processing for retrieving surface parameters. International Journal of Engineering Research and Applications. 1, 1242–1246.

[42] Peters, A.J., Walter-Shea, E., Ji, L., et al., 2002. Drought monitoring with NDVI-based Standardized Vegetation Index. Photogrammetric Engineering and Remote Sensing. 68, 71–75.

[43] Supriatna, S., Rokhmatuloh, R., Wibowo, A., et al., 2020. Rice productivity estimation by Sentinel-2A imagery in Karawang Regency, West Java, Indonesia. International Journal of GEOMATE. 19, 205–210. DOI: https://doi.org/10.21660/2020.72.5622

[44] Dipa, P., 2012. data time series NDVI-SPOT VEGETATION for rice plants[In Indonesian], [Undergraduate Thesis]. Bogor, Indonesia: Bogor Agricultural University (IPB). pp. 1–31.

[45] Orawan, S., 2023. Rice economy in Northeast Thailand: current status and challenges. FFTC Agricultural Policy Platform (FFTC-AP). Available from: https://ap.fftc.org.tw/article/1863 (cited 7 September 2023).

[46] Fitrianto, A., Tokimatsu, K., Wijaya, M.S., 2017. Estimation the amount of oil palm trees production using remote sensing technique. Proceedings of The 5th Geoinformation Science Symposium 2017 (GSS 2017); September 27–28, 2017, Yogyakarta, Indonesia. pp. 1–7. DOI: https://doi.org/10.1088/1755-1315/98/1/012016

[47] Chemura, A., van Duren, I., van Leeuwen, L.M., 2015. Determination of the age of oil palm from crown projection area detected from WorldView-2 multispectral remote sensing data: the case of Ejisu-Juaben district, Ghana. ISPRS Journal of Photogrammetry and Remote Sensing. 100, 118–127. DOI: https://doi.org/10.1016/j.isprsjprs.2014.07.013

[48] Xu, J., Yi, Z.F., 2015. Socially Constructed Rubber Plantations in the Swidden Landscape of Southwest China. In: Fox, J., Castella, J.C., Ziegler, A.D. (eds.). Shifting Cultivation and Environmental Change. Routledge: London, UK. pp. 794–810.

[49] Olson, D., Delen, D., 2008. Advanced Data Mining Techniques. Springer: Berlin, Germany. pp. 1–180. DOI: https://doi.org/10.1007/978-3-540-76917-0

[50] Lu, R., Zhang, Y., Huang, Q., et al., 2024. A refined edge-aware convolutional neural networks for agricultural parcel delineation. International Journal of Applied Earth Observation and Geoinformation. 133, 104084.

[51] Liu, Z., Li, J., Ashraf, M., et al., 2024. Remote sensing-enhanced transfer learning approach for agricultural damage and change detection: a deep learning perspective. Big Data Research. 36, 100449.

[52] Dong, R., Li, J., Zhang, Y., et al., 2020. Oil palm plantation mapping from high-resolution remote sensing images using deep learning. International Journal of Remote Sensing. 41(5), 2022–2046. DOI: https://doi.org/10.1080/01431161.2019.1681604

Downloads

How to Cite

Lavigne, Y., & Mezeix, L. (2025). Palm, Rubber and Rice Crops Classification and Diagnostic Using CNN Approach and NDVI in Thailand. Southeast Asia Development Research, 1(1), 31–46. https://doi.org/10.30564/sadr.v1i1.9564

Issue

Vol. 1 , Iss. 1 (May 2025)

Article Type

Articles

License

Copyright © 2025 Yannis. Lavigne, Laurent. Mezeix

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.