Machine Learning for Paddy Mapping Based on Agroecological Data and Multispectral Imagery

Riki Ridwana, Muhammad Kamal, Sanjiwana Arjasakusuma

Abstract


Accurate and up-to-date spatial information on paddy cultivation is essential for ensuring national food security, particularly in agrarian countries such as Indonesia. However, conventional mapping approaches often fail to capture spatial heterogeneity driven by diverse agroecological conditions. This study develops a machine learning–based paddy mapping framework by integrating multispectral Sentinel-2 imagery with agroecological variables to improve classification accuracy and model transferability. The analysis incorporates spectral features and vegetation indices derived from Sentinel-2 data, along with environmental variables such as rainfall, elevation, slope, and landform characteristics. Support Vector Machine (SVM) and Random Forest (RF) classifiers were trained and validated using reference data obtained from field surveys and official government records. Model performance was evaluated using confusion matrices, overall accuracy, F1-score, and the Kappa coefficient. Results show that both RF and SVM achieved overall accuracies exceeding 90% when agroecological variables were included, with RF consistently outperforming SVM across all evaluation metrics. The integration of agroecological data significantly improved classification reliability compared to spectral-only approaches, particularly in heterogeneous tropical landscapes. The proposed framework demonstrates strong potential for scalable, transferable agricultural mapping, supporting precision farming, irrigation planning, and sustainable food security management.

Keywords


machine learning; paddy mapping; agroecological; multispectral imagery

Full Text:

PDF

References


Arrafi, M., Somantri, L., and Ridwana, R. (2022). Pemetaan Tingkat Keparahan Kebakaran Hutan dan Lahan Menggunakan Algoritma Normalized Burn Ratio (NBR) Pada Citra Landsat 8 di Kabupaten Muaro Jambi. Jurnal Geosains Dan Remote Sensing, 3(1), 10–19. https://doi.org/10.23960/jgrs.2022.v3i1.68

Belgiu, M. (2016). Random forest in remote sensing: A review of applications and future directions. In ISPRS Journal of Photogrammetry and Remote Sensing (Vol. 114, pp. 24–31). https://doi.org/10.1016/j.isprsjprs.2016.01.011

Belgiu, M. (2018). Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sensing of Environment, 204, 509–523. https://doi.org/10.1016/j.rse.2017.10.005

Chen, Y., Hou, J., Huang, C., Zhang, Y., and Li, X. (2021). Mapping maize area in heterogeneous agricultural landscape with multi-temporal sentinel-1 and sentinel-2 images based on random forest. Remote Sensing. https://www.mdpi.com/2072-4292/13/15/2988

Choudhary, K., Shi, W., Dong, Y., and Paringer, R. (2022). Random Forest for rice yield mapping and prediction using Sentinel-2 data with Google Earth Engine. Advances in Space Research, 70(8), 2443–2457. https://doi.org/https://doi.org/10.1016/j.asr.2022.06.073

Dang, C., Liu, Y., Yue, H., Qian, J. X., and Zhu, R. (2021). Autumn Crop Yield Prediction using Data-Driven Approaches:- Support Vector Machines, Random Forest, and Deep Neural Network Methods. Canadian Journal of Remote Sensing, 47(2), 162–181. https://doi.org/10.1080/07038992.2020.1833186

Dharma, F., Aulia, A., Shubhan, F., and Ridwana, R. (2022). Pemanfaatan Citra Sentinel - 2 Dengan Metode NDVI Untuk Perubahan KerapatanVegetasi Mangrove Di Kabupaten Indramayu. J Pendidikan Geografi Undiksha, 10(2), 155–165.

Dong, J., and Xiao, X. (2016). Evolution of regional to global paddy rice mapping methods: A review. In ISPRS Journal of Photogrammetry and Remote Sensing (Vol. 119, pp. 214–227). Elsevier B.V. https://doi.org/10.1016/j.isprsjprs.2016.05.010

Gaznayee, H. A. A. (2019). Analysis of agricultural drought, rainfall, and crop yield relationships in erbil province, the kurdistan region of iraq based on landsat time-series msavi2. Journal of Advanced Research in Dynamical and Control Systems, 11(12), 536–545. https://doi.org/10.5373/JARDCS/V11SP12/20193249

Gumma, M. K., Thenkabail, P. S., Panjala, P., Teluguntla, P., Yamano, T., and Mohammed, I. (2022). Multiple agricultural cropland products of South Asia developed using Landsat-8 30 m and MODIS 250 m data using machine learning on the Google Earth Engine (GEE) cloud and spectral matching techniques (SMTs) in support of food and water security. GIScience and Remote Sensing, 59(1), 1048–1077. https://doi.org/10.1080/15481603.2022.2088651

HU, Q., WU, W., SONG, Q., LU, M., CHEN, D., YU, Q., and TANG, H. (2017). How do temporal and spectral features matter in crop classification in Heilongjiang Province, China? Journal of Integrative Agriculture, 16(2), 324–336. https://doi.org/https://doi.org/10.1016/S2095-3119(15)61321-1

Jin, S., Yang, L., Zhu, Z., and Homer, C. (2017). A land cover change detection and classification protocol for updating Alaska NLCD 2001 to 2011. Remote Sensing of Environment, 195, 44–55. https://doi.org/10.1016/j.rse.2017.04.021

Kadir, P. :, Jakarta, R., and Juli, I. (2019). Memperbaiki Data Pangan Indonesia Lewat Metode Kerangka Sampel Area.

Khanal, S., Kushal, K. C., Fulton, J. P., Shearer, S., and Ozkan, E. (2020). Remote sensing in agriculture—accomplishments, limitations, and opportunities. In Remote Sensing (Vol. 12, Issue 22, pp. 1–29). MDPI AG. https://doi.org/10.3390/rs12223783

Klerkx, L., Jakku, E., and Labarthe, P. (2019). A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda. NJAS - Wageningen Journal of Life Sciences, 90–91(November), 100315. https://doi.org/10.1016/j.njas.2019.100315

Kumar, S., Mishra, S., Khanna, P., and Pragya. (2017). Precision Sugarcane Monitoring Using SVM Classifier. Procedia Computer Science, 122, 881–887. https://doi.org/10.1016/j.procs.2017.11.450

Lee, R. Y., Chang, K. C., Ou, D. Y., and Hsu, C. H. (2020). Evaluation of crop mapping on fragmented and complex slope farmlands through random forest and object-oriented analysis using unmanned aerial vehicles. Geocarto International, 35(12), 1293–1310. https://doi.org/10.1080/10106049.2018.1559886

Li, D., Yang, F., and Wang, X. (2017). Study on Ensemble Crop Information Extraction of Remote Sensing Images Based on SVM and BPNN. Journal of the Indian Society of Remote Sensing, 45(2), 229–237. https://doi.org/10.1007/s12524-016-0597-y

Li, R. (2021). 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 model. Soil and Tillage Research, 206. https://doi.org/10.1016/j.still.2020.104838

Loebel, E., Scheinert, M., Horwath, M., Heidler, K., Christmann, J., Phan, L. D., ... & Zhu, X. X. (2022). Extracting glacier calving fronts by deep learning: The benefit of multispectral, topographic, and textural input features. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-12.

Menahem, E., Rokach, L., and Elovici, Y. (2009). Troika - An improved stacking schema for classification tasks. Information Sciences, 179(24), 4097–4122. https://doi.org/10.1016/j.ins.2009.08.025

Month, T. (2017). Nmeth.4370. 14(8), 757–759.

Murti, S. (2017). Mapping agroecosystem zone using remote sensing for food security analysis in Bantul district Daerah Istimewa Yogyakarta. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 10421). https://doi.org/10.1117/12.2278011

Murti, S. (2018). Remote sensing and GIS model for food security mapping in Gunungkidul Regency Daerah Istimewa Yogyakarta. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 10777). https://doi.org/10.1117/12.2324029

Nguyen, M. D. (2020). Harmonization of landsat and sentinel 2 for crop monitoring in drought prone areas: Case studies of Ninh Thuan (Vietnam) and Bekaa (Lebanon). Remote Sensing, 12(2). https://doi.org/10.3390/rs12020281

Ni, R., Tian, J., Li, X., Yin, D., Li, J., Gong, H., Zhang, J., Zhu, L., and Wu, D. (2021). An enhanced pixel-based phenological feature for accurate paddy rice mapping with Sentinel-2 imagery in Google Earth Engine. ISPRS Journal of Photogrammetry and Remote Sensing, 178, 282–296. https://doi.org/https://doi.org/10.1016/j.isprsjprs.2021.06.018

Noi, P. T. (2018). Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using sentinel-2 imagery. Sensors (Switzerland), 18(1). https://doi.org/10.3390/s18010018

Opitz, R., De Smedt, P., Mayoral-Herrera, V., Campana, S., Vieri, M., Baldwin, E., Perna, C., Sarri, D., and Verhegge, J. (2023). Practicing Critical Zone Observation in Agricultural Landscapes: Communities, Technology, Environment and Archaeology. Land, 12(1). https://doi.org/10.3390/land12010179

Powers, D. M. W. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. 37–63.

Prasetya, R., and Danoedoro, P. (2019). Paddy and non-paddy crops mapping using multi-temporal data of Sentinel-1A in part of Bantul Regency. Sixth International Symposium on …. https://doi.org/10.1117/12.2540635.short

Putra, M. A. B., Nuarsa, I. W., and Adnyana, I. W. S. (2018). Estimasi Produksi Padi dengan Analisis Citra Satelit Landsat 8 di Kabupaten Klungkung Provinsi Bali. Ecotrophic, 12(1), 93-103.

Ridwana, R., Al Kautsar, A., Saleh, F., Himayah, S., Arrasyid, R., and Pamungkas, T. D. (2022). Spatiotemporal monitoring of rice crops in the covid-19 pandemic period for local food security using sentinel 2b imagery case ctudy: tasikmalaya city. IOP Conference Series: Earth and Environmental Science, 1089(1). https://doi.org/10.1088/1755-1315/1089/1/012039

Ridwana, R., Kamal, M., Arjasakusuma, S., and Rabbi, M. F. A. (2024). Evaluation of Machine Learning Models for Mapping Food Crops using Sentinel-2A Imagery in West Java, Indonesia. E3S Web of Conferences, 600. https://doi.org/10.1051/e3sconf/202460003007

Ridwana, R., Kamal, M., Arjasakusuma, S., Sugandi, D., and Sakti, A. D. (2025). Bibliometric Computation Mapping Analysis of Publication Machine and Deep Learning for Food Crops Mapping using VOSviewer. Journal of Advanced Research in Applied Sciences and Engineering Technology, 50(2), 42–59. https://doi.org/10.37934/araset.50.2.4259

Singh, G., Kalra, N., Yadav, N., Sharma, A., and Saini, M. (2022). Smart Agriculture: a Review. Siberian Journal of Life Sciences and Agriculture, 14(6), 423–454. https://doi.org/10.12731/2658-6649-2022-14-6-423-454

Sisheber, B. (2022). Tracking crop phenology in a highly dynamic landscape with knowledge-based Landsat–MODIS data fusion. International Journal of Applied Earth Observation and Geoinformation, 106. https://doi.org/10.1016/j.jag.2021.102670

SMOLA, A. J., and SCHOLKOPF, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14, 199–222. http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=1CAD92EF8CCE726A305D8A41F873EEFC?doi=10.1.1.114.4288andrep=rep1andtype=pdf%0Ahttp://download.springer.com/static/pdf/493/art%3A10.1023%2FB%3ASTCO.0000035301.49549.88.pdf?auth66=1408162706_8a28764ed0fae9

Song, X. P., Huang, W., Hansen, M. C., and Potapov, P. (2021). An evaluation of Landsat, Sentinel-2, Sentinel-1 and MODIS data for crop type mapping. In Science of Remote Sensing. Elsevier. https://www.sciencedirect.com/science/article/pii/S2666017221000055

Stevens, F. (2015). Disaggregating census data for population mapping using Random forests with remotely-sensed and ancillary data. PLoS ONE, 10(2). https://doi.org/10.1371/journal.pone.0107042

Talaviya, T., Shah, D., Patel, N., Yagnik, H., and Shah, M. (2020). Implementation of artificial intelligence in agriculture for optimisation of irrigation and application of pesticides and herbicides. Artificial Intelligence in Agriculture, 4, 58–73. https://doi.org/https://doi.org/10.1016/j.aiia.2020.04.002

Teluguntla, P., Thenkabail, P., Oliphant, A., Xiong, J., Gumma, M. K., Congalton, R. G., Yadav, K., and Huete, A. (2018). A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform. ISPRS Journal of Photogrammetry and Remote Sensing, 144(February), 325–340. https://doi.org/10.1016/j.isprsjprs.2018.07.017

Todoroff, P., and Kemp, J. (2016). 5 - Contribution of Remote Sensing to Crop Monitoring in Tropical Zones (N. Baghdadi and M. B. T.-L. S. R. S. in A. and F. Zribi, Eds.; pp. 179–220). Elsevier. https://doi.org/https://doi.org/10.1016/B978-1-78548-103-1.50005-4

Tun, S. B. M. (2022). Crop Monitoring of Paddy Field Using Landsat 8 OLI. International Journal of Geoinformatics, 18(4), 35–43. https://doi.org/10.52939/ijg.v18i4.2255

Veloso, A. (2017). Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications. Remote Sensing of Environment, 199, 415–426. https://doi.org/10.1016/j.rse.2017.07.015

Wang, L., Wang, J., Liu, Z., Zhu, J., and Qin, F. (2022). Evaluation of a deep-learning model for multispectral remote sensing of land use and crop classification. The Crop Journal, 10(5), 1435–1451. https://doi.org/https://doi.org/10.1016/j.cj.2022.01.009

Wang, L., Wang, J., Zhang, X., Wang, L., and Qin, F. (2022). Deep segmentation and classification of complex crops using multi-feature satellite imagery. Computers and Electronics in Agriculture, 200, 107249. https://doi.org/https://doi.org/10.1016/j.compag.2022.107249

WANG, W., YAO, X., TIAN, Y. chao, LIU, X. jun, NI, J., CAO, W. xing, and ZHU, Y. (2012). Common Spectral Bands and Optimum Vegetation Indices for Monitoring Leaf Nitrogen Accumulation in Rice and Wheat. Journal of Integrative Agriculture, 11(12), 2001–2012. https://doi.org/10.1016/S2095-3119(12)60457-2

Wang, X., Zhang, J., Xun, L., Wang, J., Wu, Z., Henchiri, M., Zhang, S., Zhang, S., Bai, Y., Yang, S., Li, S., and Yu, X. (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 Sensing, 14(10). https://doi.org/10.3390/rs14102341

Xiong, J., Liu, Z., Chen, S., Liu, B., Zheng, Z., Zhong, Z., Yang, Z., and Peng, H. (2020). Visual detection of green mangoes by an unmanned aerial vehicle in orchards based on a deep learning method. Biosystems Engineering, 194, 261–272. https://doi.org/10.1016/j.biosystemseng.2020.04.006

Yang, Y., Huang, Q., Wu, Z., Wu, T., Luo, J., Dong, W., Sun, Y., Zhang, X., and Zhang, D. (2022). Mapping crop leaf area index at the parcel level via inverting a radiative transfer model under spatiotemporal constraints: A case study on sugarcane. Computers and Electronics in Agriculture, 198, 107003. https://doi.org/https://doi.org/10.1016/j.compag.2022.107003

Yang, Y., and Li, X. (2022). Automatic Correction of Parameters of Rice Phenology Prediction Model Based on Random Forest Algorithm. Procedia Computer Science, 208, 435–441. https://doi.org/https://doi.org/10.1016/j.procs.2022.10.061

Zhang, H., Liu, W., and Zhang, L. (2022). Seamless and automated rapeseed mapping for large cloudy regions using time-series optical satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 184, 45–62. https://doi.org/https://doi.org/10.1016/j.isprsjprs.2021.12.001

Zhang, H., Wang, Y., Shang, J., Liu, M., and Li, Q. (2021). Investigating the impact of classification features and classifiers on crop mapping performance in heterogeneous agricultural landscapes. International Journal of Applied Earth Observation and Geoinformation, 102, 102388. https://doi.org/https://doi.org/10.1016/j.jag.2021.102388

Zhang, W., Liu, H., Wu, W., Zhan, L., and Wei, J. (2020). Mapping rice paddy based on machine learning with sentinel-2 multi-temporal data: Model comparison and transferability. Remote Sensing, 12(10). https://doi.org/10.3390/rs12101620

ZHANG, X., LIU, J., Qin, Z., and QIN, F. (2019). Winter wheat identification by integrating spectral and temporal information derived from multi-resolution remote sensing data. Journal of Integrative Agriculture, 18(11), 2628–2643. https://doi.org/https://doi.org/10.1016/S2095-3119(19)62615-8

Zhao, R., Li, Y., and Ma, M. (2021). Mapping paddy rice with satellite remote sensing: A review. In Sustainability (Switzerland) (Vol. 13, Issue 2, pp. 1–20). MDPI AG. https://doi.org/10.3390/su13020503

Zheng, B., Myint, S. W., Thenkabail, P. S., and Aggarwal, R. M. (2015). A support vector machine to identify irrigated crop types using time-series Landsat NDVI data. International Journal of Applied Earth Observation and Geoinformation, 34(1), 103–112. https://doi.org/10.1016/j.jag.2014.07.002




DOI: https://doi.org/10.17509/gea.v26i1,%20April.89942

DOI (PDF): https://doi.org/10.17509/gea.v26i1.89942.g36238

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.